Intelligent early warning and measurement and control system and method for safety state of distribution network grounding operation

Abstract

The application discloses a distribution network grounding operation safety state intelligent early warning and measurement and control system and method. The system comprises an intelligent wiring clamp, an intelligent grounding needle and a visual monitoring platform; the intelligent wiring clamp is integrated with a pressure sensing module for sensing the hanging state of the intelligent wiring clamp and a conductor, a positioning module for positioning the grounding point space, and a security authentication module for device identity authentication; the intelligent grounding needle is integrated with a posture sensing module for monitoring the burying posture of the grounding needle, a depth measuring module for measuring the burying depth of the intelligent grounding needle, and a vibration sensing module for identifying the impact characteristics in the burying process of the intelligent grounding needle; the visual monitoring platform is used for receiving the multi-modal sensing data uploaded by the intelligent wiring clamp and the intelligent grounding needle, and diagnosing and warning the grounding operation state according to the multi-modal sensing data. The application improves the safety of power system operation and maintenance by constructing an end-edge-cloud collaborative system architecture.

Description

Technical Field

[0001] This application belongs to the field of power system operation and maintenance safety technology, and in particular relates to an intelligent early warning and monitoring system and method for the safety status of distribution network grounding operations. Background Technology

[0002] During planned power grid outages for maintenance, connecting grounding wires is a core technical measure to ensure the safety of workers. It releases residual charge on the lines, shields against induced current, and prevents accidental energization. However, traditional grounding wire operation relies entirely on manual experience, resulting in two major management blind spots: Process black box: Back-end administrators cannot remotely and in real-time perceive the true status of grounding operations. The lack of critical quality information, such as whether the clamps are reliably connected (whether there is "virtual connection") and whether the depth and angle of the grounding pin are compliant, can easily lead to serious misoperations such as missed connection, missed removal, or incorrect connection, causing personal electric shock accidents.

[0003] Out of control: The existing model is unable to effectively verify the core compliance requirement of "a designated device performing a designated task at a designated location".

[0004] Currently, although there are grounding wire management systems based on RFID (Radio Frequency Identification), they can only realize electronic ledgers for asset issuance and return, and cannot sense the quality of connection and precise location, let alone monitor the status of grounding pins. Therefore, there is an urgent need for a safety management and control technology solution that can realize transparency, intelligence, and traceability throughout the entire grounding operation process to improve the safety of power system operation and maintenance. Summary of the Invention

[0005] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes an intelligent early warning and monitoring system and method for the safety status of power distribution network grounding operations, in order to improve the safety of power system operation and maintenance.

[0006] In the first aspect, this application provides an intelligent early warning and monitoring system for the safety status of distribution network grounding operations, including: intelligent clamps, intelligent grounding pins, and a visual monitoring platform; The intelligent connector integrates a pressure sensing module for sensing the connection status between the intelligent connector and the wire, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification. The smart grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial attitude, a depth measurement module for measuring the burial depth of the smart grounding pin, and a vibration sensing module for identifying the impact characteristics of the smart grounding pin's burial process. The visualization monitoring platform is used to receive multimodal sensing data uploaded by the smart connector and the smart grounding pin, and to diagnose and warn of the grounding operation status based on the multimodal sensing data.

[0007] The intelligent early warning and monitoring system for the safety status of distribution network grounding operations according to this application constructs an end-edge-cloud collaborative system architecture including intelligent clamps, intelligent grounding pins, and a visual monitoring platform. The intelligent clamps integrate pressure sensing, positioning, and safety authentication modules, enabling the perception and authentication of clamp connection status, grounding point spatial location, and equipment identity. The intelligent grounding pins integrate attitude sensing, depth measurement, and vibration sensing modules, enabling comprehensive monitoring of the grounding pin's burial attitude, burial depth, and burial impact characteristics. The visual monitoring platform centrally receives multimodal sensor data and performs comprehensive diagnosis and early warning. This upgrades the human-based grounding operation model, which relies on personnel responsibility, to a technology-based model based on multiple technical verifications, fundamentally reducing safety accidents caused by human error. It achieves remote visibility, process traceability, status verification, and risk control in grounding operations, improving the safety of power system operation and maintenance.

[0008] According to one embodiment of this application, the visualization monitoring platform is further used for: Construct a digital twin model of the grounding operation scenario, and visualize the diagnosis and early warning results of the grounding operation status in a 3D geographic information system.

[0009] In this embodiment, the operation status is visualized by using digital twin and three-dimensional geographic information system technology, enabling operation and maintenance personnel to intuitively grasp the information of the entire grounding operation process. This reduces the safety hazards caused by subjective judgment errors, inspection omissions, and unintuitive operation status information in manual operation. The grounding operation process is visualized and traceable, and operation and maintenance personnel do not need to be on-site to supervise, which further improves the safety and work efficiency of power system operation and maintenance.

[0010] According to one embodiment of this application, the pressure sensing module includes a multi-node pressure sensor array with a distributed layout, used to collect pressure distribution data of the contact area between the smart connector and the wire; the security authentication module includes a security chip compliant with national cryptographic algorithms, used to store the device's unique identifier and encrypt the transmitted data.

[0011] In this embodiment, by employing a distributed multi-node pressure sensor array, pressure distribution data of the contact area between the clamp and the wire can be collected, thereby more accurately determining the tightness of the connection between the clamp and the wire. The security authentication module is equipped with a security chip that conforms to the national cryptographic algorithm. By storing the unique identity of the device and encrypting the transmitted data, reliable authentication of the device identity and secure protection of data transmission can be achieved.

[0012] According to one embodiment of this application, the attitude sensing module includes an attitude sensor; the depth measurement module includes a laser rangefinder, the detection end of which is provided with a self-cleaning air curtain window; and the vibration sensing module includes a vibration sensor.

[0013] In this embodiment, an attitude sensor is used to monitor the attitude changes of the grounding pin in real time during the burial process, which facilitates the analysis of the burial angle and direction of the grounding pin; the depth measurement module uses a laser rangefinder sensor and has a self-cleaning air curtain window at the detection end, which can not only accurately measure the burial depth of the grounding pin, but also reduce the interference of dust and impurities on the measurement accuracy through the self-cleaning air curtain window, thereby improving the accuracy of the measurement data; the vibration sensing module uses a vibration sensor to identify the impact characteristics of the grounding pin during the burial process, and by analyzing the vibration data, it can be determined whether the grounding pin has encountered underground obstacles or abnormal conditions.

[0014] According to one embodiment of this application, the visualization monitoring platform includes a data receiving module, a data fusion analysis module, a digital twin construction module, and an early warning push module; the data fusion analysis module has a built-in multi-sensor data fusion algorithm, which includes at least one of DS evidence theory, support vector machine, convolutional neural network, and hidden Markov model.

[0015] In this embodiment, the data fusion analysis module has a built-in multi-sensor data fusion algorithm, which can integrate multi-modal sensor data from smart clamps and smart grounding pins. Through data fusion processing, it not only improves the accuracy of the data, but also enhances the comprehensive analysis capability for complex grounding operation scenarios, and can more comprehensively reflect the actual status of grounding operations. The digital twin construction module can deeply integrate the digital twin model of the grounding operation scenario with real-time monitoring data, providing a visual interface for operation and maintenance personnel; the early warning push module can push early warning information to operation and maintenance personnel based on the diagnostic results of the data fusion analysis module, reducing the risk of accidents.

[0016] According to one embodiment of this application, the data fusion analysis module is used to extract features from the pressure distribution data collected by the pressure sensing module through a convolutional neural network to identify the connection status of the smart connector; the connection status includes reliable connection, false connection, or no connection; and to verify whether the connection position of the smart connector is within the geofence range specified by the electronic work order based on the positioning data of the positioning module, and generate evaluation information for the smart connector.

[0017] In this embodiment, a convolutional neural network is used to extract features from the pressure distribution data collected by the pressure sensing module to identify the reliable, loose, or unattached status of the smart connector, thus improving the accuracy of the attachment status monitoring. The positioning data from the positioning module verifies whether the attachment position of the smart connector conforms to the geofence specified in the electronic work order and generates assessment information. This reduces safety hazards and maintenance risks caused by incorrect attachment positions. The assessment information combines dual verification of attachment status and geographical location, further improving the accuracy of the smart connector status assessment and enhancing the standardization and safety of the operation process.

[0018] According to one embodiment of this application, the data fusion analysis module is used to model the time-series data collected by the attitude sensing module, depth measurement module and vibration sensing module using a hidden Markov model, identify the embedding process of the smart grounding pin and determine the embedding quality of the smart grounding pin, and generate evaluation information of the smart grounding pin.

[0019] In this embodiment, the time-series data collected by the attitude sensing module, depth measurement module, and vibration sensing module of the smart grounding pin are modeled and analyzed using a hidden Markov model. This allows for the extraction of dynamic change characteristics of the sensor data and the capture of the state transition process during the burial of the grounding pin. Consequently, the state of the smart grounding pin during the entire process of preparation, burial, and placement can be accurately identified, thereby enabling the assessment of the burial quality of the grounding pin and the determination of the grounding safety status.

[0020] According to one embodiment of this application, the data fusion analysis module is used to perform uncertainty reasoning on the evaluation information of the smart connector and the evaluation information of the smart grounding pin using DS evidence theory, and output the evaluation conclusion of the grounding operation status.

[0021] In this embodiment, uncertainty reasoning is performed by connecting the evaluation information of the smart clamp and the smart grounding pin through DS evidence theory. This fully considers the reliability and uncertainty of evaluation information from different sensor modules. By reasonably allocating trust levels and conflict handling mechanisms, comprehensive analysis and reasoning are performed on each evaluation information, reducing the limitations and inaccuracies of a single information source, thereby obtaining a more reliable grounding operation status evaluation conclusion.

[0022] According to one embodiment of this application, the early warning push module is used to assess the risk level of the abnormality when there is an abnormality in the grounding operation status, and push alarm information using a push method corresponding to the risk level; the push method includes at least one of the interface pop-up of the visualization monitoring platform, SMS and mobile terminal.

[0023] In this embodiment, through a graded early warning mechanism, when an abnormality is detected in the grounding operation status, the risk level can be assessed, and the corresponding push method can be selected according to the risk level to push the alarm information to the operation and maintenance personnel, thereby improving the efficiency of alarm information push.

[0024] Secondly, this application provides an intelligent early warning and monitoring method for the safety status of distribution network grounding operations, applied to a visual monitoring platform, the method comprising: Through various modules of the intelligent connector and intelligent grounding pin, multimodal sensing data is collected in real time during the grounding operation. Among them, the intelligent connector integrates a pressure sensing module for sensing the connection status between the intelligent connector and the conductor, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification. The intelligent grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial attitude, a depth measurement module for measuring the burial depth of the intelligent grounding pin, and a vibration sensing module for identifying the impact characteristics of the intelligent grounding pin during the burial process. Diagnosis and early warning of grounding operation status are performed based on the multimodal sensing data.

[0025] According to the intelligent early warning and monitoring method for the safety status of distribution network grounding operations proposed in this application, an end-edge-cloud collaborative system architecture is constructed, including intelligent clamps, intelligent grounding pins, and a visual monitoring platform. The intelligent clamps integrate pressure sensing, positioning, and safety authentication modules, enabling the perception and authentication of clamp connection status, grounding point spatial location, and equipment identity. The intelligent grounding pins integrate attitude sensing, depth measurement, and vibration sensing modules, enabling comprehensive monitoring of the grounding pin's burial attitude, burial depth, and burial impact characteristics. The visual monitoring platform centrally receives multimodal sensor data and performs comprehensive diagnosis and early warning. This upgrades the human-based grounding operation model, which relies on personnel responsibility, to a technically-based model based on multiple technology verifications, fundamentally reducing safety accidents caused by human error. It achieves remote visibility, process traceability, status verification, and risk control in grounding operations, thereby improving the safety of power system operation and maintenance.

[0026] According to one embodiment of this application, the method further includes: Construct a digital twin model of the grounding operation scenario, and visualize the diagnosis and early warning results of the grounding operation status in a 3D geographic information system.

[0027] According to one embodiment of this application, the diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: The pressure distribution data collected by the pressure sensing module is processed by a convolutional neural network to extract features and identify the connection status of the smart connector. The connection status includes reliable connection, loose connection, or no connection. The system also verifies whether the connection position of the smart connector is within the geofence specified by the electronic work order based on the positioning data of the positioning module, and generates evaluation information for the smart connector.

[0028] According to one embodiment of this application, the diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: The timing data collected by the attitude sensing module, depth measurement module, and vibration sensing module are modeled using a hidden Markov model to identify the embedding process of the smart grounding pin, determine the embedding quality of the smart grounding pin, and generate evaluation information for the smart grounding pin.

[0029] According to one embodiment of this application, the diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: The DS evidence theory is used to perform uncertainty reasoning on the evaluation information of the smart connector and the smart grounding pin, and the evaluation conclusion of the grounding operation status is output.

[0030] According to one embodiment of this application, the diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: If an anomaly exists in the grounding operation status, assess the risk level of the anomaly; Alarm information is pushed using the push method corresponding to the risk level; the push method includes at least one of the interface pop-up of the visualization monitoring platform, SMS and mobile terminal.

[0031] Thirdly, this application provides an intelligent early warning and monitoring device for the safety status of distribution network grounding operations, applied to a visual monitoring platform, the device comprising: The data acquisition module is used to collect multimodal sensing data in real time during the grounding operation through various modules of the smart clamp and the smart grounding pin. The smart clamp integrates a pressure sensing module for sensing the connection status between the smart clamp and the conductor, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification. The smart grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial posture, a depth measurement module for measuring the burial depth of the smart grounding pin, and a vibration sensing module for identifying the impact characteristics of the smart grounding pin during burial. The diagnosis and early warning module is used to diagnose and warn of the grounding operation status based on the multimodal sensing data.

[0032] Fourthly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent early warning and monitoring method for the safety status of distribution network grounding operations as described in the second aspect above.

[0033] Fifthly, this application provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the intelligent early warning and monitoring method for the safety status of distribution network grounding operations as described in the second aspect above.

[0034] Sixthly, this application provides a chip, which includes a processor and a communication interface, the communication interface being coupled to the processor, and the processor being used to run programs or instructions to implement the intelligent early warning and monitoring method for the safety status of distribution network grounding operations as described in the second aspect above.

[0035] The above-described one or more technical solutions in the embodiments of this application have at least the following technical effects: The intelligent early warning and monitoring system for the safety status of distribution network grounding operations according to this application constructs an end-edge-cloud collaborative system architecture including intelligent clamps, intelligent grounding pins, and a visual monitoring platform. The intelligent clamps integrate pressure sensing, positioning, and safety authentication modules, enabling the perception and authentication of clamp connection status, grounding point spatial location, and equipment identity. The intelligent grounding pins integrate attitude sensing, depth measurement, and vibration sensing modules, enabling comprehensive monitoring of the grounding pin's burial attitude, burial depth, and burial impact characteristics. The visual monitoring platform centrally receives multimodal sensor data and performs comprehensive diagnosis and early warning. This upgrades the human-based grounding operation model, which relies on personnel responsibility, to a technology-based model based on multiple technical verifications, fundamentally reducing safety accidents caused by human error. It achieves remote visibility, process traceability, status verification, and risk control in grounding operations, improving the safety of power system operation and maintenance.

[0036] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0037] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1This is a schematic diagram of the module structure of the intelligent early warning and monitoring system for the safety status of distribution network grounding operations provided in this application embodiment; Figure 2 This is a schematic diagram of the layered architecture of the intelligent early warning and monitoring system for the safety status of distribution network grounding operations provided in this application embodiment; Figure 3 This is a flowchart illustrating the intelligent early warning and monitoring method for the safety status of distribution network grounding operations provided in this application embodiment; Figure 4 This is a schematic diagram of the intelligent early warning and monitoring device for the safety status of power distribution grounding operations provided in this application embodiment; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0040] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0041] In distribution network operation and maintenance, grounding work is a crucial step in ensuring the personal safety of maintenance personnel. The quality of grounding work directly impacts the safety of workers and the stable operation of the power system. Traditional distribution network grounding work relies on manual judgment to determine whether the clamps are securely attached and whether the grounding pins are properly buried. The process lacks real-time monitoring, leading to safety hazards such as insecure connections, insufficient grounding pin depth, and abnormal posture. Furthermore, the work status cannot be remotely tracked, increasing the risk of electric shock and other accidents due to human negligence. Therefore, this application provides an intelligent early warning and monitoring system and method for the safety status of distribution network grounding work.

[0042] In the embodiments of this application, the intelligent early warning and monitoring system and method for the safety status of distribution network grounding operations can be applied to various grounding operation scenarios such as equipment maintenance, line fault handling, and commissioning of new equipment in distribution networks.

[0043] The intelligent early warning and monitoring system and method for the safety status of distribution network grounding operations provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0044] like Figure 1 As shown, this application provides an intelligent early warning and monitoring system for the safety status of distribution network grounding operations, including: an intelligent clamp 110, an intelligent grounding pin 120, and a visual monitoring platform 130; The intelligent connector 110 integrates a pressure sensing module 111 for sensing the connection status between the intelligent connector and the wire, a positioning module 112 for spatial positioning of the grounding point, and a security authentication module 113 for device identity authentication. The smart grounding pin 120 integrates an attitude sensing module 121 for monitoring the grounding pin's burial attitude, a depth measuring module 122 for measuring the smart grounding pin's burial depth, and a vibration sensing module 123 for identifying the impact characteristics of the smart grounding pin's burial process. The visualization monitoring platform 130 is used to receive multimodal sensing data uploaded by smart clamps and smart grounding pins, and to diagnose and warn of the grounding operation status based on the multimodal sensing data.

[0045] In the power system operation and maintenance safety technology system, terminal clamps are specialized node devices for connecting, branching, and grounding conductors in the power system. Through the synergistic effect of mechanical structure and conductive materials, terminal clamps achieve reliable electrical connections between two or more conductors, and between conductors and equipment terminals, meeting the dual requirements of mechanical fixation and electrical conductivity. Functionally, terminal clamps ensure the continuity of power transmission by reducing contact resistance and minimizing power loss, thus preventing faults such as localized overheating and spark discharge caused by poor connections. Terminal clamps also improve the convenience of operation and maintenance, enabling connection and disassembly without complex processing of conductors, thereby improving the efficiency of line erection, maintenance, and modification. Furthermore, terminal clamps enhance the safety of power system operation by resisting external environmental interference and preventing accidental electric shock or short circuit accidents through structural features such as insulation protection and anti-loosening design.

[0046] Terminal clamps typically consist of a conductive body, a mechanical clamping mechanism, an insulating protective layer, and connecting accessories. Different types of terminal clamps differ in structural details to suit different application scenarios.

[0047] In this embodiment, the intelligent connector 110, in addition to adopting a mechanical structure similar to that of a conventional connector, also integrates multiple functional modules such as a pressure sensing module 111, a positioning module 112, and a safety authentication module 113, thus integrating mechanical connection with intelligent sensing and realizing a technological upgrade from passive connection to active sensing.

[0048] Among them, the pressure sensing module 111 is a functional module of the intelligent connector 110 that realizes the monitoring of the wiring status. The working principle of the pressure sensing module 111 is to collect the contact pressure data between the connector and the wire through the built-in high-precision pressure sensor, and convert the pressure data into an electrical signal. This electrical signal can be transmitted to the visual monitoring platform 130. The visual monitoring platform 130 can determine the wiring is not secure when the pressure value is lower than the preset threshold based on the dynamic changes of the contact pressure captured by the pressure sensing module 111, and provide an immediate warning to the operator.

[0049] The positioning module 112 is used to achieve spatial positioning of the grounding point. It can integrate a GNSS (Global Navigation Satellite System) positioning chip and acquire the latitude and longitude coordinates of the smart junction box 110 in real time through the BeiDou positioning system, GPS (Global Positioning System), etc., and combine it with a timestamp to form data that includes location and time association. In distribution network grounding operations, the selection of the grounding point must strictly follow the power safety regulations and must be located within the work geofence specified in the work order. The location data collected by the positioning module 112 can provide the spatial location of the grounding point for the visualization monitoring platform 130, which facilitates the remote verification of whether the grounding point meets the requirements of the regulations by the background management personnel. It can also be associated with the distribution network geographic information system (GIS) to realize the visual marking of the grounding point on the electronic map, providing data support for the traceability and management of the operation process.

[0050] The security authentication module 113 is used for device identity authentication. It can achieve two-way authentication between the smart connector 110 and the visual monitoring platform 130 by adopting a device identity authentication mechanism based on encryption algorithms. The security authentication module 113 can have a unique device identity identifier built in. When the device (smart connector 110) is started and connected to the system, it sends an authentication request containing the device identity identifier and encrypted information to the visual monitoring platform 130. After the visual monitoring platform 130 authenticates the device, it allows the smart connector 110 to access the system and transmit data.

[0051] In power system operation and maintenance, grounding pins complement the circuit connection function of terminal clamps. One end of the grounding pin is inserted into the earth, and the other end is connected to the grounding trunk line or equipment grounding terminal. It is used to conduct unsafe currents such as equipment fault current and lightning impulse current to the earth. When equipment experiences faults such as insulation breakdown, the grounding pin quickly conducts the fault current to the earth through a low-impedance circuit, triggering the relay protection device to operate and preventing the fault from escalating. When subjected to lightning impulses or system overvoltage during operation, the grounding pin can dissipate the overvoltage energy and prevent the equipment insulation from being broken down.

[0052] A grounding pin typically includes a pin body, connecting terminals, and auxiliary installation components. The pin body can be made of hot-dip galvanized round steel, copper-clad steel, or copper alloy. One end of the pin body is machined into a pointed cone shape to reduce soil insertion resistance, while the other end has a threaded or flanged connection structure to facilitate connection with the grounding main line by welding or bolting.

[0053] In this embodiment, the smart grounding needle 120, in addition to adopting a mechanical structure similar to that of a conventional grounding needle, also integrates multiple functional modules such as an attitude sensing module 121, a depth measurement module 122, and a vibration sensing module 123, thereby enabling comprehensive perception of the burying process of the smart grounding needle 120.

[0054] The attitude sensing module 121 is used to monitor the embedding attitude of the smart grounding pin 120 in real time. Through its built-in gyroscope and accelerometer, the attitude sensing module 121 can collect data on the tilt angle and attitude changes of the grounding pin in three-dimensional space. According to power safety regulations, the embedding attitude of the grounding pin must meet vertical or specific tilt angle requirements. Excessive attitude deviation will lead to increased grounding resistance and reduced grounding protection effectiveness. The attitude sensing module 121 can capture the attitude parameters of the grounding pin in real time and send them to the visualization monitoring platform 130. When the tilt angle exceeds a preset threshold based on the attitude parameters, an abnormal attitude signal can be generated, reminding the operator to adjust the grounding pin attitude in a timely manner.

[0055] The depth measurement module 122 can use ultrasonic ranging or infrared ranging technology to collect data on the depth of the smart grounding pin 120 buried below the ground surface. The burial depth of the smart grounding pin 120 is a key factor determining the grounding resistance; insufficient depth will cause the grounding resistance to exceed safety standards, failing to effectively discharge fault current and thus posing a safety risk. The depth measurement module 122 can send the collected depth data to the visualization monitoring platform 130. The visualization monitoring platform 130 can compare the depth data with a preset safe depth threshold in real time. When the actual burial depth does not meet the safe depth threshold requirement, it sends a depth insufficient warning signal.

[0056] The vibration sensing module 123 is used to identify the impact characteristics of the smart grounding pin 120 during its burial process. The vibration sensing module 123 can collect characteristic parameters such as vibration frequency, amplitude, and duration of the grounding pin during the hammering burial process. The burial impact characteristics of the smart grounding pin 120 can indirectly reflect the burial geological conditions and the degree of burial stability. For example, under hard geological conditions, the impact vibration frequency will be higher than in soft geological conditions, and abnormal impact amplitude indicates that the smart grounding pin 120 may have encountered underground obstacles, causing burial obstruction. The vibration sensing module 123 can send the collected vibration characteristic parameters to the visualization monitoring platform 130. The visualization monitoring platform 130 can determine whether the burial process is abnormal by analyzing the impact characteristic parameters, and if an abnormality is detected, it will issue a prompt to the operators.

[0057] The Visual Monitoring Platform 130 is the system's data processing and management center, integrating multiple functions such as data reception, storage, analysis, diagnosis, early warning, and visualization. It can realize the diagnosis and early warning of the entire grounding operation process.

[0058] During data processing, the visualization monitoring platform 130 can preprocess the received multimodal sensor data, including data cleaning, format conversion, and outlier removal, eliminating invalid data caused by sensor noise or transmission interference. Then, the preprocessed data is categorized and stored according to data type, forming a structured database containing wiring status data, position data, authentication data, attitude data, depth data, and vibration data. The received multimodal sensor data can include data transmitted by the smart wiring clamp 110, such as pressure data collected by the pressure sensing module 111, position data collected by the positioning module 112, and authentication requests from the security authentication module 113. It can also include data transmitted by the smart grounding pin 120, such as attitude parameters collected by the attitude sensing module 121, depth data collected by the depth measurement module 122, and vibration characteristic parameters collected by the vibration sensing module 123.

[0059] The visualization monitoring platform 130 integrates various algorithms to analyze and judge multimodal sensor data, thereby identifying the grounding operation status. For example, based on power safety regulations and on-site operation standards, it can preset safety thresholds and logical judgment rules for various sensor data. For instance, when the pressure value of the pressure sensing module 111 is <50N, the position of the positioning module 112 deviates from the work area by >10m, and the depth value of the depth measurement module 122 is <0.6m, a corresponding abnormal warning is triggered. It can also analyze and judge multimodal sensor data through machine learning models to identify the grounding operation status. For example, by training the machine learning model with historical operation data and inputting multimodal sensor data into the trained model, the model can learn the correlation characteristics between various sensor data and the relationship between the grounding operation status, thus determining the grounding operation status corresponding to the current multimodal sensor data. For example, by combining the changing trends of vibration and depth data, it can be determined whether the intelligent grounding pin 120 is difficult to bury due to hard geological conditions.

[0060] The intelligent early warning and monitoring system for the safety status of distribution network grounding operations according to this application constructs an end-edge-cloud collaborative system architecture including intelligent clamps, intelligent grounding pins, and a visual monitoring platform. The intelligent clamps integrate pressure sensing, positioning, and safety authentication modules, enabling the perception and authentication of clamp connection status, grounding point spatial location, and equipment identity. The intelligent grounding pins integrate attitude sensing, depth measurement, and vibration sensing modules, enabling comprehensive monitoring of the grounding pin's burial attitude, burial depth, and burial impact characteristics. The visual monitoring platform centrally receives multimodal sensor data and performs comprehensive diagnosis and early warning. This upgrades the human-based grounding operation model, which relies on personnel responsibility, to a technology-based model based on multiple technical verifications, fundamentally reducing safety accidents caused by human error. It achieves remote visibility, process traceability, status verification, and risk control in grounding operations, improving the safety of power system operation and maintenance.

[0061] In some embodiments, the visualization monitoring platform 130 is also used for: Construct a digital twin model of the grounding operation scenario, and visualize the diagnosis and early warning results of the grounding operation status in a 3D geographic information system.

[0062] In this embodiment, the visualization monitoring platform 130 pre-imports three-dimensional geographic information data of the distribution network operation area, such as the basic geographic information of the operation area, including topography, roads, buildings, distribution network line towers, and conductor routes. Based on the physical parameters (such as size, appearance, and installation method) of the smart connector 110 and smart grounding pin 120, it constructs a three-dimensional model library of equipment. Each equipment three-dimensional model is associated with a unique equipment identity identifier, which forms a one-to-one correspondence with the equipment identity identifier of the security authentication module 113.

[0063] During the grounding operation, the visualization monitoring platform 130 integrates multimodal sensor data with basic geographic information and equipment 3D models to construct a digital twin model of the grounding operation scenario. Specifically, it can establish 3D terrain data of the distribution network operation area based on basic geographic information, match the latitude and longitude coordinates of the smart connector 110 collected by the positioning module 112 with the distribution network conductor position data in the 3D terrain data to locate the 3D model of the smart connector 110 at the corresponding position of the conductor; and integrate the positioning data of the smart grounding pin 120, the attitude parameters of the attitude perception module 121, the depth data of the depth measurement module 122 with the 3D terrain data to form a digital twin model of the grounding operation scenario.

[0064] The core of the digital twin model lies in its real-time linkage with the physical scene. The visualization monitoring platform 130 receives the latest sensor data uploaded by the smart connector 110 and the smart grounding pin 120 in real time by setting a data update cycle, and dynamically updates the status of the digital twin model according to the data changes. For example, when the pressure sensing module 111 detects a decrease in the contact pressure between the smart connector 110 and the wire, it updates the status label of the corresponding device's 3D model; when the attitude sensing module 121 detects a change in the tilt angle of the smart grounding pin 120, the grounding pin model in the digital space will synchronously show the change in tilt attitude.

[0065] After completing the grounding operation status diagnosis, the visualization monitoring platform 130 can add corresponding status indicators and early warning information to the 3D model of the equipment in the digital twin model based on the diagnostic results. For example, when the equipment is operating normally, the 3D model of the equipment is highlighted in green; when a minor anomaly occurs (such as a pressure value approaching the threshold but not triggering an early warning), it is displayed in yellow; when an early warning is triggered, the equipment model is displayed in flashing orange, and an early warning message is generated next to the 3D model of the equipment. The early warning message can include the identification of the abnormal equipment, the type of anomaly (such as loose wiring, insufficient grounding pin depth, abnormal posture, etc.), the specific value of the abnormal parameter, the time of the anomaly, and the suggested handling measures.

[0066] In this embodiment, the visualization monitoring platform 130 can embed the digital twin model into a 3D geographic information system for integrated display. Maintenance personnel can view and operate the work scene from multiple dimensions through the platform's interactive interface. For example, they can view the overall layout and local details of the work scene through zooming, panning, and rotating operations; clicking on the 3D model of the intelligent wiring clamp 110 or intelligent grounding pin 120 in the digital twin model will bring up a detailed equipment information panel, displaying the equipment's real-time sensor data, equipment authentication information, historical operating status curves, and other data. Furthermore, the visualization monitoring platform 130 also supports a timeline backtracking function to view changes in the work scene status at different time points, achieving full traceability of the work process.

[0067] In some embodiments, the visualization monitoring platform 130 can also push the digital twin model and the early warning results to different terminal devices, such as the large screen display system in the background monitoring center, the computer terminal of the maintenance personnel, and the mobile terminal (such as smartphone or tablet computer) of the on-site workers.

[0068] In this embodiment, the operation status is visualized by using digital twin and three-dimensional geographic information system technology, enabling operation and maintenance personnel to intuitively grasp the information of the entire grounding operation process. This reduces the safety hazards caused by subjective judgment errors, inspection omissions, and unintuitive operation status information in manual operation. The grounding operation process is visualized and traceable, and operation and maintenance personnel do not need to be on-site to supervise, which further improves the safety and work efficiency of power system operation and maintenance.

[0069] In some embodiments, the pressure sensing module 111 includes a multi-node pressure sensor array with a distributed layout for collecting pressure distribution data of the contact area between the smart connector 110 and the wire; the security authentication module 113 includes a security chip that conforms to the national cryptographic algorithm for storing the device's unique identifier and encrypting the transmitted data.

[0070] In this embodiment, the smart connector 110 adopts a high-strength engineering plastic and metal composite structure, and the pressure sensing module 111 adopts a flexible thin film pressure sensor array, which can fit the inner wall of the smart connector 110 and adapt to the curvature change of the wire surface. The pressure sensor array adopts a distributed layout, with multiple sensing nodes set along the clamping direction of the connector.

[0071] The security authentication module 113 includes a security chip that conforms to the national cryptographic algorithm. During the production stage of the security authentication module 113, a unique device identity can be written into the read-only storage area of ​​the security chip using a dedicated card writing device.

[0072] The intelligent wiring clamp 110 may also include a communication module that supports multiple communication protocols, through which various types of sensor data are sent to the visual monitoring platform 130.

[0073] In one example, the authentication process is as follows: The smart connector 110 first powers on and performs a self-test, establishing a secure connection with the visualization monitoring platform 130. Two-way authentication is performed using a security chip compliant with national cryptographic algorithms to ensure the device's legitimacy. After successful authentication, both parties negotiate a session key. Data generated by each module in the smart connector 110 (such as pressure values, positioning coordinates, and attitude angles) is dynamically sliced ​​and encrypted using the session key before transmission, and a timestamp (such as BeiDou time synchronization) and CRC (Cyclic Redundancy Check) checksum are added to prevent data tampering and replay attacks. The encrypted data packet is sent to the visualization monitoring platform 130 via a wireless network. Upon receiving the data, the visualization monitoring platform 130 first decrypts and verifies its integrity. Only after successful verification is the data sent to the subsequent processing flow.

[0074] In this embodiment, by employing a distributed multi-node pressure sensor array, pressure distribution data of the contact area between the clamp and the wire can be collected, thereby more accurately determining the tightness of the connection between the clamp and the wire. The security authentication module is equipped with a security chip that conforms to the national cryptographic algorithm. By storing the unique identity of the device and encrypting the transmitted data, reliable authentication of the device identity and secure protection of data transmission can be achieved.

[0075] In some embodiments, the attitude sensing module 121 includes an attitude sensor; the depth measurement module 122 includes a laser rangefinder, the detection end of which is provided with a self-cleaning air curtain window; and the vibration sensing module 123 includes a vibration sensor.

[0076] In this embodiment, the attitude sensor can be an inertial measurement unit (IMU), including a gyroscope, accelerometer, magnetometer, etc. The attitude sensor can be a six-axis or nine-axis sensor, capable of measuring attitude parameters such as pitch angle, roll angle, and yaw angle of the smart grounding pin 120. Among them, the pitch angle and roll angle reflect the tilt state of the smart grounding pin 120, and the yaw angle helps to determine the orientation of the smart grounding pin 120.

[0077] The depth measurement module 122 uses a laser rangefinder for distance measurement. The detection end of the laser rangefinder integrates a self-cleaning air curtain window, which consists of high-strength wear-resistant quartz glass and an annular air path. The quartz glass can block external dust and dirt from contaminating the detection end. The annular air path is connected to a miniature air pump built into the smart grounding pin 120. When the miniature air pump is activated, it sprays high-pressure airflow onto the surface of the quartz glass through the annular air path, forming a uniform air curtain to remove dust, moisture, and other impurities adhering to the glass surface.

[0078] The vibration sensing module 123 uses a vibration sensor to collect vibration characteristic parameters. The vibration sensor can be fixedly installed inside the middle metal shell of the smart grounding pin 120, and is tightly fitted to the shell. It can receive the vibration characteristic parameters generated by the smart grounding pin 120 during the burial process.

[0079] In this embodiment, an attitude sensor is used to monitor the attitude changes of the grounding pin in real time during the burial process, which facilitates the analysis of the burial angle and direction of the grounding pin; the depth measurement module uses a laser rangefinder sensor and has a self-cleaning air curtain window at the detection end, which can not only accurately measure the burial depth of the grounding pin, but also reduce the interference of dust and impurities on the measurement accuracy through the self-cleaning air curtain window, thereby improving the accuracy of the measurement data; the vibration sensing module uses a vibration sensor to identify the impact characteristics of the grounding pin during the burial process, and by analyzing the vibration data, it can be determined whether the grounding pin has encountered underground obstacles or abnormal conditions.

[0080] In some embodiments, the visualization monitoring platform includes a data receiving module, a data fusion analysis module, a digital twin construction module, and an early warning push module; the data fusion analysis module has a built-in multi-sensor data fusion algorithm, which includes at least one of DS evidence theory, support vector machine, convolutional neural network, and hidden Markov model.

[0081] In this embodiment, the data receiving module supports multiple communication protocols, such as 4G / 5G, LoRa, NB-IoT, etc. It can adaptively select the communication method according to the network coverage of the work area and receive multimodal sensing data uploaded by the smart connector 110 and the smart grounding pin 120.

[0082] The data receiving module can send the received multimodal sensor data to the data fusion and analysis module. The data fusion and analysis module incorporates multiple algorithms, including Dempster-Shafer (DS) evidence theory, support vector machines, convolutional neural networks, and hidden Markov models, to fuse and process the multimodal sensor data, thereby diagnosing and providing early warnings for grounding operation status. For example, DS evidence theory can be used to fuse multi-source data for the same state parameter. For instance, pressure data from more than 110 pressure sensor nodes of a smart connector can be used as independent evidence, and the confidence level of the fused pressure can be calculated through evidence synthesis rules, thereby improving the reliability of pressure state judgment. Adaptive algorithms can be selected based on the feature differences of different types of data. For example, convolutional neural networks can be used to extract features from vibration characteristic parameters to mine deep correlation features of vibration frequency and amplitude. Support vector machines can be used to classify and train attitude parameters and depth data to establish a mapping model between parameters and "normal / abnormal" states. Hidden Markov models can be used to analyze the changing trends of different state parameters. For example, when abnormal attitude parameters and abnormal vibration characteristics occur simultaneously, it can be determined that the attitude deviation is caused by obstruction of grounding pin burial, and a diagnostic result including the cause of the abnormality and the confidence level can be output.

[0083] The early warning push module receives the diagnostic results from the data fusion analysis module, initiates the corresponding early warning process, and promptly pushes the diagnostic analysis results and early warning information to relevant personnel.

[0084] The digital twin building module is used to construct digital twin models and dynamically update them based on multimodal sensor data.

[0085] In this embodiment, the data fusion analysis module incorporates a multi-sensor data fusion algorithm, which integrates multimodal sensor data from smart clamps and smart grounding pins. Through data fusion processing, it not only improves data accuracy but also enhances the comprehensive analysis capability for complex grounding operation scenarios, enabling a more comprehensive reflection of the actual state of grounding operations. The digital twin construction module can deeply integrate the digital twin model of the grounding operation scenario with real-time monitoring data, providing a visual interface for maintenance personnel. The early warning push module can push early warning information to maintenance personnel based on the diagnostic results of the data fusion analysis module, reducing the risk of accidents.

[0086] In some embodiments, the data fusion analysis module is used to extract features from the pressure distribution data collected by the pressure sensing module through a convolutional neural network, identify the connection status of the smart connector 110; the connection status includes reliable connection, false connection or no connection; and verify whether the connection position of the smart connector 110 conforms to the geofence range specified by the electronic work order based on the positioning data of the positioning module, and generate evaluation information of the smart connector 110.

[0087] In this embodiment, a training set can be pre-constructed to train the convolutional neural network. The training set includes historical pressure distribution data collected by the pressure sensing module, with the corresponding smart connector connection status as labels. The training task is to output predicted values ​​of the smart connector connection status based on the input historical pressure distribution data. In each training round, the convolutional neural network extracts and predicts features from the input historical pressure distribution data, outputs predicted values ​​of the smart connector connection status, and calculates the loss value between the predicted value and the label based on a loss function, such as the cross-entropy loss function. The parameters of the convolutional neural network are updated based on the loss value using the backpropagation algorithm. After the update is completed, a new round of training begins until the predicted value and the label become consistent or a preset number of training rounds are reached.

[0088] After training, the convolutional neural network can learn the correlation between historical pressure distribution data and attachment status. After inputting pressure distribution data, the convolutional neural network will extract features from the pressure distribution data, capture local correlation features of pressure distribution, such as pressure difference between adjacent sensor nodes, distribution location of pressure peaks, etc. Then, it will downsample and fuse the extracted features, activate them through activation functions, and finally output the probability value of attachment status. The attachment status with the highest probability value is determined as the recognition result.

[0089] In this embodiment, the data fusion analysis module can also extract the electronic work order information corresponding to the grounding operation from the work task database of the visualization monitoring platform 130, and obtain the geofence range of the smart connector mounting area preset in the electronic work order. The data fusion analysis module compares the location data output by the positioning module 112 with the geofence range to determine whether the location data is within the geofence range. If the location data is not within the geofence range, the location of the smart connector 110 is deemed compliant. Furthermore, the timestamp corresponding to the location data can be compared with the work start timestamp to verify whether the location data is valid data within the current work cycle, thereby reducing the interference of historical positioning data in the judgment.

[0090] The data fusion and analysis module can combine the results of the attachment status identification and the results of the location compliance judgment to generate evaluation information for the smart junction box 110. The evaluation information can adopt a standardized format, including one or more of the following: basic information (such as the device identification, device model, installation operation number, etc. of the smart junction box 110), attachment status, location evaluation results (including location compliance judgment results, positioning coordinates, positioning accuracy, distance from the fence boundary, etc.), anomaly prompts, and evaluation confidence level.

[0091] In this embodiment, a convolutional neural network is used to extract features from the pressure distribution data collected by the pressure sensing module to identify the reliable, loose, or unattached status of the smart connector, thus improving the accuracy of the attachment status monitoring. The positioning data from the positioning module verifies whether the attachment position of the smart connector conforms to the geofence specified in the electronic work order and generates assessment information. This reduces safety hazards and maintenance risks caused by incorrect attachment positions. The assessment information combines dual verification of attachment status and geographical location, further improving the accuracy of the smart connector status assessment and enhancing the standardization and safety of the operation process.

[0092] In some embodiments, the data fusion analysis module is used to model the time-series data collected by the attitude sensing module 121, depth measurement module 122 and vibration sensing module 123 using a hidden Markov model, identify the embedding process of the smart grounding pin 120 and determine the embedding quality of the smart grounding pin, and generate evaluation information of the smart grounding pin.

[0093] In this embodiment, the timing data may include the timing sequence of attitude parameters collected by the attitude sensing module 121, such as pitch angle and roll angle timing sequences, the timing sequence of depth data collected by the depth measurement module 122, and the timing sequence of vibration characteristic parameters collected by the vibration sensing module 123, such as vibration frequency and amplitude timing sequences. It should be noted that since the sampling frequencies of different modules may be different, it is necessary to time-align the timing data collected by different modules. For example, linear interpolation can be used to align the different timing data.

[0094] In this embodiment, a training set can be pre-constructed to train the Hidden Markov Model (HMM). The training set is constructed using time-series data of the intelligent grounding pin 120 being buried under different geological conditions (soil, gravel, hard soil) and different operating procedures. Each time-series data point is labeled with the corresponding burial process stage (preparation stage, hammering stage, burial stage, and placement stage) and the final burial quality label (qualified / unqualified). During training, the burial process stages are used as the "hidden states" of the model, and the extracted feature vectors are used as the "observations." The parameters of the HMM are iteratively optimized so that the HMM can learn the mapping relationship between different burial stages and observations.

[0095] The acquired time-series data can be input into a trained Hidden Markov Model (HMM). The HMM recursively calculates the maximum probability of each hidden state at each time point and determines the optimal state path by combining the state transition probabilities. For example, in the preparation phase, the HMM identifies the observation features of "stable attitude angle, zero depth increment, and no peak vibration feature," and outputs the "preparation phase" state accordingly. In the embedding phase, it identifies the features of "stable depth increment, periodic occurrence of vibration peaks, and slight fluctuations in attitude angle," and outputs the "embedding phase" state accordingly. The HMM can output the current embedding phase. When the feature of "a sudden drop in depth increment but an increase in vibration peak" occurs, it is identified as an "embedding obstruction" abnormal phase, and the feature data of that time point is marked.

[0096] The data fusion and analysis module can determine the embedding quality based on the stage identification results of the Hidden Markov Model. For example, it can analyze whether the embedding process sequentially goes through the preparation stage, embedding stage, and placement stage; if any stage is missing, the process is considered incomplete. It can also extract the depth value of the placement stage and compare it with a preset threshold; if the depth value is less than the preset threshold, the depth is determined to be substandard. If there is an abnormal "embedding obstruction" stage, it can analyze the duration of the obstruction and the corresponding depth to determine whether it caused attitude deviation or insufficient depth. By combining the judgment results from multiple dimensions, the embedding quality can be classified as "excellent," "qualified," or "unqualified."

[0097] In this embodiment, the time-series data collected by the attitude sensing module, depth measurement module, and vibration sensing module of the smart grounding pin are modeled and analyzed using a hidden Markov model. This allows for the extraction of dynamic change characteristics of the sensor data and the capture of the state transition process during the burial of the grounding pin. Consequently, the state of the smart grounding pin during the entire process of preparation, burial, and placement can be accurately identified, thereby enabling the assessment of the burial quality of the grounding pin and the determination of the grounding safety status.

[0098] In some embodiments, the data fusion analysis module is used to perform uncertainty reasoning on the evaluation information of the smart clamp 110 and the evaluation information of the smart grounding pin 120 using DS evidence theory, and output an evaluation conclusion on the grounding operation status.

[0099] DS evidence theory is a reasoning method for dealing with uncertain information. It can quantify the degree of support of evidence for a proposition through a basic probability allocation function (m function) and use synthesis rules to fuse independent evidence from multiple sources, thereby solving the uncertainty problem of single evidence reasoning. It is suitable for scenarios such as multi-sensor data fusion and state assessment.

[0100] While the evaluation information from the intelligent clamp 110 and the intelligent grounding pin 120 reflects the operating status of their respective devices, the safety of grounding operations depends on the complete circuit performance of the conductor end connection and the grounding end connection. Evaluation of a single device has limitations and uncertainties. The data fusion analysis module employs the DS evidence theory, treating the evaluation information from the intelligent clamp 110 and the intelligent grounding pin 120 as independent evidence sources. It performs uncertainty reasoning, and through credibility allocation and evidence synthesis, it merges the credibility of multiple evidence sources to output a comprehensive evaluation conclusion that reflects the overall grounding operation status. For example, the evaluation conclusion for the grounding operation status could be "Grounding status: Normal, credibility 95%" or "Connection status: Loose connection, credibility 90%".

[0101] In this embodiment, uncertainty reasoning is performed by connecting the evaluation information of the smart clamp and the smart grounding pin through DS evidence theory. This fully considers the reliability and uncertainty of evaluation information from different sensor modules. By reasonably allocating trust levels and conflict handling mechanisms, comprehensive analysis and reasoning are performed on each evaluation information, reducing the limitations and inaccuracies of a single information source, thereby obtaining a more reliable grounding operation status evaluation conclusion.

[0102] In some embodiments, the early warning push module is used to assess the risk level of an abnormality when there is an abnormality in the grounding operation status, and push alarm information using a push method corresponding to the risk level; the push method includes at least one of the interface pop-up of the visual monitoring platform, SMS and mobile terminal.

[0103] In this embodiment, the early warning push module has a built-in risk level assessment model, which can assess the anomalies in the grounding operation status to identify the risk level. For example, the risk level can be divided into Level 1 (emergency danger), Level 2 (significant risk), Level 3 (general risk), etc.

[0104] The risk level is divided into three levels: Level 1 (Emergency Danger), which is the highest level. The criteria for this level is that the abnormality directly causes the grounding protection circuit to fail or be on the verge of failure, which may immediately lead to personal injury or equipment damage. For example, the risk level can be assessed as Level 1 (Emergency Danger) if at least one of the following abnormalities exists in the grounding operation: the smart clamp 110 is in an "unconnected" state; the smart grounding pin 120 is "buried in substandard quality and the depth is <0.5m"; and the overall operation status assessment conclusion is "dangerous" with a confidence level of ≥95%. Level 2 (Significant Risk) is a medium level. The criteria for this level is that the abnormality causes a decrease in the performance of the grounding circuit, but it has not completely failed and there is a potential safety hazard, such as the smart clamp 110 being "virtually connected". Level 3 (General Risk) is the lowest level. The criteria for this level is that the abnormality is a slight deviation in parameters, but it does not affect the performance of the grounding circuit, such as the smart clamp 110 being reliably connected but the pressure value is close to the threshold.

[0105] Different push notification methods can be used to send alarm information for different risk levels. For example, for Level 1 (emergency danger), a "multi-channel collaborative push" method is used, including: a red high-frequency flashing pop-up window appears on the large screen of the 130 visual monitoring platform's backend monitoring center; a voice call reminder is sent to the mobile terminals of relevant personnel; and SMS and APP push notifications are sent to relevant personnel simultaneously. The SMS content may include "Emergency alarm, XX anomaly has occurred in work area XX (coordinates), immediately shut down and handle!" For Level 2 (significant risk), the push notification method may include: an orange solid-on pop-up window appears on the 130 visual monitoring platform's backend large screen; APP push notifications and SMS are sent to the mobile terminals of relevant personnel, and the alarm information may include anomaly details and handling suggestions. For Level 3 (general risk), the push notification method may include: a green prompt message is displayed on the 130 visual monitoring platform's backend interface without a pop-up window; an APP push notification is sent to the mobile terminals of on-site operators with the content "XX equipment parameters are slightly fluctuating, please pay attention to monitoring," without triggering SMS and audible / visual alarms.

[0106] In this embodiment, through a graded early warning mechanism, when an abnormality is detected in the grounding operation status, the risk level can be assessed, and the corresponding push method can be selected according to the risk level to push the alarm information to the operation and maintenance personnel, thereby improving the efficiency of alarm information push.

[0107] The following scenario example will further illustrate the intelligent early warning and monitoring system for the safety status of distribution network grounding operations according to this application.

[0108] The hierarchical architecture of the intelligent early warning and monitoring system for the safety status of power distribution grounding operations is as follows: Figure 2 As shown, a layered architecture design with "end-edge-cloud" collaboration is adopted. Through the hierarchical linkage of the perception layer, communication layer, data layer and application layer, the entire process of power distribution network grounding operation status perception, transmission, analysis and control is realized.

[0109] The sensing layer can include smart clamps and smart grounding pins deployed at the distribution network grounding work site to achieve real-time, multi-dimensional sensing of key grounding operation statuses. The smart clamps and smart grounding pins can adopt low-power, high-protection hardware designs, are suitable for outdoor working environments, and support multi-protocol communication. They can upload collected sensor data (pressure, positioning, attitude, depth, vibration, etc.) via encrypted communication modules (4G / 5G / NB-IoT).

[0110] The communication layer serves as the transmission hub connecting the perception layer and the data layer. Its communication network supports multiple communication methods, including 4G / 5G, LoRa, and NB-IoT. The communication layer employs encrypted transmission protocols to encrypt data frames, ensuring the confidentiality and integrity of data during transmission and preventing the risk of data leakage or tampering.

[0111] The data layer can include an edge gateway and supporting analysis, processing, and component modules. Its function is to realize edge aggregation, preprocessing, and analysis of data. The data layer receives multimodal sensor data uploaded by the perception layer through communication components and uses database components to realize local storage and caching of data. The processing module performs preprocessing on the data, such as filtering (Kalman filtering, median filtering, etc.), linear compression, spatiotemporal registration (aligning different time series data), and outlier removal, to improve data quality. The analysis module calls algorithms (such as convolutional neural networks, hidden Markov models, clustering, digital signature algorithms, etc.) to perform preliminary analysis on the preprocessed data, such as identifying the connection status of smart clamps and the embedding stage of smart grounding pins, thereby offloading some computing tasks to the edge and reducing the computing pressure on the cloud-based visualization monitoring platform.

[0112] The core of the application layer is a cloud-based visualization monitoring platform. Its function is to centrally monitor, intelligently diagnose, and visualize the grounding operation status, providing decision support for maintenance personnel. The visualization monitoring platform receives pre-processed data and preliminary analysis results uploaded from the data layer, uses intelligent algorithms (such as DS evidence theory) to fuse multi-source data, and outputs a comprehensive assessment conclusion on the grounding operation status. Furthermore, it utilizes GIS display functions to overlay information such as grounding point location and equipment status onto a 3D geographic information system, achieving a visual presentation of the operation scenario. The visualization monitoring platform also supports functions such as historical tracing (retrieving status data for any operation period), anomaly reporting (automatically generating anomaly handling records), and report analysis (statistically analyzing operation compliance rates and anomaly type distribution).

[0113] The intelligent early warning and monitoring system for the safety status of distribution network grounding operations, as described in this application, has been piloted at XXX Power Supply Company and deployed at 10kV distribution network maintenance sites. Operators use intelligent grounding equipment (including intelligent clamps and intelligent grounding pins), and maintenance personnel can view the entire grounding operation process in real time through a visual monitoring platform at the monitoring center. The system has successfully issued early warnings for multiple instances of insufficient burial depth of intelligent grounding pins and abnormal pressure of intelligent clamps. The average time for a single grounding operation has been reduced by more than 20%, and the average power outage time for maintenance has been reduced by approximately 30 minutes.

[0114] After its implementation, this system has achieved significant technical and economic benefits: Safety benefits: It fundamentally reduces personal safety accidents caused by misoperation of grounding wires, thus strengthening the safety defense line; Operation and maintenance efficiency: The grounding operation process is visualized and traceable, and maintenance personnel do not need to be on-site to supervise, which improves work efficiency by more than 20%, reduces the average planned power outage time by 30 minutes, and increases power supply and electricity revenue; Management Improvement: A new paradigm of standardized and digitalized grounding operation safety management has been established, enabling full recording of the operation process and identification of responsibilities.

[0115] This application also provides an intelligent early warning and monitoring method for the safety status of distribution network grounding operations, which is applied to a visual monitoring platform.

[0116] like Figure 3 As shown, the intelligent early warning and monitoring method for the safety status of distribution network grounding operations includes steps 310 and 320.

[0117] Step 310: Collect multimodal sensing data in real time during the grounding operation through the various modules of the smart connector and smart grounding pin; wherein, the smart connector integrates a pressure sensing module for sensing the connection status between the smart connector and the conductor, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification; the smart grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial attitude, a depth measurement module for measuring the burial depth of the smart grounding pin, and a vibration sensing module for identifying the impact characteristics of the smart grounding pin during the burial process. Step 320: Diagnose and provide early warning of grounding operation status based on multimodal sensor data.

[0118] According to the intelligent early warning and monitoring method for the safety status of distribution network grounding operations proposed in this application, an end-edge-cloud collaborative system architecture is constructed, including intelligent clamps, intelligent grounding pins, and a visual monitoring platform. The intelligent clamps integrate pressure sensing, positioning, and safety authentication modules, enabling the perception and authentication of clamp connection status, grounding point spatial location, and equipment identity. The intelligent grounding pins integrate attitude sensing, depth measurement, and vibration sensing modules, enabling comprehensive monitoring of the grounding pin's burial attitude, burial depth, and burial impact characteristics. The visual monitoring platform centrally receives multimodal sensor data and performs comprehensive diagnosis and early warning. This upgrades the human-based grounding operation model, which relies on personnel responsibility, to a technically-based model based on multiple technology verifications, fundamentally reducing safety accidents caused by human error. It achieves remote visibility, process traceability, status verification, and risk control in grounding operations, thereby improving the safety of power system operation and maintenance.

[0119] In some embodiments, the method further includes: Construct a digital twin model of the grounding operation scenario, and visualize the diagnosis and early warning results of the grounding operation status in a 3D geographic information system.

[0120] According to one embodiment of this application, the diagnosis and early warning of grounding operation status based on multimodal sensing data includes: The convolutional neural network extracts features from the pressure distribution data collected by the pressure sensing module to identify the connection status of the smart connector. The connection status includes reliable connection, loose connection, or no connection. The positioning data from the positioning module is used to verify whether the connection position of the smart connector is within the geofence range specified by the electronic work order, and evaluation information of the smart connector is generated.

[0121] In some embodiments, the diagnosis and early warning of grounding operation status based on multimodal sensing data includes: The time-series data collected by the attitude sensing module, depth measurement module, and vibration sensing module are modeled using a hidden Markov model to identify the embedding process of the smart grounding pin, determine the embedding quality of the smart grounding pin, and generate evaluation information for the smart grounding pin.

[0122] In some embodiments, the diagnosis and early warning of grounding operation status based on multimodal sensing data includes: The DS evidence theory is used to perform uncertainty reasoning on the evaluation information of the smart clamp and the smart grounding pin, and output the evaluation conclusion of the grounding operation status.

[0123] In some embodiments, the diagnosis and early warning of grounding operation status based on multimodal sensing data includes: Assess the risk level of any abnormalities in the grounding operation. Alarm information is pushed out using a method corresponding to the risk level; the push method includes at least one of the following: a pop-up window on the visual monitoring platform, SMS, and mobile terminal.

[0124] The implementation process of the intelligent early warning and monitoring method for the safety status of distribution network grounding operations can be referred to the description of the intelligent early warning and monitoring system for the safety status of distribution network grounding operations, and will not be repeated in this application.

[0125] The intelligent early warning and monitoring method for the safety status of distribution network grounding operations provided in this application can be executed by an intelligent early warning and monitoring device for the safety status of distribution network grounding operations. This application uses the example of an intelligent early warning and monitoring device for the safety status of distribution network grounding operations executing the method to illustrate the intelligent early warning and monitoring device for the safety status of distribution network grounding operations provided in this application.

[0126] This application also provides an intelligent early warning and monitoring device for the safety status of distribution network grounding operations, which is applied to a visual monitoring platform.

[0127] like Figure 4 As shown, the intelligent early warning and monitoring device for the safety status of power distribution network grounding operations includes: The data acquisition module is used to collect multimodal sensing data in real time during the grounding operation through various modules of the smart clamp and smart grounding pin. Among them, the smart clamp integrates a pressure sensing module for sensing the connection status between the smart clamp and the conductor, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification. The smart grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial attitude, a depth measurement module for measuring the burial depth of the smart grounding pin, and a vibration sensing module for identifying the impact characteristics of the smart grounding pin during the burial process. The diagnostic and early warning module is used to diagnose and provide early warnings about the grounding operation status based on multimodal sensor data.

[0128] The intelligent early warning and monitoring device for the safety status of power distribution grounding operations in this application embodiment can be an electronic device or a component of an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the specific type of device.

[0129] The intelligent early warning and monitoring device for the safety status of distribution network grounding operations in this embodiment can be a device with an operating system. This operating system can be Microsoft Windows, Android, iOS, or other possible operating systems; this embodiment does not impose specific limitations.

[0130] In some embodiments, such as Figure 5As shown, this application embodiment also provides an electronic device 500, including a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the program is executed by the processor 501, it implements the various processes of the above-described intelligent early warning and monitoring method embodiment for the safety status of distribution network grounding operations, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0131] It should be noted that the electronic devices in the embodiments of this application include the aforementioned mobile electronic devices and non-mobile electronic devices.

[0132] This application also provides a non-transitory computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described intelligent early warning and monitoring method for the safety status of distribution network grounding operations, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0133] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0134] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-mentioned intelligent early warning and monitoring method for the safety status of distribution network grounding operations.

[0135] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0136] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described intelligent early warning and monitoring method embodiment for the safety status of distribution network grounding operations, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0137] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0138] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0139] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0140] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0141] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0142] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. An intelligent early warning and monitoring system for the safety status of power distribution network grounding operations, characterized in that, include: Intelligent wiring clamps, intelligent grounding pins, and a visual monitoring platform; The intelligent connector integrates a pressure sensing module for sensing the connection status between the intelligent connector and the wire, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification. The smart grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial attitude, a depth measurement module for measuring the burial depth of the smart grounding pin, and a vibration sensing module for identifying the impact characteristics of the smart grounding pin's burial process. The visualization monitoring platform is used to receive multimodal sensing data uploaded by the smart connector and the smart grounding pin, and to diagnose and warn of the grounding operation status based on the multimodal sensing data. The visualization monitoring platform includes a data fusion and analysis module, which is used to model the time-series data collected by the attitude sensing module, depth measurement module and vibration sensing module through a hidden Markov model, identify the embedding process of the smart grounding pin and determine the embedding quality of the smart grounding pin, and generate evaluation information of the smart grounding pin. The embedding process includes a preparation stage, a hammering stage, an embedding stage, and a placement stage. Determining the embedding quality of the smart grounding pin includes analyzing whether the embedding process sequentially goes through the preparation stage, the embedding stage, and the placement stage. If any stage is missing, the process is considered incomplete. If there is an abnormal stage of obstruction during burial, analyze the duration of obstruction and the corresponding depth to determine whether it leads to attitude deviation or insufficient depth. Based on the combined judgment results from multiple dimensions, determine the burial quality of the smart grounding pin.

2. The system according to claim 1, characterized in that, The visualization monitoring platform is also used for: Construct a digital twin model of the grounding operation scenario, and visualize the diagnosis and early warning results of the grounding operation status in a 3D geographic information system.

3. The system according to claim 1, characterized in that, The pressure sensing module includes a multi-node pressure sensor array with a distributed layout, used to collect pressure distribution data in the contact area between the smart connector and the wire; the security authentication module includes a security chip that conforms to national cryptographic algorithms, used to store the device's unique identifier and encrypt the transmitted data.

4. The system according to claim 1, characterized in that, The attitude sensing module includes an attitude sensor; the depth measurement module includes a laser rangefinder, the detection end of which is provided with a self-cleaning air curtain window; the vibration sensing module includes a vibration sensor.

5. The system according to claim 1, characterized in that, The visualization monitoring platform includes a data receiving module, a digital twin construction module, and an early warning push module; the data fusion analysis module has a built-in multi-sensor data fusion algorithm, which includes at least one of DS evidence theory, support vector machine, convolutional neural network, and hidden Markov model.

6. The system according to claim 5, characterized in that, The data fusion and analysis module is used to extract features from the pressure distribution data collected by the pressure sensing module through a convolutional neural network, identify the connection status of the smart connector, including reliable connection, loose connection, or no connection; and verify whether the connection position of the smart connector is within the geofence range specified by the electronic work order based on the positioning data of the positioning module, and generate evaluation information for the smart connector.

7. The system according to claim 6, characterized in that, The data fusion and analysis module is used to perform uncertainty reasoning on the evaluation information of the smart connector and the smart grounding pin using DS evidence theory, and output the evaluation conclusion of the grounding operation status.

8. The system according to claim 5, characterized in that, The early warning push module is used to assess the risk level of the abnormality when there is an abnormality in the grounding operation status, and push alarm information using the push method corresponding to the risk level. The push method includes at least one of the following: interface pop-up of the visualization monitoring platform, SMS, and mobile terminal.

9. A method for intelligent early warning and monitoring of the safety status of distribution network grounding operations, characterized in that, The method, applied to a visual monitoring platform, includes: Through various modules of the intelligent connector and intelligent grounding pin, multimodal sensing data is collected in real time during the grounding operation. Among them, the intelligent connector integrates a pressure sensing module for sensing the connection status between the intelligent connector and the conductor, a positioning module for spatial positioning of the grounding point, and a security authentication module for device identification. The intelligent grounding pin integrates an attitude sensing module for monitoring the grounding pin's burial attitude, a depth measurement module for measuring the burial depth of the intelligent grounding pin, and a vibration sensing module for identifying the impact characteristics of the intelligent grounding pin during the burial process. Diagnosis and early warning of grounding operation status based on the multimodal sensing data; including: modeling the time-series data collected by the attitude sensing module, depth measurement module and vibration sensing module using a hidden Markov model, identifying the burial process of the smart grounding pin and determining the burial quality of the smart grounding pin, and generating evaluation information of the smart grounding pin; the burial process includes a preparation stage, a hammering stage, a burial stage and a positioning stage, and determining the burial quality of the smart grounding pin includes: analyzing whether the burial process sequentially goes through the preparation stage, the burial stage and the positioning stage, and judging that the process is incomplete if any stage is missing; if there is an abnormal burial obstruction stage, analyzing the duration of obstruction and the corresponding depth, judging whether it leads to attitude deviation or insufficient depth, and determining the burial quality of the smart grounding pin by comprehensively judging the results of multiple dimensions.

10. The method according to claim 9, characterized in that, The method further includes: Construct a digital twin model of the grounding operation scenario, and visualize the diagnosis and early warning results of the grounding operation status in a 3D geographic information system.

11. The method according to claim 9, characterized in that, The diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: The pressure distribution data collected by the pressure sensing module is processed by a convolutional neural network to extract features and identify the connection status of the smart connector. The connection status includes reliable connection, loose connection, or no connection. The system also verifies whether the connection position of the smart connector is within the geofence specified by the electronic work order based on the positioning data of the positioning module, and generates evaluation information for the smart connector.

12. The method according to claim 9, characterized in that, The diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: The DS evidence theory is used to perform uncertainty reasoning on the evaluation information of the smart connector and the smart grounding pin, and the evaluation conclusion of the grounding operation status is output.

13. The method according to claim 9, characterized in that, The diagnosis and early warning of grounding operation status based on the multimodal sensing data includes: If an anomaly is found in the grounding operation status, assess the risk level of the anomaly. Alarm information is pushed using the push method corresponding to the risk level; the push method includes at least one of the interface pop-up of the visualization monitoring platform, SMS and mobile terminal.

Images