49results about How to "Reduce outage time" patented technology

The invention relates to a real-time fault detection and automatic repair system for a power grid. The real-time fault detection and automatic repair system comprises a multi-level sensing module, a data processing module, an automatic repair module and a monitoring and logging module. The multi-level sensing module collects data such as voltage, current, frequency and temperature in operation of a power grid by deploying multiple types of sensors, and sends the data to the data processing module. And the data processing module analyzes the collected data through an embedded intelligent algorithm, identifies potential faults and generates fault diagnosis results. And the automatic repair module executes repair operations of isolating a fault area, reconstructing a power grid topological structure and recovering normal power supply according to a fault diagnosis result. The monitoring and log module records the operation state of the power grid and the fault diagnosis and repair process, and provides fault analysis and performance evaluation functions through a user interface. According to the system, real-time detection, accurate positioning and automatic repair of power grid faults and comprehensive monitoring of operation data are realized, and the safety and reliability of power grid operation are remarkably improved.

The invention relates to the technical field of power failure troubleshooting, and discloses a single-phase earth fault rapid positioning method based on multi-source data fusion, and the method comprises the steps: collecting historical fault data, power system operation data and environment data through employing a plurality of monitoring devices, such as a power system monitoring device, a fault recorder and a distributed sensor; and forming a basic data set. By performing fault feature analysis on the data set, a dual machine learning model is constructed, including a fault prediction model and a positioning model. A training data set is used to train a model, model parameters are optimized, then the trained model is used to predict real-time data, potential fault risks are identified, and a targeted troubleshooting plan and a rapid positioning strategy are formulated. According to the invention, through data fusion and a machine learning algorithm, the accuracy of fault positioning is improved, the positioning time is shortened, and the power failure time and the influence on users are reduced.

The invention relates to a magnetic control fast switch and dynamic voltage restorer combined power supply switching system and method. The system comprises a magnetic control switch unit, a voltage monitoring unit, a voltage compensation unit and an arc extinguishing unit. The magnetic switch unit is made of a novel magnetic control material and forms a vertical motion opening and closing mechanism through excitation and demagnetization of a built-in coil and assistance of a spring, and the vertical motion opening and closing mechanism is used for changing an internal magnetic domain and rapidly opening and closing. The voltage detection unit adopts a double-second-order generalized integral phase-locked loop voltage monitoring structure and is used for detecting instantaneous phase and frequency information of power grid voltage; the voltage compensation unit adopts a dynamic voltage restorer and is used for performing voltage compensation according to a difference value between a current power supply and an objective table power supply in a power supply switching gap so as to effectively maintain the stability of load voltage when voltage sag occurs in a power grid; and the arc extinguishing unit adopts a T-shaped double-outlet vacuum arc extinguishing chamber and is used for realizing zero arc in the whole power supply switching process. According to the invention, rapid switching of the power supply can be realized, and continuous voltage is ensured in the switching process.

The invention discloses an intelligent opening and closing method and system for a reclosing circuit breaker based on an electromagnet, and relates to the field of intelligent control, and the method comprises the steps: monitoring a line current in real time, comparing the line current with a preset threshold value, and carrying out the opening after the overcurrent abnormality is detected. Entering a first time delay stage after opening, comprehensively evaluating the states of the circuit breaker and the circuit, and constructing a dynamic weight index system to calculate an evaluation score; if the score exceeds a threshold value, closing is carried out after time delay is finished, otherwise, an alarm is triggered. And entering a second delay stage after switching on, continuously monitoring the electric parameters and establishing an anomaly judgment mechanism, forming a closed-loop protection process of monitoring, switching off, evaluating, switching on and re-monitoring, and realizing intelligent linkage of overcurrent protection and state self-adaption. The method has the advantages that through real-time line electric parameter monitoring, multi-dimensional state evaluation and an intelligent decision-making mechanism, precise opening and closing of the circuit breaker are achieved, the power supply reliability is improved, the power failure time is shortened, and the misoperation risk is reduced.

The invention discloses a power distribution network post-fault load recovery method considering minimum duration, which comprises the following steps of: 1, establishing a target function of a power distribution network post-fault load recovery model by taking maximization of weighted load recovery quantity and maximization of minimum duration of a micro-grid as targets; 2, establishing a power distribution network radial constraint by considering the running radial performance of the power distribution network; 3, considering the minimum duration of the micro-grid, and establishing the minimum duration constraint of the micro-grid; 4, mobile emergency power supply vehicle constraints are established; 5, considering operation safety of the power distribution network, and establishing power flow balance and safe operation constraints of the power distribution network; and 6, solving the power distribution network post-fault load recovery model, and obtaining a power distribution network post-fault load recovery scheme. According to the method, the operation safety of the power distribution network is ensured, the problem of unbalanced power flow is avoided, the minimum duration time of the micro-grid and the mobile emergency power supply vehicle are cooperatively considered, the load recovery method after the power distribution network breaks down is effectively obtained, and the power failure loss is reduced.

The invention relates to the technical field of intelligent electric energy meters, and discloses an energy consumption analysis-driven electric energy meter preventive maintenance scheduling method and platform. According to the method, a deep learning method based on LSTM is utilized, a fault prediction model is constructed through historical energy consumption data, energy consumption data of the electric energy meter are collected in real time and preprocessed, then the fault prediction model is utilized to predict the fault trend of the electric energy meter, and the remaining service life of the electric energy meter is evaluated. And formulating and implementing a preventive maintenance scheduling plan according to the prediction result and the residual service life evaluation. In addition, a corresponding platform is also constructed and comprises a data acquisition module, a data processing module, a fault prediction module, a scheduling planning module, a maintenance execution module and a performance evaluation module. The reliability and the service life of the electric energy meter are improved, the maintenance resource configuration is optimized, the fault rate and the power failure time are reduced, and a comprehensive, efficient and reliable solution is provided for preventive maintenance of the electric energy meter.

The application discloses a busbar structure of a comprehensive distribution box, relates to the technical field of busbar structures of distribution boxes, and is used for parallel connection of multiple circuit breakers and comprises a main conducting bar and multiple wiring terminals, further comprises a supporting base, a bracket, a spacing adjusting unit, a locking unit and a pressing unit, the spacing adjusting unit is used for adjusting the equidistant distribution distance between the multiple wiring terminals, the locking unit is used for locking the position of the spacing adjusting unit, and the pressing unit is used for locking the fitting position between the main conducting bar and the multiple wiring terminals. Advantages are that: the equidistant synchronous adjustment of the spacing between the wiring terminals is realized by the spacing adjusting unit to adapt to different circuit breaker specifications, and the independent detachable design of the wiring terminals is utilized to realize the quick replacement of single circuit breakers, so that the maintenance operation is greatly simplified while the mold opening cost and the inventory pressure are reduced, the problem that all normal circuits need to be removed due to the maintenance of a single circuit breaker is avoided, the power-off time is shortened, and the maintenance cost is reduced.

The invention provides an evaluation and repair method and system for a composite bushing umbrella skirt. The method comprises the following steps: detecting and evaluating the current aging state of the composite bushing umbrella skirt to obtain an aging grade; setting a repair decision according to the aging level; and repairing the composite sleeve umbrella skirt according to the result of the repairing decision. Through the processing of the steps, the evaluation and restoration method breaks through the limitation of detection decentralization, evaluation subjectivity and restoration manual operation in the prior art, establishes a standardized grading evaluation and decision-making mechanism, constructs a whole-process automatic restoration system, and improves the accuracy of the whole-process automatic restoration. According to the method, the aging state of the composite sleeve umbrella skirt can be automatically and accurately evaluated, the repairing process is intelligently and adaptively executed, the repairing effect is verified in a closed loop mode, and standardization, automation and precision of aging repairing of the composite sleeve umbrella skirt are achieved, so that the operation and maintenance cost and dependence on manpower are greatly reduced on the premise that the repairing quality is guaranteed, and the repairing efficiency is improved. And the repair efficiency and quality of the composite sleeve umbrella skirt are improved.

This utility model discloses a dedicated drawer switch and switch cabinet developed based on a pull-out low-voltage switchgear, belonging to the field of power supply equipment. The drawer switch includes a drawer body, an input socket, a switch assembly, and a locking assembly. The input socket is located on the drawer panel and electrically connected to a disconnecting switch. The switch assembly includes an operating handle and a drive rod. The operating handle is rotatably mounted on the drawer panel and can rotate between an open and closed position. The operating handle drives the disconnecting switch via the drive rod. The locking assembly includes a connecting structure and a locking pin. A fixing hole is provided in the drawer compartment corresponding to the locking pin. The locking pin is connected to the drive rod via the connecting structure. When the operating handle is in the open position, the locking pin disengages from the fixing hole; when the operating handle is in the closed position, the locking pin is inserted into the fixing hole. The switch cabinet includes a drawer compartment, and the drawer compartment is equipped with the aforementioned drawer switch.

A cable channel environment automatic adjusting device disclosed by the present invention comprises a monitoring module, a communication module, a CPU processor, a power supply module and a control module, an output end of the monitoring module is connected with the CPU processor, a power supply port of the CPU processor is connected with the power supply module, the CPU processor is further electrically connected with the communication module and the control module, and the communication module is wirelessly connected to a mobile equipment terminal. The monitoring module collects water level, temperature, humidity and video environment information of accumulated water of the cable channel and transmits the environment information to the CPU processor, and the control module is started through the CPU processor to automatically adjust the environment of the cable channel. The cable can reliably operate in a normal-temperature and dry environment, the service life of the cable is effectively prolonged, the power failure time is shortened, and the power supply reliability is improved.

The application relates to the technical field of power distribution control, in particular to an active power distribution network fault self-healing system and a method thereof, which comprises a data sensing module, a fault positioning module, an isolation control module, a fault self-healing module and a power supply recovery module, and realizes intelligent processing of the whole process from fault detection to power supply recovery through cooperation of the multiple modules. The system can quickly position faults based on FTU layout structure and operation data, optimizes analysis efficiency in combination with a GPU computing power dynamic distribution mechanism, and realizes accurate isolation of a fault area, self-healing repair and smooth grid recovery by using intelligent strategy generation and digital twin technology. The application effectively improves the power supply reliability, system stability and operation intelligent level of the power distribution network.

The application discloses a kind of network unmanned aerial vehicle inspection achievement automatic back transmission and defect identification method, it is related to power distribution network inspection technical field.The purpose is to solve the problems of low efficiency, fault response lag, data transmission without security and defect identification relying on artificial in traditional manual inspection.The method comprises: unmanned vehicle carries unmanned aerial vehicle and hangar drives to parking point, unmanned aerial vehicle takes off and carries out inspection and collects achievement data;After unmanned aerial vehicle returns, unmanned aerial vehicle platform processes and transmits achievement data to unmanned aerial vehicle management platform;Management platform uses AI image recognition technology to identify defects in data, generates identification results;Finally, management platform synchronizes identification results to power grid digital brain platform, and is associated with equipment operating state storage.The application realizes the full-process automation and intelligentization of distribution network inspection, greatly improves the inspection efficiency and the accuracy of data processing, optimizes the fault response mechanism, and provides strong support for the intelligent operation and maintenance of distribution network line.

The application discloses a kind of electric power facilities flood disaster space heterogeneity analysis method and system, the method includes receiving to strong rainfall defense alarm, disaster early warning after flood disaster emergency response notice, start the process of electric power facilities flood disaster space heterogeneity analysis;According to the water level sensing monitoring information of the disaster power facility ontology obtained by processing, the individual area of the disaster power facility region and the total area of the disaster power facility region, construct the neural network of the damaged range of the disaster power facility region, and output the monitoring analysis result of the spatial heterogeneity of the disaster power facility region, i.e.The method and system of the application solve the spatial distribution index of the disaster power facility region, draw monitoring water level spatial distribution curve, crack the problem of describing flood disaster space heterogeneity, help electric power enterprise to guide to carry out emergency early warning, load transfer, flood control reinforcement, repair power, material allocation, and greatly reduce power equipment downtime and customer outage time.

This invention relates to the field of power metering technology, specifically disclosing a phase sequence switching control method for energy meters that ensures the safety of the secondary circuit of a current transformer (CT) / potential transformer (PT). The method synchronously acquires and converts three-phase voltage and current signals, constructs a multi-dimensional spatial vector of phase angles, calculates the spatial angle between the vector and the positive-sequence reference vector, and combines this with phase dispersion to generate accurate phase sequence status values ​​to determine reverse phase sequence. When reverse phase sequence is determined, a phased safety switching command sequence is generated based on real-time electrical status verification: first, a disconnect command is issued after verifying voltage stability; then, a current short-circuit command is issued only after verifying a valid voltage drop. The action units are sequentially driven to perform voltage disconnection and current short-circuit operations, driving the dual-contact unit to synchronously switch the three-phase wiring. After switching, the circuit is restored and the phase sequence is re-verified. If multiple failures occur, an adjustment and safety locking mechanism is activated. This invention solves the problems of open circuit on the CT secondary side and short circuit on the PT secondary side during switching.

This utility model relates to a surge arrester that is easy to disassemble, comprising several surge arrester units, with adjacent surge arrester units detachably connected via a threaded structure. Each surge arrester unit includes: a connecting cylinder with a silicone rubber shed on its outer side; a nonlinear resistor element detachably installed inside the connecting cylinder; the uppermost and lowermost surge arrester units are respectively detachably connected to an upper connecting seat and a lower connecting seat; a mating part is integrally formed at the lower end of the connecting cylinder, and the mating part has external threads on its outer side; the inner walls of adjacent connecting cylinders have internal threads adapted to the external threads, achieving detachable connection through thread engagement. This easily disassembled surge arrester, due to its detachable structural design, allows for replacement of only the damaged component or the corresponding surge arrester unit when components such as the silicone rubber shed or the nonlinear resistor element are damaged, without replacing the entire surge arrester, significantly reducing maintenance costs and material waste.

A distribution network uninterruptible power maintenance system comprises a 10 kV PT cabinet, a 10 kV switch cabinet and a 10 kV transformer platform which are connected in sequence, the 10 kV transformer platform is connected with a distribution network maintenance power flow control box and then connected to a user, the distribution network uninterruptible power maintenance system further comprises an electric pickup truck used for supplying power, the electric pickup truck is connected with the distribution network maintenance power flow control box, the 10 kV PT cabinet is connected with a transmitting end of a synchronous detector, and the synchronous detector is connected with a receiving end of the synchronous detector. The synchronous detector transmitting end is in wireless connection with the synchronous detector receiving end, and the synchronous detector receiving end is connected with the electric pickup truck; the electric pickup truck is provided with a combined battery. The technical problem to be solved by the invention is to provide the non-power-cut maintenance system and method for the distribution network, so that power supply for users can be maintained while line power-cut maintenance is performed, and a novel maintenance mode is realized.

This invention discloses a multifunctional cable grounding box, including a grounding box body, a grounding bar inside the box, a control switch below the grounding bar, and a protector between the grounding bar and the control switch. The protector includes a primary protector and a backup protector arranged in parallel. One end of each protector is connected to the grounding bar, and the other end is connected to the control switch, allowing switching between the primary and backup protectors via the control switch. An insulation transition section is correspondingly located below the control switch, and a current-guiding plate is connected to the insulation transition section, which is connected to the core wire clamp via the current-guiding plate. This design enables rapid switching of the protectors, balancing power supply continuity, circuit safety, and maintenance convenience. Moving the position of the insulation switching bar allows for switching of the grounding mode, flexibly adapting to complex scenarios and achieving full-scene coverage.

The application discloses a kind of monitoring method and device based on ring network cabinet full life cycle twinborn data, it is related to equipment management technical field.The method includes: in production stage, key manufacturing data is collected for ring network cabinet to form production gene bank, combined with unique digital identification to build digital twin initial model, while real-time acquisition various operating data, then rely on manufacturing execution system to individualize correction to initial model, match physical entity parameter, use five-layer collaborative fusion algorithm to deeply fuse production and operating data, diagnose early abnormality and typical fault, carry out ring network cabinet intelligent monitoring and operation and maintenance.The present application can establish complete digital archives for each equipment, realize the whole link data through from production to process optimization, improve early fault identification sensitivity, reduce the repeated incidence of similar fault.

The invention discloses a TDR and passive transient analysis fused power transmission cable fault diagnosis system, and belongs to the technical field of power system fault diagnosis and intelligent diagnosis. The method comprises the following steps: firstly, constructing a pulse injection and signal acquisition integrated device at the end part of a cable, acquiring three-phase voltage and current transient signals, and forming increments before and after a fault; and further constructing an incident wave and a reflected wave at a port, extracting a high-frequency detail component by adopting wavelet decomposition, enhancing wave head features in combination with a TEO energy operator, and analyzing a fault type. And judging a grounding fault, a high-resistance fault or a low-resistance fault. If the fault is a low-resistance fault, passive distance measurement is adopted, and if the fault is a high-resistance fault, the active distance measurement device generates pulse distance measurement. According to the high-resistance and low-resistance self-adaptive distance measurement method, the wave head detectability and the distance measurement stability can be improved under the conditions of different fault impedances and different fault types, and the reliability of cable fault positioning is improved.

This invention discloses a method, apparatus, device, and storage medium for detecting grounding faults in low-voltage lines. Multiple Rogowski coils are spaced apart on the grounding wire of the low-voltage line. These coils are used for non-contact detection of the AC current on the grounding wire. The AC current detected by each Rogowski coil at the same acquisition time is converted from analog to digital and integrated to obtain a voltage data sequence. A filtering algorithm is used to filter the voltage data sequence to obtain an effective leakage current data sequence. Characteristic information representing leakage faults is extracted from the leakage current data sequence. Based on this characteristic information, the location of the grounding leakage fault in the low-voltage line is determined, and the fault location is sent to the mobile terminal of maintenance personnel. This invention achieves the judgment of grounding faults in low-voltage lines through non-contact detection of abnormal currents, reducing labor costs, improving detection efficiency and accuracy, reducing power outage time caused by leakage, and reducing economic losses.

The invention relates to a live-line switching method for a bus operation mode of a distributed substation, and belongs to the technical field of power transformation and distribution system operation. According to the technical scheme, when a switch of a 10kV bus coupler cabinet of a 110kV transformer substation is located at a switching-on position, and a 10kV bus coupler cabinet trolley and a bus coupler lifting cabinet trolley are both located at operating positions, a first power supply incoming line and a switching-on locking loop of a bus coupler cabinet and a second power supply incoming line and a bus coupler cabinet of each distributed transformer substation are shielded, and three-throw three-loop closing is achieved; therefore, live-line switching of the bus operation modes of the distributed substations is realized. The system has the advantages that the risk of substation circulation caused by manual misoperation is fundamentally avoided, the stability and accuracy of signal transmission are effectively guaranteed by adopting a multi-node signal transmission mode, potential safety hazards caused by signal problems are reduced, power failure is not needed when operation modes of all distributed substations are switched, and the system is safe and reliable. The power failure time and the power failure frequency are reduced, the power supply reliability is improved, and normal power utilization is effectively guaranteed.

The application discloses a kind of installation structures of strain tower lightning arrester suitable for coastal multi-thunder typhoon area, solve the problem that traditional lightning arrester installation cannot meet the protection demand of strong thunder area and the problem of insufficient wind load resistance and overturning resistance capability.Therein, the lightning arrester includes a lightning arrester body and a fixed base, the lightning arrester body is fixed on the tower body support of strain tower through the fixed base, and is spaced apart from the strain insulator at a set distance;The fixed base is provided with a lightning arrester position adjusting structure for adjusting the installation position of the lightning arrester;The lightning arrester is reinforced by a double-insulator cable-stayed support assembly, the double-insulator cable-stayed support assembly includes two cable-stayed insulators, the oblique downward end of the cable-stayed insulator is connected with the lightning arrester, and the oblique upward end is connected with the tower body support of strain tower.

The utility model belongs to the technical field of power transmission line iron towers, and particularly relates to a double-loop crossed spanning power transmission iron tower which comprises tower legs, a tower body and a tower head. The tower head comprises an upper tower head section and a lower tower head section which are adjacently arranged up and down; the upper tower head section is provided with an upper ground wire support and an upper wire cross arm which are vertically spaced and arranged in parallel. The lower tower head section is provided with a lower ground wire support and a lower wire cross arm which are vertically spaced and arranged in parallel. The projections of the upper wire cross arm and the lower wire cross arm on the horizontal plane intersect with each other. By arranging the upper wire cross arm and the lower wire cross arm which are vertically arranged at intervals and are different in length direction, double-loop power transmission lines in different directions are crossed and spanned at the same power transmission tower, the occupied area is saved, the construction amount is reduced, the construction cost is saved, and the power failure time during construction is shortened.

This invention discloses a current protection method and system for distributed power generation distribution networks, relating to the field of distribution network technology. The invention first collects parameters of the distribution network's common coupling point in real time to predict grid-connected or islanded operation modes. It then distinguishes between inverter-type and synchronous generator-type power supplies based on harmonic content and current response speed, accurately calculating the main protection settings for each power supply. Next, it employs dual-start components for current surges and voltage dips to detect faults, comprehensively determining whether the fault is within or outside the designated area. Subsequently, it determines the braking level based on fault characteristics, dynamically adjusts power supply output limits, and forms a three-dimensional protection system with dual backup protection. Finally, it sets differentiated reclosing delay times based on fault levels and adopts corresponding closing sequences according to the operating mode. This achieves full-scenario adaptability of the protection strategy, significantly improves the accuracy of fault determination, ensures grid stability through the synergy of protection and braking, optimizes recovery strategies to improve power supply reliability, and perfectly adapts to the safe and efficient operation requirements of diverse distribution networks.

The utility model discloses a modularization easy maintenance electric energy meter belongs to the electric energy meter technical field, the electric energy meter comprises a support seat, a metering module, a communication module, a display module and a connecting assembly, one side of the support seat is hinged with a protective cover, one side of the support seat is fixedly provided with a connecting seat, the top end of the connecting seat is provided with a plurality of installing grooves, and the installing grooves are connected with the connecting seat. The metering module, the communication module and the display module are slidably mounted in the corresponding mounting grooves, and the connecting assembly is composed of first connecting parts arranged at the bottom ends of the inner walls of the mounting grooves and second connecting parts arranged at the bottom ends of the metering module, the communication module and the display module. And the first connecting part and the second connecting part are inserted and electrically connected. The electric energy meter is convenient to maintain and flexible in function.

The invention discloses a power distribution network pre-disaster investment scheme optimization system and method based on a genetic algorithm, and the method comprises the steps: building a two-stage optimization model containing pre-disaster investment and post-disaster recovery after obtaining basic data; the expected value of post-disaster load recovery can be maximized under the conditions of budget constraint, node capacity, load recovery, network connectivity and the like. A disaster scene is independently modeled according to representative intensity and spatial distribution, a pre-disaster investment scheme is coded through a genetic algorithm, the fitness is evaluated based on a multi-scene expected recovery load, global optimization is achieved through selection, intersection and variation, and a distributed power supply deployment, line reinforcement and controllable switch configuration scheme meeting budget is output. And rapid recovery is realized in cooperation with post-disaster fault isolation and network reconstruction. The load recovery level and the resource utilization efficiency of the power distribution network after disasters are remarkably improved under limited resources, economy and reliability are considered, and the method can be used for disaster-resistant planning and transformation of the power distribution network.

This invention discloses a rapid fault location method for distribution networks, relating to the field of power system operation and maintenance technology. It aims to address the problems of existing transient fault location methods that do not integrate topology and transient signals, resulting in insufficient location accuracy. The method includes: acquiring the transient waveforms of three-phase voltages before and after a fault, and extracting line-mode components through phase-mode transformation; constructing a distribution network topology map, calculating the graph Laplace matrix and performing eigenvalue decomposition to obtain the graph Fourier transform basis; organizing the analyzed signal into a graph signal, and obtaining the spectral coefficients at each time point after transformation; setting a high-frequency cutoff frequency and calculating the node fault irregularity index; performing spatial gradient calculation on the index, and identifying the neighborhood of the node with the largest gradient magnitude and unidirectional index decay as the fault location. This invention integrates distribution network topology and transient spatial features, accurately extracts high-frequency fault information, and provides rapid, high-precision, and anti-interference capabilities, adapting to the rapid fault handling needs of complex distribution networks.

The invention relates to the technical field of power equipment fault positioning, in particular to a power equipment fault positioning method based on a graph neural network, which comprises the following steps of: establishing a Chain-GNN model to be matched with hardware deployment to pre-process data during normal operation of a circuit, and determining normal operation baseline data; step 2, setting an abnormal score threshold and a bidirectional traveling wave fault rule base, and oppositely and synchronously injecting bidirectional traveling waves into a preliminarily alarmed line, and step 4, after a fault point is confirmed, ensuring normal operation of other equipment; after the sublines are erected, first-aid repair is carried out, and after first-aid repair is completed, all the sublines are disconnected, and original circuit connection is recovered; comparing the normal operation baseline data in the step 1 to determine whether the line recovers normal operation, if so, entering a step 6, and if not, returning to the step 3 to re-determine the fault point; and the Chain-GNN model can automatically archive the whole process data of the fault processing at this time.

The application provides a power transmission line distributed fault diagnosis device, which comprises an upper shell and a lower shell which are detachably connected to enclose a containing cavity, opposite ends of the containing cavity are respectively penetrated by semicircular holes which are communicated with the containing cavity, and two semicircular holes at the same end enclose an installation hole; two groups of wire clamping assemblies are respectively arranged in the installation holes at the two ends; a mainboard is arranged in the containing cavity; a power frequency traveling wave hidden danger sensor is in communication connection with an input end of the mainboard; a positioning module is in communication connection with an input end of the mainboard and is used for monitoring time and position information; a communication module is in communication connection with the mainboard and is used for being in communication connection with a monitoring master station; a battery is in electrical connection with the mainboard, the power frequency traveling wave hidden danger sensor and the positioning module; a solar panel is fixedly connected with an outer wall of the upper shell or the lower shell; a power board is in electrical connection with the solar panel, the mainboard, the power frequency traveling wave hidden danger sensor, the positioning module and the battery; and a transparent protective cover covers the solar panel. The application has the advantages of wide monitoring range, fast response speed and high positioning accuracy.

The invention provides a power distribution network fault research and judgment analysis method and system based on artificial intelligence, aiming at solving the problems that fault line selection of a single criterion is easy to cause line selection misjudgment, single-phase grounding load characteristics cannot be known, and fault analysis and fault positioning work cannot be performed in a targeted manner. Multi-source fault information feature data in a power distribution network of a monitoring area are obtained through an RPA robot, single-phase earth fault multi-source data are analyzed through an artificial intelligence algorithm formed by optimizing and fusing a self-adaptive genetic algorithm and a BP neural network, and according to an analysis result of the fault multi-source data through the artificial intelligence algorithm, the fault multi-source data is analyzed. Various electric power data characteristics existing in the single-phase earth fault are identified, then the single-phase earth fault of the power distribution network is automatically positioned, fault line selection and fault positioning power supply services are provided for the single-phase earth fault based on an analysis result and in combination with the actual condition of the power distribution network, and a scientific operation mode optimization strategy is formulated. And safe and stable operation of a power grid is ensured.