684 results about "Feeder line" patented technology

The invention relates to a source-containing power distribution network multi-target collaborative voltage optimization control method based on an FACMAC algorithm, and belongs to the technical field of photovoltaic inversion control. According to the technical scheme, a power distribution network physical system is composed of a plurality of feeder lines, a transformer, a line and a plurality of grid-connected photovoltaic inverters, and each inverter can measure operation information such as local voltage and current in real time; the data acquisition and communication system is used for acquiring node operation data and realizing low-delay communication; the multi-agent reinforcement learning control system is composed of a plurality of distributed agents and factorization centralized Critic modules, and whole-network voltage optimization decision can be carried out in training and execution stages. And the execution unit adjusts the reactive power output of the inverter in real time according to the control instruction. According to the method, the whole-network cooperative regulation and control capability is improved, the training efficiency bottleneck in a high-dimensional scene is relieved, the expression capability on a complex nonlinear coupling relationship is enhanced, and efficient, stable and extensible power distribution network voltage optimization control is realized.

The invention provides a circuit breaker action coil current characteristic diagnosis and analysis system and method. Belongs to the technical field of power system automation and substation state monitoring. The method comprises the following steps: carrying out synchronous wave recording on current of a plurality of circuit breaker actuating coils on a direct current feeder screen side to generate multi-channel synchronous wave recording data; meanwhile, SOE message information is collected, a circuit breaker with specific action is automatically matched and positioned by utilizing a timestamp and action identification information in an SOE message, and action circuit breaker positioning data is generated; the current waveform data of the circuit breaker actuating coil are collected in real time, and a high-precision algorithm is used for feature extraction and analysis, so that abnormal fluctuation in current change can be accurately captured, such as overlarge starting current and unstable holding current, the risk of misoperation or rejection of operation of the circuit breaker caused by abnormal current characteristics is reduced, and the service life of the circuit breaker is prolonged. Electric power system accidents caused by equipment faults are avoided, and the operation reliability of the circuit breaker is improved.

The invention relates to the technical field of electric energy conversion control, and discloses a multi-source load auxiliary power supply power balance control system, which comprises a sampling module, a control module and a modulation module, the sampling module obtains parallel converter branch current and direct current bus voltage; the control module determines a weight by utilizing physical associated association of a bus voltage change gradient and branch current change polarity, corrects a dynamic slope factor determined by a current change rate according to the weight, and performs upper limit clamping on the dynamic slope factor according to a bus voltage margin; according to the invention, the rigid restriction of droop control logic is eliminated, the power deviation generated by asymmetry of feeder impedance is automatically offset while the bus voltage stabilization precision is maintained, and the convergence speed and the certainty of the system during violent load switching are improved.

The invention provides a wide-angle scanning dual-circularly-polarized phased-array antenna unit, which belongs to the field of dual-circularly-polarized antennas and comprises a first dielectric layer, a second dielectric layer and a third dielectric layer which are sequentially stacked, the antenna radiator is arranged on the side, away from the second dielectric layer, of the first dielectric layer, the antenna radiator comprises four radiation patches, each radiation patch comprises a metal patch and a loading branch knot, and each metal patch is provided with a slotted structure; the first metal ground layer is clamped between the first dielectric layer and the second dielectric layer, and a cross coupling gap and a first coupling gap and a second coupling gap which are perpendicular to each other are formed in the first metal ground layer; the U-shaped feeder line is clamped between the second dielectric layer and the third dielectric layer, and two ends of the U-shaped feeder line are respectively connected with a coaxial feed column penetrating through the third dielectric layer; the second metal ground layer is arranged on the side, away from the second dielectric layer, of the third dielectric layer; an array is also provided; the problem that a traditional circularly polarized antenna is narrow in impedance bandwidth and limited in polarization is solved.

The invention relates to the technical field of power systems, and discloses a power distribution network fault positioning method, device and equipment and a medium, and the method comprises the steps: synchronously collecting fault traveling wave data through a transformer area intelligent terminal and a feeder terminal disposed in a power distribution network; dynamically calculating traveling wave transmission parameters based on the topological information and the real-time operation parameters of the power distribution network; performing feature extraction and fusion processing on fault traveling wave data acquired by the transformer area intelligent terminal and the feeder terminal to generate a joint feature matrix; based on the joint feature matrix and the traveling wave transmission parameters, cooperative verification is carried out through the single-end positioning information and the double-end positioning information, and a fault section is determined; and performing fault type identification on the fault section by using the intelligent classification model, and performing consistency verification according to an obtained fault type identification result and the fault section to generate a fault diagnosis result. According to the invention, accurate positioning of the power distribution network fault can be realized, and the problems of positioning blind areas, high cost and easy misjudgment in the prior art are solved.

The invention relates to the technical field of power distribution automation operation and maintenance, in particular to a power distribution automation operation and maintenance method based on electric power big data. The method comprises the following steps: collecting and processing power distribution operation data, calling a fault feature rule set to analyze the power distribution operation data, and identifying and detecting a power distribution fault event; based on the electrical topological structure, the protection action information and the power distribution node on-off state of the current power distribution network, a fault feeder line and a fault section are identified, a switching value logic relation and a topological accessibility model are used for power distribution positioning of a fault event area, and a fault diagnosis result data set is output; and generating a fault isolation operation and maintenance strategy and an overhaul task priority list by using an operation and maintenance scheduling model based on the fault diagnosis result data set and the load transfer capacity, the field operation capacity and the historical overhaul resource distribution information of the power distribution station. According to the method, fault diagnosis and an intelligent scheduling mechanism are fused, and the fault response speed and the operation and maintenance cooperation efficiency of the power distribution system under complex working conditions are improved.

The invention relates to the technical field of arc fault detection, and discloses a method and device for detecting an arc fault in a switch cabinet, and the method comprises the steps: collecting a three-phase current signal of each feeder loop in the switch cabinet, and obtaining target current data through preprocessing; decomposing the target current data to obtain a plurality of current mode components, and performing clustering reconstruction on the plurality of current mode components to obtain an arc feature set; and inputting the arc characteristic set into the time sequence convolutional network embedded with the Mayr arc physical model to carry out fault identification, and obtaining a fault identification result, the Mayr arc physical model is embedded into the time sequence convolutional network, the arc fault detection accuracy is improved, the full-process automatic response from early warning monitoring to emergency isolation is realized, and the fault identification efficiency is improved. A protection action can be completed before a series arc fault evolves into a serious inter-phase short circuit, and the real-time protection capability of the switch cabinet is improved.

An inertia cooperative control method of an integrated optical storage alternating current and direct current hybrid micro-grid comprises the steps that firstly, according to static and dynamic power capacities of energy storage units in direct current sub-grids and allowed direct current voltage deviation, sub-grid equivalent virtual resistance and virtual capacitance are calculated; secondly, RC + R type parallel virtual impedance parameters are distributed according to the power proportion of each energy storage unit, and multi-energy-storage cooperative response power disturbance according to the capacity is achieved; then, a phase angle is generated based on the mapping relation between direct-current side voltage and frequency, an alternating-current voltage amplitude instruction is determined in combination with reactive power droop control and feeder impedance voltage drop compensation, and a dq-axis voltage instruction is generated through virtual impedance compensation; normalized three-phase modulation waves are obtained through voltage-current double closed-loop control and dq / abc coordinate transformation, and six paths of PWM signals are generated to drive an interconnection converter after the normalized three-phase modulation waves are compared with triangular carrier waves. The method does not need to depend on external communication, has the capabilities of autonomous inertia support, voltage and frequency coordinated regulation and reasonable multi-source power distribution, and improves the stability and dynamic response performance of the system under island operation.

The invention discloses an energy storage type SOP black-start method, system and device based on improved VSG network construction control and a medium, and relates to the field of power grid black-start, and the method comprises the steps: an energy storage type converter MMC carries out the active and reactive control based on an improved VSG network construction control strategy; a non-fault side MMC is controlled to firstly close an isolation circuit breaker and slowly charge a direct-current capacitor, and when the voltage reaches a set threshold value, a current-limiting resistor is quitted; the fault side MMC is started by the same step as the non-fault side MMC; after synchronization is completed, AC circuit breakers between the non-fault side MMC and the feeder load and between the fault side MMC and the feeder load are closed respectively; based on the collected power grid power data, MMC output parameters are adjusted to meet the power grid connection condition, the control mode is switched according to the grid connection state, and the black start process is ended. And by arranging the black start resistor for current-limiting charging and sub-module voltage balance control, the phenomena of overcurrent and voltage unbalance in the black start process are avoided.

The embodiment of the invention discloses a high-resistance grounding fault active line selection method, device and system, relates to the technical field of power distribution network relay protection, and aims to solve the problems of low sensitivity and poor reliability of high-resistance grounding fault line selection. The method comprises the following steps: when fault starting is monitored, controlling a switch assembly connected with a damping resistor in a neutral point grounding loop to act so as to change the access state of the damping resistor; collecting bus zero-sequence voltage and zero-sequence current of each feeder line before and after the action of the switch assembly; calculating the zero-sequence active power variation of each feeder line before and after the action; and finally, comparing the zero-sequence active power variation of each feeder line to determine a fault feeder line. According to the invention, excitation is actively injected and the power variation is analyzed, so that the fault characteristics are enhanced, and the method has the beneficial effects of high sensitivity and high reliability.

The invention relates to the technical field of power distribution network fault self-healing, in particular to a power distribution network fault self-healing method based on intelligent distributed feeder automation, which comprises the following steps of: acquiring a permanent fault signal of a feeder section of a power distribution network and an isolated network topology; based on the updated network topology, obtaining a real-time load value weight of each load node in the non-fault power-loss area and an output upper limit of the distributed power supply; an optimal power supply recovery path is determined based on distributed calculation by taking the maximum recovery total load value weight as a target, and the determination of the path needs to meet the output constraint of the available distributed power supply; and controlling the interconnection switch and the section switch on the path to execute switching-on and switching-off operations, forming a new power supply network, completing self-healing, and verifying the power flow distribution in the newly formed power supply network. After power supply is restored, the states of voltage and current are verified through load flow calculation, and voltage out-of-limit is improved through reactive power output adjustment of the distributed power supply without manual intervention.

The invention discloses a super-fusion pole-mounted switch device, belongs to the technical field of switch devices, and discloses the super-fusion pole-mounted switch device which comprises a switch body, a power taking unit and a feeder terminal. The switch body comprises a deep fusion solid-sealed polar pole which is integrally poured, a vacuum arc extinguish chamber, an isolating switch contact and a voltage and current sensor are integrated in the switch body, and the electricity taking unit supplies power to the deep fusion solid-sealed polar pole through a separable spring electric contact structure; the feeder terminal is embedded in the switch box body and is operated in a hot-line mode through a special operating rod. The invention further provides a transient electromagnetic interference suppression module which is used for eliminating electromagnetic interference in the equipment. The CLC topological power taking unit can adapt to multiple working conditions; the state monitoring module is fused with multi-source data to diagnose faults, and the problems that an existing primary and secondary fusion column switch is low in fusion degree, weak in anti-electromagnetic interference, poor in electricity taking reliability and low in intelligence are solved. The equipment can supply power to the 10kV power distribution network intelligently, the reliability is improved, and the operation and maintenance cost is reduced.

The invention discloses a feeder automation test method and system, and relates to the technical field of distribution network automation, and the method comprises the steps: building a qualitative simulation model according to the physical parameters of a power distribution network; performing fault simulation on the power distribution network through the qualitative simulation model to obtain operation states and parameters at different operation moments, and taking the operation states and parameters as typical section sequences; performing fault transient simulation on the power distribution network according to the typical section sequence to obtain a transient simulation result; matching the transient simulation result with a preset strategy library to obtain an optimal processing strategy; and collecting actual action data of feeder automation in a fault scene in real time, and performing consistency comparison on the actual action and the optimal processing strategy to obtain a feeder automation test result. By adopting the embodiment of the invention, the limitation of the traditional simulation step length can be broken through, efficient technical support is provided for logic verification of a feeder automation system in a millisecond response scene, and the test capability of power distribution network fault processing is remarkably improved.

The invention relates to a hierarchical fine net load prediction and lean distribution network planning system, and belongs to the technical field of smart power grids. Comprising a load prediction engine which generates net load curves of a transformer area, a feeder line and a transformer substation according to a spatial hierarchy; the planning decision platform outputs a grid optimization scheme based on the prediction result; the dynamic feedback module is used for collecting operation data in real time to correct the prediction and planning model; according to the invention, the net load prediction error is reduced to below 7%; the utilization rate of distribution network equipment is increased to more than 65%; and the new energy consumption rate is increased by 15-30%. The invention relates to an integrated system integrating multi-level net load prediction and dynamic lean planning.

Disclosed in the present invention are a feeder automation test method and apparatus, a device, and a storage medium. The method comprises: calculating a voltage effective value and a current effective value of each node in a distribution network framework under different fault handling section conditions of a feeder automation system; sending the voltage effective values and the current effective values to a corresponding tester, such that after receiving the voltage effective values and the current effective values, the tester converts the voltage effective values into an analog voltage waveform, converts the current effective values into an analog current waveform, outputs the analog voltage waveform and the analog current waveform to a corresponding field power distribution terminal, and returns switch position change information of the field power distribution terminal; and comparing the switch position change information with preset standard feeder automation action logic in a corresponding fault handling section condition and then, on the basis of a comparison result, obtaining a feeder automation test result. The present invention can improve the reliability of feeder automation tests.

The invention provides a source network load storage power electronic equipment voltage quality hierarchical regulation and control method, and relates to the technical field of power system regulation and control. According to the method, a unified voltage quality index set is established, a layered and hierarchical architecture of a device inner layer, a feeder layer, a station domain layer and a system layer is combined, a multi-layer instruction is generated by utilizing state evaluation, device capability modeling, event grading judgment and collaborative optimization, and a multi-level instruction is generated through feasibility and consistency checking, override triggering and a closed-loop execution mechanism. Dynamic layered management of voltage quality is realized, global standard reaching, device service life and operation economy are considered, and stability, reliability and overall efficiency of power grid operation are effectively improved.

The invention discloses a power distribution feeder fault detection method considering transient frequency response of a distributed power supply, which relates to the technical field of power distribution network fault detection and comprises the following steps: acquiring a voltage traveling wave signal and performing wavelet transformation to obtain a multi-scale wavelet coefficient; calculating wavelet energy entropy and extracting local time-frequency energy characteristics; constructing a time-frequency energy matrix and calculating a norm of the time-frequency energy matrix to judge whether detection is started or not; and after a threshold condition is met, normalizing the energy matrix, screening out invalid data, calculating a non-zero norm, obtaining a distribution proportionality coefficient according to the non-zero norm, and finally completing fault identification. The method has better effects in the aspects of accuracy and applicability.

The invention provides an E-SOP and mobile emergency power supply coordinated multi-feeder power grid optimization scheduling method under an extreme disaster, and belongs to the technical field of power grid scheduling. The method comprises the following steps: calculating the wind speed change of each position by adopting a Batts typhoon wind field model, and establishing an element vulnerability curve to obtain the time-varying failure rate of a power transmission line; a Monte Carlo method is utilized to generate a fault scene, a mobile emergency power supply pre-layout double-layer game optimization model is constructed to determine the quantity capacity and candidate connection positions of an emergency power supply, and an E-SOP operation constraint model is established to realize coordination and cooperation of energy storage charging and discharging and power output of a current converter. And a mobile emergency power supply scheduling constraint and a line maintenance constraint are formulated to ensure reasonable allocation of resources, and finally an optimal configuration scheme of the capacity position of the mobile emergency power supply is determined, so that the technical problem that the power distribution network cannot realize E-SOP and mobile emergency power supply multi-feeder collaborative optimization scheduling under extreme disasters is solved.

The invention discloses a fault diagnosis line selection method based on data driving, and aims to solve the problems that the line selection accuracy is low under complex working conditions such as high-resistance grounding and intermittent arc, and secondary damage of equipment is easily caused by a manual line pulling method in the prior art. The method comprises the following steps: synchronously acquiring zero-sequence current and voltage data of each feeder line; performing multi-scale energy decomposition through wavelet packet transformation; extracting time sequence characteristics of each frequency band by using a parallel gating circulation unit network; constructing a feeder topological graph, and aggregating spatial correlation by adopting a graph convolutional network; and fusing the spatio-temporal characteristics through a self-attention mechanism, and outputting a fault line by a classifier. The system comprises a data synchronous acquisition module, a multi-scale decomposition module, a time domain feature extraction module, a spatial correlation analysis module, a space-time fusion module and a classification module. According to the method, high-precision, high-robustness and non-intrusive fault line selection can be realized without a power grid accurate model and depending on active intervention.

The invention discloses a power distribution network multi-target feeder network reconstruction optimization method and device considering a distributed power supply, equipment and a storage medium, and the method comprises the steps: triggering a multi-mode reconstruction process through presetting an optimization target, a time scale and a safety constraint parameter; integrating real-time data and prediction data into a unified analysis section by adopting a dynamic weighted fusion algorithm; on the basis of load rate calculation and state evaluation results, a load unbalance degree, network loss and a cost function of operation times are considered to search a transfer path, a weight coefficient is dynamically adjusted, and an optimization strategy is generated; and generating a strategy combination through loop iteration, and executing and generating a report after multi-layer security check. According to the power distribution network multi-target feeder network reconstruction optimization method and device considering the distributed power supply, the equipment and the storage medium provided by the invention, multi-target optimization of load balance and line loss reduction of the transformer and the line is realized on the premise of meeting security constraints, and the economy and reliability of power distribution network operation are improved.

The invention relates to the technical field of power fault detection, and mainly relates to a residual voltage detection circuit and a line protection device.The residual voltage detection circuit comprises a sampling circuit and a signal holding circuit, the signal holding circuit adopts double coils and comprises a first coil and a second coil, and a loop where the first coil is located is provided with a first controllable switch tube in series; the first controllable switch tube is connected when the sampling circuit collects residual voltage, a second controllable switch tube is arranged in a loop where the second coil is located in series, the control end of the second controllable switch tube is used for being connected with a feeder terminal, and the signal holding circuit further comprises a residual voltage output branch used for being connected with the feeder terminal. The residual voltage output branch is provided with a first contact of the double coils in series. A sampling circuit is used for obtaining a residual voltage signal generated at the moment of closing of a faulty power grid line, and a signal holding circuit formed by double coils is used for transmitting a sampling signal to a feeder terminal, so that the feeder terminal can still receive the residual voltage signal when the feeder terminal loses power after power supply is recovered.

The invention provides a master station and voltage-time cooperative self-healing method, device and equipment, and belongs to the technical field of power distribution automation of a power system. The method is applied to a power distribution network containing a distributed power supply, and comprises the following steps: when a fault signal of a feeder line and an opening signal of an outgoing circuit breaker are received, detecting whether a splitting signal of a grid-connected switch of the distributed power supply is received within a certain time, and if not, remotely controlling the splitting of the distributed power supply by a power distribution master station; and after delay time is determined according to the fault type of the feeder line and delay waiting is carried out, whether a closing and blocking signal is received is detected, and if yes, the power distribution main station starts self-healing to carry out fault positioning and recover power supply of a non-fault area at the downstream of a fault point. The method can improve the fault processing reliability of the power distribution network, and improves the safety and power supply reliability of the power distribution network.

The invention discloses a single-phase earth fault line selection method based on double-layer parameter adaptive optimization, and the method comprises the following steps: collecting three-phase current corresponding to each feeder line of a target system after the single-phase earth fault of the target system occurs, and carrying out the calculation to obtain zero-sequence transient current; inputting the zero-sequence transient current into a self-adaptive optimization decomposition model for self-adaptive decomposition to obtain an intrinsic mode component of a corresponding feeder line; extracting transient characteristics based on the intrinsic mode component and constructing a transient characteristic matrix; and inputting the transient characteristic matrix into a pre-trained optimization mechanism fault line selection model, outputting a fault posterior probability corresponding to each feeder line, and determining a fault feeder line according to the fault probability. According to the invention, double-layer parameter adaptive optimization is used for carrying out joint optimization on key parameters of a decomposition model and key parameters of a line selection model, so that effective feature extraction and reliable discrimination can still be realized under the conditions of complex zero-sequence transient current high-frequency components and unclear features caused by the access of the distributed power supply; therefore, misjudgment and missed judgment are reduced, and the fault line selection accuracy and robustness are improved.

A multi-port flexible interconnection device for distribution networks, and a control method and system thereof are provided. The multi-port flexible interconnection device includes a bipolar output inverter and a multi-port flexible interconnection module connected in series therewith. The multi-port flexible interconnection module includes multiple unipolar output inverters which share the same common connection bus and are connected in parallel, and AC output ports of each unipolar output inverter are interconnected with different feeders. By adjusting an AC output voltage in series between the feeders, active and reactive power decoupling control for each feeder is achieved. Energy balance for the entire device and its components is maintained by controlling an internal circulating current of the bipolar output inverter. The provided introduces the multi-port flexible interconnection module to interconnect multiple feeders in a distribution network, enabling flexible power interchange between feeders and facilitating a flexible AC distribution network featuring multi-terminal interconnection.

The invention relates to the technical field of digital ring main unit power distribution operation regulation and control, and discloses an intelligent power distribution operation regulation and control system of a digital ring main unit, which comprises a state sensing module, a logic judgment unit and an execution regulation and control module, the logic discrimination unit identifies a feeder power distribution state according to the power flow distribution data and generates a topology reconstruction scheme; the execution regulation and control module drives a switch to act, migrates the feeder loop to a target bus section, forms transition impedance by using closing pre-breakdown current during migration, inhibits transient inrush current, drives an impedance compensation branch to access according to a zero-sequence current vector of the feeder loop, and counteracts neutral point potential drift by using potential bias generated by reactive power injection; according to the method, the power distribution topology is converted from static hard connection to logic remapping, circuit transient state physical process reconstruction and stock hardware redundancy mining are utilized, node power vector balanced distribution is achieved under the condition that the feeder line continuous power receiving state is maintained, and power flow randomness conflicts are eliminated.

The invention discloses a regional main transformer reverse heavy overload-oriented power distribution network collaborative reconstruction regulation and control method. The method comprises the steps of optimizing feeder reverse power flow based on matrix monitoring and optimal distribution, constructing a feeder power flow state matrix, an adjustable equipment state matrix and an adjustable weight matrix, and performing power optimal distribution on the reverse power flow; main transformer cooperative power transfer control is implemented according to main transformer operation state identification and power adjustment margin calculation; and establishing a power distribution network reconstruction multi-objective optimization model fusing feeder line reverse power flow management and main transformer cooperative power transfer, and solving through a second-order cone programming relaxation technology. The invention provides an effective main transformer reverse heavy overload treatment scheme, and through collaborative optimization of the network topology and the local regulation and control strategy, the main transformer reverse heavy overload level is significantly reduced, the network loss is reduced, the absorption capability of the power distribution network to the distributed power supply is improved, and the power distribution efficiency is improved. The problem of stable operation of the power distribution network under the background of high-proportion distributed new energy access is solved.

The invention provides a power distribution network early fault section identification method and system based on multi-dimensional feature probability mapping, and belongs to the technical field of power system power distribution network fault detection. The method comprises the following steps: collecting zero-sequence voltage of a power distribution network bus and zero-sequence current signals of head ends of all feeder lines, and obtaining derivative signals of the zero-sequence voltage and the zero-sequence current signals; calculating the third harmonic energy of the zero-sequence current of each feeder line, and when the third harmonic energy exceeds a set threshold value, judging that the feeder line has an early fault; processing the zero-sequence current signal, and extracting an IMF1 component; calculating a correlation characteristic quantity and a dot product characteristic quantity for each section formed by the current difference values of the adjacent measuring devices based on the IMF1 component; and respectively carrying out standardized transformation on the correlation characteristic quantity and the dot product characteristic quantity, substituting the correlation characteristic quantity and the dot product characteristic quantity into a Laplacian cumulative distribution function, calculating a probability value of a fault in each section, and judging a fault section according to a set probability threshold value. The method can effectively and reliably identify the early fault section of the power distribution network.

The invention provides a load balancing method and system for an automobile charging demand, and is applied to the field of electric data processing. According to the method, the charging load distribution information is identified and dynamically managed and controlled under the multi-layer architecture of the power distribution network, closed-loop control from load identification to model construction to risk prediction to constraint update is realized, the operation state of the charging pile and the operation constraint of the power distribution network can be sensed in real time under the condition of centralized charging of the electric vehicle, and the reliability of the system is improved. The power demand is predicted in advance, a potential risk area is identified, local feeder overload, voltage out-of-limit and electric energy quality deterioration are prevented, risk node power can be actively reduced by introducing risk upper limit judgment and protection measures, three-phase loads are balanced, and stable power supply is guaranteed.

The invention discloses a power distribution network single-phase earth fault line selection method and a related device, and the method comprises the steps: firstly collecting zero-sequence voltage (ZSV) and zero-sequence current (ZSC) data in a power distribution network, carrying out the normalization processing, and constructing a color ZSV-ZSCs image; then, segmenting the image by adopting a full convolutional generative adversarial network (FCGAN), and extracting a fault feeder characteristic waveform from the image; and by calculating similarity (Ds) and continuity (Dc) indexes between a segmentation result and an original signal, a set of fault judgment criteria is established, and effective identification of a bus fault, a line fault and a fault feeder line is realized. The method fully combines image semantic segmentation and feature discrimination strategies, improves segmentation precision and evaluation credibility, can be suitable for an automatic fault detection system under complex working conditions, has the technical advantages of high processing efficiency, high adaptability, high recognition accuracy and the like, and is suitable for fault monitoring and diagnosis scenes of a modern intelligent power distribution network.

The invention discloses a power distribution network sensing and topology dynamic identification method, system and device and a storage medium, and relates to the technical field of power distribution network monitoring and management, and the method comprises the steps: carrying out the real-time data collection and processing of each transformer, line and user side equipment in a power distribution network through edge equipment; based on the data processed by the edge device, system parameter identification of time-varying parameters is carried out, and a resistance value and a reactance value on a feeder line between a transformer outlet and any user ammeter are calculated; uploading a system parameter identification result of the time-varying parameter to a cloud, performing identification and collaborative optimization on a topological structure and line parameters of the whole transformer area power distribution network, and further processing and transmitting to a dispatching center; real-time data acquisition and parameter identification of the power distribution network are realized, line resistance and reactance are accurately mastered, power supply reliability and efficiency are improved, energy consumption and power failure loss are reduced, and safe and stable operation of the power distribution network is guaranteed.