589results about "Parameter calibration/setting" patented technology

The invention belongs to the field of power systems, and discloses a power distribution network fault autonomous diagnosis and self-healing control method and system based on deep reinforcement learning, and the method comprises the steps: carrying out the collection and preprocessing of the multi-source heterogeneous data of a power distribution network; key feature vectors are extracted from the multi-source heterogeneous data based on a graph convolutional network, and a state representation model is constructed; based on an asynchronous dominant actor-commentator algorithm, constructing a fault diagnosis agent capable of quickly diagnosing faults; a meta-reinforcement learning algorithm is adopted, a dynamic reconstruction strategy library is generated through pre-training, and a self-healing control agent capable of rapidly adapting to various different fault scenes to generate an optimal reconstruction strategy is constructed; constructing a self-healing control module based on virtual impedance matching, wherein the self-healing control module is used for intelligent reconstruction and self-healing control of the power distribution network; a risk-sensitive reward function and a game equilibrium strategy optimization method are introduced to improve performance and robustness; and finally carrying out system deployment and engineering verification.

The invention belongs to the technical field of fault analysis and monitoring, and particularly relates to an intelligent monitoring and fault isolation method and system for a branch box, and the method comprises the steps: carrying out the multi-physical field data fusion collection of the branch box, and obtaining a spatial-temporal feature matrix; performing dynamic feature extraction on the multi-physical field data of the branch box, and outputting a fused dynamic feature vector of the branch box; obtaining a branch box topological graph structure, and obtaining a branch box node fault probability matrix; building a physically constrained fault propagation model based on the branch box node fault probability matrix, obtaining a pre-isolation set, and outputting a dynamic blocking instruction; taking the pre-isolation set as an initial solution space constraint, outputting a fault type and obtaining an isolation instruction; and setting a branch box topology reconstruction constraint, and performing closed-loop control on each branch box node in combination with the isolation instruction to obtain a switching action sequence of each branch box node and a reconstructed power supply path. Precise monitoring, rapid isolation and intelligent reconstruction of the fault of the branch box can be realized, and the operation and maintenance efficiency of the power distribution network is remarkably improved.

The invention discloses a big data-based power distribution network protection setting decision system and method, and relates to the technical field of power distribution network protection, and the system comprises a multi-source data collection module which collects the operation data of a power distribution network; the big data feature processing module is used for carrying out feature extraction and constructing a multi-dimensional feature vector library containing time sequence features and frequency domain features; the protection setting model module is used for constructing a protection setting decision model based on a deep learning framework and carrying out supervised learning training by utilizing historical fault data and a setting scheme; the multi-scene simulation verification module is used for constructing a power distribution network digital simulation model; and the scheme evaluation optimization module is used for establishing an evaluation index system and outputting an optimal protection setting scheme. According to the method, deep learning and historical data are combined, an optimal protection setting scheme is automatically generated, faults are recognized through wavelet transform and Fourier transform, protection parameters are adjusted in real time, mistaken and leaked protection is reduced, timeliness is improved through edge calculation, the strategy is optimized, and the safety of the power distribution network is enhanced.

An intelligent circuit breaker system and method for managing overcurrent conditions includes a current sensor configured to measure electrical current applied to a power line load, a memory storing trip curve data, and a processor configured to evaluate the measured current against a pre-established threshold. Upon detecting an overcurrent condition, the processor starts a timer, evaluates the duration of the overcurrent against the trip curve, and disconnects the load when specified conditions are met. The system can dynamically adjust threshold values based on environmental factors, log operational data, and select appropriate trip curves for specific load types. A user interface provides real-time feedback on current values, timer status, and load disconnection events. Additionally, the system can automatically reset and reconnect the load upon return to safe operating conditions. The functionality is further embodied in a method and as computer-readable instructions for execution by a processor, providing a robust, adaptable, and efficient solution for modern overcurrent protection.

The invention discloses an electrical equipment overload protection method and system based on multistage load monitoring, and relates to the technical field of electrical equipment overload protection, and the method comprises the steps: setting an equipment-level monitoring node, a line-level monitoring node and a system-level monitoring node, and obtaining a three-level load data set; constructing a load characteristic matrix; setting an initial overload threshold conforming to the industrial standard of the switch equipment; a correction coefficient is configured, and the initial overload threshold value is synchronously corrected; drawing up a grading threshold comparison table; meanwhile, a load dynamic constraint mechanism and an equipment health intervention mechanism are set, and electrical equipment overload protection parameter setting is carried out. The technical problems that in the prior art, the overload protection threshold value of the electrical equipment is fixed, dynamic adjustment is lacked, and the adaptability to the health state and load change of the equipment is insufficient, so that protection pertinence and effectiveness are low are solved, accurate overload protection of the electrical equipment is achieved, and the safety of the electrical equipment is improved. And the technical effects of pertinence and effectiveness of overload protection are improved.

The invention discloses a reclosing locking method and system based on winding hot-spot temperature fitting, and relates to the technical field of power transformer dynamic stability assessment, and the method comprises the steps: determining a target transformer, collecting parameters, building a winding current calculation model, calculating steady-state and short-circuit current waveforms, and carrying out the winding temperature rise test of the transformer, the method comprises the following steps: measuring a steady-state temperature rise value, constructing and correcting an electromagnetic heat flow coupling model, generating steady-state and transient-state temperature field data of a winding, constructing a target function of a winding hot-spot temperature, fitting simulation data by utilizing an optimization algorithm, obtaining a fitting function, calculating a winding stress value under a short-circuit working condition in real time, and comparing the winding stress value with a dynamically adjusted stress limit value, so as to obtain a winding stress value. Alarm and locking reclosing are triggered according to the result, and intelligent protection of the transformer is achieved. According to the invention, through accurate parameter acquisition, model establishment, temperature field simulation, hot-spot temperature fitting and stress calculation, real-time monitoring and intelligent protection of the transformer winding under the short-circuit working condition are realized.

The invention discloses a power distribution network 30-degree phase angle difference non-perception loop closing dynamic protection constant value cooperation method, and relates to the technical field of power grid automation, and the method comprises the following steps: extracting a protection equipment connection relation based on a power distribution network topology structure, and constructing a topology model containing a hierarchical membership relation; according to the real-time measurement data, generating an interval load distribution model by adopting a periodic entropy weight correction removing algorithm; simulating a load transfer process under a 30-degree phase angle difference based on the topology model and the interval load distribution model, and outputting current change time sequence data of the transfer path protection equipment; according to the hierarchical membership relationship and the current change time sequence data, calculating and checking a protection constant value, and dynamically adjusting the protection constant value by using an impact tolerance coefficient to generate a final protection constant value; and issuing the final protection constant value to the protection equipment, and triggering load transfer operation.

The invention discloses a relay protection setting value checking optimization method based on an AI technology, and belongs to the technical field of relay protection setting value.The method comprises the steps that historical operation records are collected from an electric power system, a setting value analysis model is established according to the historical operation records, and the setting value analysis model is used for analyzing setting value input data to obtain a relay protection setting value; determining an acquisition item and a data acquisition mode according to the constant value analysis model, and performing data acquisition and processing according to the acquisition item and the data acquisition mode to obtain constant value input data; optimizing and adjusting a data acquisition mode based on the constant value input data; analyzing the constant value input data through a constant value analysis model to obtain a relay protection constant value; optimizing and adjusting the constant value analysis model according to the analysis record of the relay protection constant value; identifying an application protection setting value in real time; and comparing the relay protection constant value with the application protection constant value to obtain a constant value checking result, and optimizing and adjusting the application protection constant value according to the constant value checking result.

The invention discloses an adaptive direct-current partition protection method based on a reconfigurable topology perception fault tree and an improved LSTM (Long Short Term Memory), which is suitable for fault diagnosis and partition protection of a direct-current system of a transformer substation. According to the algorithm, improved dynamic fault tree analysis and a long short-term memory (LSTM) network model are combined, and rapid positioning and selective isolation protection of direct-current system faults are achieved. The method comprises the following steps: firstly, constructing an updatable dynamic fault tree model based on fault historical data, and correcting a fault event weight in real time by adopting a Bayesian method to realize dynamic reconstruction of a fault propagation path; secondly, a multi-target particle swarm optimization algorithm is introduced, optimization is carried out between the minimum protection response time and the minimum isolation range, and an optimal partition scheme is generated; multi-dimensional time sequence characteristics such as fault current and bus voltage are extracted through a multi-channel LSTM model, and the fault development trend is predicted; and finally, dynamically adjusting a trigger threshold and a delay parameter of a protection action in combination with an online reinforcement learning strategy network of an Actor-Critic architecture. The method has the advantages of quick fault response, flexible partition, adaptive protection strategy and the like, and the safety and the stability of the direct current system can be remarkably improved.

The invention discloses a distribution network constant value setting method and system for large-scale distributed photovoltaic grid connection, and relates to the technical field of power system relay protection, and the method comprises the steps: carrying out the protection region division of a power distribution network according to the network topology parameters of the power distribution network, and obtaining a plurality of protection regions; fault characteristic parameters in the protection areas are calculated respectively, and the distributed power supplies in the protection areas are classified and modeled based on the fault characteristic parameters to obtain an equivalent model; and calculating a protection setting value parameter based on the equivalent model, and generating a protection setting value setting result. According to the method, the dynamic response characteristics of the distributed power supply group can be accurately reflected, the problem of large errors of the protection range and sensitivity calculation in a traditional method is effectively solved, and reliable technical support is provided for protection configuration of a large-scale distributed photovoltaic grid-connected power distribution network.

The invention discloses a self-adaptive protection setting method and system for primary and secondary fusion pole-mounted circuit breakers, and relates to the related field of power system emergency protection devices, and the method comprises the steps: obtaining a plurality of primary and secondary fusion pole-mounted circuit breakers; identifying a branch relation, and determining a circuit breaker group including a superior-subordinate relation; setting a short-time activation window, extracting abnormal operation monitoring parameters when the main circuit breaker is abnormal, carrying out recovery time window calculation on the abnormal operation monitoring parameters, and judging whether a linkage protection instruction is sent to the branch circuit breaker or not by comparing the recovery time window with the short-time activation window; if the recovery time window is smaller than the short-time activation window, the linkage protection instruction is not activated, and if the recovery time window is larger than the short-time activation window, the linkage protection instruction is activated. The technical problem of poor protection accuracy and economical efficiency of the existing protection setting for the primary and secondary fusion pole-mounted circuit breaker is solved, and the technical effect of improving the accuracy and economical efficiency of power grid protection is achieved.

The invention discloses a graph topology-based power distribution network protection parameter automatic checking method and system, and belongs to the technical field of power transmission and distribution. The method comprises the steps of obtaining a transformer substation outgoing line protection constant value, a terminal protection constant value, line zero-sequence current data, a topological relation below the transformer substation, line parameters and operation state data of lines, switches and distribution transformers; sVG analysis and power distribution network topological graph construction are carried out; subgraph extraction and hierarchy analysis; line parameter and protection constant value verification, including line parameter verification and protection constant value verification; the line parameter verification comprises branch line segment verification and switch position verification; the protection constant value verification comprises overcurrent I section verification, overcurrent II section verification and zero sequence protection verification. According to the method, automatic checking of the power distribution network protection parameters is realized, the checking efficiency and accuracy are greatly improved, and the method is suitable for a protection constant value checking scene of a complex power distribution network.

The invention discloses a power relay protection monitoring method and device based on intelligent matching and a medium, relates to the field of power relay protection, and solves the problem that a relay protection device is not adaptively arranged in combination with factors such as actual operation conditions during relay protection of a current power system. Matching and acquiring power failure data and power use data of the power line according to the line number; s2, setting relay protection measures of the power line according to the power fault data; s3, real-time operation data of different power lines are collected in real time, and the operation conditions of the power lines are analyzed and judged according to the real-time operation data; step S4, acquiring real-time determined duration of the fault section corresponding to the power line; and S5, analyzing the protection efficiency of the relay protection measure corresponding to the power line according to the determined duration. According to the invention, effective relay protection of the power system is realized based on the intelligently configured relay protection measure.

The invention relates to the field of display, and discloses a short-circuit protection circuit, an array substrate, a display device and a short-circuit protection method.The short-circuit protection circuit is used for an OLED device and comprises the steps that an information sensing module obtains the actual working current of the OLED device and real-time parameters related to the working state of the OLED device; the dynamic expectation calculation module calculates the dynamic expectation working current n of the OLED device according to the real-time parameters and a preset OLED electrical characteristic model; the decision module synthesizes the actual current, the expected current and the current change rate / fluctuation amplitude to generate a risk judgment signal; and the response control module executes protection operation according to the judgment signal. According to the OLED short-circuit protection method, the accuracy, the sensitivity and the intelligent management level of OLED short-circuit protection are remarkably improved through the technology of dynamically calculating the expected current and carrying out decision making and parameter self-adaptive adjustment by fusing the actual current time sequence characteristics.

The invention relates to the technical field of power system relay protection, in particular to a self-adaptive direction overcurrent protection method and system based on real-time load flow calculation. According to the method, operation data are collected and preprocessed in real time, current operation state parameters are obtained based on load flow calculation, and the action current constant value of direction overcurrent protection and the action angle constant value of a direction element are adjusted in a self-adaptive mode in combination with a network topology structure and protection configuration information. When the fault is judged, the real-time operation data and the adjusted action constant value are combined, so that the accurate judgment of the fault direction of a complex power grid structure including a distributed power supply, a micro-grid or an alternating current / direct current hybrid connection and the like and the reliable execution of the protection action are realized; therefore, the problems that a conventional protection constant value is fixed and is difficult to adapt to the change of a power grid operation mode and the fault characteristic change is caused by the access of a distributed power supply are effectively solved, and the selectivity, sensitivity and adaptability of overcurrent protection are remarkably improved.

The invention provides a power distribution network relay protection fixed value setting method and device. The method comprises the following steps: constructing a primary equipment topology connection relation of a power distribution network outgoing line unit; identifying the distributed new energy equipment in the outgoing line unit; searching a path from the distributed new energy equipment to an equivalent bus according to the topological connection relation; recording a primary equipment set in the path; integrating the primary equipment set and the equivalent bus to form global topological connection; calculating the short-circuit current of the power distribution network based on the global topological connection; and setting a fixed value of the relay protection device according to the short-circuit current. According to the invention, by constructing the multi-outlet-unit collaborative topology and identifying the new energy path, the calculation model is simplified, the new energy influence of the same bus is considered, and the short-circuit current calculation precision is improved, so that the efficient and accurate setting of the relay protection setting value is realized, and the stable operation of the power grid is ensured.

A self-triggering, bidirectional control electronics component for an electronic switch (50), for the detection and rapid shutdown of currents at a selected threshold value for both current flow directions, includes a threshold switch having a plurality of selectable shutdown threshold values for both current flow directions, the threshold switch coupled to a bidirectional current sensor system (65), arranged in the electronic switch, based on sensing of sensors on an input side of the threshold switch; and a high-speed de-energizing circuit (53) on an output side of the threshold switch including a high non-load circuit voltage for rapid removal of current from a magnetic drive coil (45), the high-speed de-energizing circuit being configured to rapidly remove the current from the magnetic drive coil when the bidirectional current sensor system senses a current greater than or equal to the selected threshold value among the plurality of selectable shutdown threshold values.

The invention provides a verification method and system for reliable tripping of an electric energy meter, and relates to the technical field of electric energy meters, and the verification method for reliable tripping of the electric energy meter comprises the steps: obtaining detection parameters of the electric energy meter; performing parameter analysis on the electric energy meter detection parameters through the initial monitoring model to obtain an analysis result; finely adjusting the initial monitoring model according to the analysis result to obtain an updated model; according to the updating model, updating the tripping threshold monitoring table; wherein the trip-out threshold monitoring table comprises a plurality of trip-out monitoring thresholds and a trip-out mode formed by the trip-out monitoring thresholds; according to the electric energy meter detection parameters and the tripping threshold monitoring table, a corresponding tripping mode is selected to control tripping; in the tripping process, generating a tripping result according to a feedback signal of the tripping process; and comparing the tripping result with the tripping mode. According to the verification method and system provided by the invention, the reliability of tripping mode selection can be effectively ensured, and meanwhile, the reliability of the tripping process can also be ensured.

The invention relates to the technical field of protection circuits, and discloses an electric leakage protection circuit, electrical equipment and an electric leakage protection method.The electric leakage protection circuit comprises an electric leakage detection switch; the voltage detection unit is configured to detect the input voltage of the power supply end so as to generate a voltage detection signal; the driving unit is configured to determine the input voltage type of the power supply end according to the voltage detection signal; the threshold value generation unit is configured to generate a leakage protection threshold value according to the input voltage type; and the electric leakage protection unit is configured to detect the working current flowing through the electric leakage detection switch and control the load to be in an off state under the condition of judging that the electric leakage phenomenon exists. According to the invention, corresponding electric leakage detection protection can be carried out by detecting different input voltage types, the application scene is expanded, the accuracy and reliability of electric leakage protection under different voltage input conditions can be ensured, and the requirement of users for safe electricity utilization is fully met.

The invention discloses a rapid fusing device for adaptive overload protection, and belongs to the technical field of overload protection. Comprising a multi-dimensional monitoring module used for collecting circuit current, environment temperature and humidity and equipment operation parameters in real time; the intelligent processing module is internally provided with a self-adaptive algorithm unit, and dynamically calculates and adjusts a multi-stage fusing threshold value based on real-time acquired data; the rapid execution module comprises a composite fusing structure and an arc extinguishing unit, and the composite fusing structure executes overload early warning, graded fusing or complete cutting action according to the multi-stage fusing threshold value; and the communication interaction module is used for realizing device state remote monitoring, threshold parameter remote configuration and fault information uploading. Parameters such as current, temperature and humidity are collected in real time through the multi-dimensional monitoring module, a multi-stage fusing threshold value is dynamically adjusted in combination with a self-adaptive algorithm of the intelligent processing module, the limitation that the threshold value of a traditional fuse is fixed is broken through, load fluctuation and environment change can be accurately adapted, and mistaken fusing or protection lag is avoided.

The invention relates to the technical field of electric leakage protection, and particularly discloses a self-adaptive intelligent electric leakage protection system, which comprises a real-time monitoring module used for monitoring electric leakage current magnitude data of any one electric leakage accident of electric equipment in real time, by comparing the electric leakage current magnitude of any one electric leakage accident of the electric equipment with the preset electric leakage current magnitude threshold value, the electric leakage risk of the current electric leakage accident can be analyzed to realize electric leakage protection, and then the electric leakage current magnitude change condition in historical monitoring of the electric equipment is combined; and analyzing the risk level of the future electric leakage accident of the electric equipment based on the electric leakage current magnitude data of the current electric leakage accident, namely estimating the risk level of the future electric leakage accident of the electric equipment, thereby realizing early warning of high-risk electric leakage, and optimizing the circuit electric leakage protection method based on electric leakage early warning. And the situation that the leakage current greatly exceeds the leakage protection threshold value in the future can be avoided.

The invention provides a control method and device for an intelligent self-adaptive voltage protector, and relates to the technical field of voltage protector control, and the method comprises the steps: collecting the input voltage data of a target voltage protector, and obtaining a voltage time-varying behavior set; constructing a voltage dynamic tolerance threshold domain according to the voltage time-varying behavior set of the target voltage protector and the operating parameters of the target voltage protector, and determining a voltage tolerance confidence interval of the target voltage protector through the voltage dynamic threshold domain; according to the voltage tolerance confidence interval, obtaining an electric quality excursion index of the target voltage protector, performing risk prediction on the target voltage protector according to the electric quality excursion index to obtain a voltage risk label, and determining a regulation and control response strategy according to the voltage risk label and a preset risk response; and performing intelligent regulation and control on the target voltage protector through the protection response strategy. According to the invention, the protection range can be adaptively adjusted according to the operation condition and the voltage dynamic characteristics, and the accuracy and reliability of voltage protection are effectively improved.

The invention relates to the technical field of power distribution networks, and discloses a deep learning-based protection setting value setting method for a power distribution network containing a distributed power supply, and the method comprises the following steps: obtaining real-time operation data of the power distribution network, and constructing a dynamic graph representation of the power distribution network according to the real-time operation data; processing the dynamic graph representation by using a graph attention network model, and extracting deep features representing the topological structure and node dynamic information of the power distribution network; according to the method, intelligent perception and rapid diagnosis of faults in a distributed power supply environment, dynamic optimization of protection constant values and serialization decision of subsequent control measures are unified in one framework, information sharing and action cooperation are achieved, and fault diagnosis and constant value calculation are processed in parallel in combination with multi-task learning. The adaptive capacity and decision accuracy of complex operation scenes such as high permeability and variable topological structures of the distributed power supply are improved, and an effective guarantee is provided for safe and stable operation of the distributed power supply after the distributed power supply is connected to the power distribution network.

The invention discloses a protection setting calculation and optimization method based on an intelligent power plant management platform, and relates to the technical field of power system protection. By constructing a platform and equipment communication link, integrally collecting and preprocessing internal and external parameters, and dynamically updating topology and model parameters in combination with a switch state, the problem that a traditional static model is difficult to adapt to operation changes is solved, the timeliness and accuracy of the model are improved, a multi-scene database is constructed in a classified mode, labels are labeled, and the efficiency is improved. Fault current distribution is accurately calculated, constant value adaptability verification is carried out, constant value optimization is carried out in combination with a multi-objective optimization algorithm and sensitivity analysis, limitation of single-scene constant values is avoided, constant value conflicts under different scenes are reduced, reliability of initial constant values is guaranteed, sensitivity analysis is superposed, it is ensured that the constant values are still reliable during parameter fluctuation, and the reliability of the constant values is improved. The risk of protection operation refusal and misoperation is reduced, a constant value is issued, the device state is monitored in real time, evaluation indexes are calculated, the constant value is controllable in the whole process, and stable operation of the device is guaranteed.

The invention discloses an IIDG-accessed power distribution network protection mismatch risk constant value identification and adjustment method and system. The method comprises the following steps: calculating IIDG allowable output fluctuation boundaries corresponding to upstream and downstream protection constant values; when the output fluctuation of the IIDG accords with a set flow starting criterion, judging whether the output fluctuation of the IIDG is in a range of an IIDG allowable output fluctuation boundary corresponding to each protection constant value, and if so, determining that the corresponding protection constant value is a risk constant value; calculating short-circuit current on an upstream line and a downstream line of an IIDG grid-connected point when a short-circuit fault occurs in the current operation state, further adjusting a protection constant value judged as a risk constant value, and updating an IIDG allowable output fluctuation boundary corresponding to the protection constant value; and comparing the adjusted protection setting value with the protection setting value before adjustment, and if the difference exceeds a set allowable range, using the adjusted protection setting value. According to the method, the influence of the IIDG output fluctuation on the protection constant value is quantified, and the reliability of a protection system is remarkably improved.

The invention provides an intelligent voltage protection system and method based on the Internet of Things, and the method comprises the steps: carrying out the equipment action recognition according to behavior association data, and obtaining an equipment external action recognition result of target equipment; performing equipment action recognition according to the internal voltage state data to obtain an internal action recognition result of the target equipment; performing behavior consistency check according to the external action recognition result and the internal action recognition result of the equipment to obtain an external behavior consistency degree, performing dynamic behavior prediction on the target equipment according to the image sensing data and the external behavior consistency degree, and determining an equipment behavior prediction result; the equipment voltage protection threshold value is dynamically adjusted according to the behavior prediction result, intelligent voltage protection is performed on the target equipment through the equipment voltage protection threshold value, the behavior prediction of the target equipment can be performed through the image sensing data of the Internet of Things, and the voltage protection threshold value is dynamically adjusted according to the behavior prediction result. Therefore, voltage false alarm caused by frequent start and stop is avoided.

The invention is applicable to the technical field of electrical systems, and provides a new energy access-oriented real-time power grid dynamic constant value checking method, which comprises the following steps of: constructing a full model by acquiring multi-aspect data of a power grid, generating various research state operation modes, and calculating setting parameters by adopting an iterative algorithm considering a new energy short-circuit characteristic, so that the real-time dynamic constant value checking of the power grid is realized. The sensitivity and selectivity of the protection setting value can be accurately checked in real time. Compared with an existing static checking mode, the implementation mode of the invention can adapt to dynamic changes of a power grid operation mode after new energy access, timely discover potential problems of a protection constant value in a new energy environment, generate early warning information and a constant value recommendation interval, effectively avoid failure of the protection constant value, improve reliability and safety of a power grid protection system, and improve the safety of the power grid protection system. Stable operation of the power grid under the condition of new energy high-permeability grid connection is guaranteed, the problem that the prior art cannot adapt to new energy dynamic changes, and consequently a protection constant value may fail is solved, and powerful support is provided for safe operation of the power grid.

The invention belongs to the technical field of soft starter control, and particularly provides a soft starter control method and system based on dynamic threshold correction and current change prediction, and the method comprises the steps: data collection: collecting the collected data, including the environment temperature, the input current collection and the operation duration of a soft starter; data cleaning and preprocessing; establishing a temperature-time-current threshold correction relation; a soft starter state classification model is constructed based on the long-short-term memory network and used for perfecting the temperature-time-current threshold correction relation constructed in the third step and outputting the soft starter state; soft starter state classification model training optimization and evaluation; and using the trained soft starter state classification model to carry out soft starter operation state discrimination. The method and the system are combined with multi-dimensional data such as temperature and time, a current protection threshold is dynamically adjusted, and the problem that a traditional static constant value is poor in adaptability is solved.

The invention provides a relay protection constant value checking method and device for an automatic protection switch of a distribution network, and relates to the technical field of power grid operation and maintenance, and the method comprises the steps: obtaining the original data of a constant value list of the automatic protection switch; dynamically identifying a communication protocol type based on the head feature of the original data; analyzing the original data according to the identified communication protocol type to obtain fixed value item data; performing fuzzy matching on the obtained fixed value item data and pre-configured source data table data, and establishing a mapping relation; executing at least one of step length compliance verification, numerical range verification and unit compatibility verification on the mapped constant value item; and outputting a checking report containing each checking error and correction suggestion, and performing constant value change downloading according to the checking report. According to the scheme, the verification efficiency and accuracy of the protection setting value can be improved.

An electrical wiring device including: a plurality of line terminals comprising a line-side phase terminal and a line-side neutral terminal; a plurality of load terminals comprising a load-side phase terminal and a load-side neutral terminal; a line conductor electrically coupling the line-side phase terminal to the load-side phase terminal; a neutral conductor electrically coupling the line-side neutral terminal to the load-side neutral terminal; and a controller configured to trigger a trip mechanism to electrically decouple the at least one of the plurality of line terminals from at least one of the plurality of load terminals based, at least in part, on comparing a magnitude of the current differential to a threshold, wherein the threshold is a function of the frequency of the current differential.