A low-voltage power grid fault early warning method and system for a user terminal

Abstract

The application discloses a kind of user terminal-oriented low-voltage power grid fault early warning method and system, belong to fault early warning technical field;In the process of low-voltage power grid operation, the environmental data around user terminal is collected in real time;Collect the real-time operation data of power grid equipment;The environmental data and the real-time operation data of power grid equipment are fused;Based on the data after fusion, the potential mode of power grid fault is identified, and the fault occurrence time is predicted;Fault early warning information and adjustment strategy are fed back to user terminal in real time, real-time monitoring load change after receiving feedback by user, and dynamic adjustment is carried out.The application further ensures that power grid can respond quickly when facing fault risk by dynamically adjusting load and equipment use, reduces the possibility of fault occurrence, thereby effectively improves the operation efficiency, stability and reliability of power grid.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of fault early warning, and specifically relates to a low-voltage power grid fault early warning method and system for user terminals. BACKGROUND

[0002] In recent years, with the development of smart grid technology, especially the continuous progress of environmental perception, data fusion and predictive analysis technology, the fault detection technology of low-voltage power grids has gradually developed in the direction of intelligence and precision. Some researches have proposed early warning of power grid faults by collecting real-time operation data and surrounding environmental data of power grid equipment, combining data fusion and pattern recognition technology. These methods can more accurately capture abnormal states in the operation of power grids, and through data analysis and fault prediction, the possible fault modes of power grids can be identified in advance, thereby providing more warning time for power grid maintenance. However, the existing technology still faces some challenges, such as the time sequence synchronization of environmental data and power grid equipment data, the accuracy of data fusion and the real-time performance of algorithms, which limit the accuracy and effectiveness of the fault early warning system.

[0003] Some low-voltage power grid fault early warning technologies still have deficiencies in data fusion and real-time fault prediction. First, many existing methods rely on simple single sources or linear weighting methods of environmental data and equipment data, which cannot fully capture the complex interaction between power grid equipment and the environment. Second, although some intelligent solutions can monitor the operating state of power grid equipment, they often ignore the potential impact of environmental changes on the state of power grid equipment, especially the impact of temperature, humidity and other factors on the load and operating state of power grid equipment. The existing technology is difficult to accurately evaluate. In addition, most existing systems lack sufficient dynamic adjustment mechanisms when predicting faults, and cannot respond in real time to changes in power grid load and user terminal load adjustment requirements. SUMMARY

[0004] The purpose of the present application is to provide a low-voltage power grid fault early warning method and system for user terminals to solve the problems raised in the background art.

[0005] In order to solve the above technical problems, the present application provides the following technical solutions:

[0006] The application discloses a low-voltage power grid fault early warning method for a user terminal, and comprises the following steps: S1, collecting environmental data around the user terminal in real time during operation of the low-voltage power grid; collecting real-time operation data of power grid equipment; S2, fusing the environmental data and the real-time operation data of the power grid equipment; S3, identifying a potential mode of power grid fault based on the fused data, and predicting a fault occurrence time; and S4, feeding back fault early warning information and adjustment strategies to the user terminal in real time, monitoring load changes of the user after receiving the feedback in real time, and dynamically adjusting.

[0007] As a preferred scheme of the low-voltage power grid fault early warning method for the user terminal, environmental data of an environment where the user terminal is located is collected in real time during operation of the low-voltage power grid after authorization of the user, the environmental data comprises temperature data and humidity data, and the temperature data and the humidity data are collected by a temperature and humidity sensor.

[0008] The operation data of the power grid equipment are collected, the operation data comprises current data and voltage data, the current data is collected by a current transformer, and the voltage data is collected by a voltage transformer.

[0009] As a preferred scheme of the low-voltage power grid fault early warning method for the user terminal, the environmental data is fused with the operation data of the power grid equipment, and the fusion is specifically as follows:

[0010] The environmental data and the operation data of the power grid equipment are time-synchronized to construct a synchronized data set, denoted as , wherein denotes the synchronized data set at a time point t, denotes the i-th environmental data collected at the time point t, denotes the j-th operation data collected at the time point t, T denotes a total number of time points, I denotes a total number of environmental data types, and J denotes a total number of operation data types.

[0011] The synchronized environmental data and the synchronized operation data of the power grid equipment are fused by weighting, and the fusion is specifically as follows:

[0012]

[0013] , wherein denotes a fused data set at the time point t, denotes a preset weight coefficient of the i-th environmental data, denotes a preset weight coefficient of the j-th operation data.

[0014] As a preferred scheme of the low-voltage power grid fault early warning method for the user terminal, the fused data set feature extraction is performed, specifically as follows:

[0015]

[0016] wherein, is the extracted feature dataset, represents current data at time point t, represents temperature data at time point t, and represents a time decay parameter, represents voltage data at time point t, represents humidity data at time point t, and represents a weight coefficient.

[0017] predicting the fault type, specifically as follows:

[0018]

[0019] wherein, represents the predicted fault type, represents the kth feature in the feature dataset K represents the total number of features, represents the preset contribution of the kth feature to the fault type prediction.

[0020] As a preferred scheme of the low-voltage power grid fault early warning method for user terminals according to the present application, the fault occurrence time is predicted, specifically as follows:

[0021]

[0022] wherein, represents the predicted fault occurrence time, represents the start time, represents the time offset coefficient of the kth feature.

[0023] risk assessment is performed based on the predicted fault type and the predicted fault occurrence time , specifically as follows:

[0024]

[0025] wherein, represents the risk value of fault occurrence, represents the preset fault risk factor.

[0026] As a preferred scheme of the low-voltage power grid fault early warning method for user terminals according to the present application, risk assessment is performed based on the risk value of fault occurrence a preset risk value threshold, if the risk value of the fault occurrence is greater than the risk value threshold, generating fault warning information and load scheduling strategy, specifically as follows:

[0027]

[0028] wherein, represents the load adjustment amount at time point t, represents the power grid load at time point t, represents the target load calculated according to the fault warning and load scheduling strategy.

[0029] The calculated load adjustment feedback information and fault warning strategy are transmitted in real time to the user terminal through the communication network of the low-voltage power grid.

[0030] As a preferred scheme of the low-voltage power grid fault warning method for user terminals, the load change situation of the user after receiving the feedback is monitored in real time, and dynamic adjustment is performed, which includes load priority allocation and device maintenance, the load priority allocation refers to preferentially using emergency load, postponing the use of non-emergency load, and temporarily shutting down unnecessary devices, and the device maintenance refers to adjusting the device usage state according to the warning information.

[0031] If the user does not adjust the load according to the suggestion, secondary reminding and feedback correction strategy are provided.

[0032] A low-voltage power grid fault warning system for user terminals, the system comprises: a data acquisition and synchronization module for acquiring environmental data of user terminals and operation data of power grid equipment in real time, and performing time synchronization; a data fusion and feature extraction module for weighted fusion of environmental data and power grid equipment data to generate a fusion data set; feature extraction based on the fusion data set; a fault prediction and risk assessment module for predicting the type of power grid fault based on the extracted feature data, and evaluating the risk value of the fault in combination with the time prediction of the fault occurrence; a load scheduling and warning feedback module for generating fault warning information and load adjustment strategy according to the risk assessment result, and transmitting to the user terminal in real time through the low-voltage power grid communication network; a load dynamic monitoring and adjustment module for monitoring the load change situation of the user terminal after receiving the feedback in real time; if the user does not adjust the load according to the suggestion, secondary reminding and correction strategy are provided.

[0033] ​Compared with the prior art, the present application has the beneficial effects that: by collecting environmental data and operation data of power grid equipment in real time, the overall monitoring of the power grid operation state and the surrounding environment is ensured, thereby providing an accurate basis for subsequent data fusion and fault prediction; by time synchronizing and weightedly fusing the environmental data and the power grid equipment data, the consistency and accuracy of the data are ensured, so that the subsequent analysis can consider the potential impact of environmental factors on the operation of the power grid, thereby improving the accuracy of fault prediction; based on the fused data set, key features are extracted and the fault type and occurrence time are predicted, which can identify potential faults in advance and provide sufficient warning time for power grid managers; combined with the predicted fault risk value, the system feeds back fault warning information and load adjustment strategy in real time, guiding users to optimize electricity load or take energy-saving measures, reducing the burden on the power grid, and improving the safety and stability of the power grid; by dynamically adjusting the load and equipment usage, the power grid can quickly respond when facing fault risks, reducing the possibility of fault occurrence, thereby effectively improving the operation efficiency, stability and reliability of the power grid; this method not only enhances the power grid fault warning capability, but also realizes the collaborative optimization of the power grid, users and equipment, promoting the efficient use of energy and the intelligent management of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0034] The accompanying drawings are included to provide a further understanding of the application, and constitute a part of the specification, illustrate the application, and are used to explain the application together with the embodiments of the application, and do not constitute a limitation on the application.

[0035] Figure 1 is a step schematic diagram of a user terminal-oriented low-voltage power grid fault warning method of the present application;

[0036] Figure 2 is a structure schematic diagram of a user terminal-oriented low-voltage power grid fault warning system of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application. EMBODIMENT

[0038] Please refer to Figure 1 In this embodiment 1: a user terminal-oriented low-voltage power grid fault warning method is provided, which comprises the following steps:

[0039] Step S1: During the operation of the low-voltage power grid, real-time environmental data around the user terminal is collected; real-time operation data of the power grid equipment is collected.

[0040] Specifically, after user authorization, during the operation of the low-voltage power grid, environmental data of the environment where the user terminal is located is collected in real time, the environmental data includes temperature data and humidity data, and the temperature data and humidity data are collected by a temperature and humidity sensor.

[0041] Further, the operation data of the power grid equipment is collected, the operation data includes current data and voltage data, the current data is collected by a current transformer, and the voltage data is collected by a voltage transformer.

[0042] Step S2: Fuse the environmental data with the real-time operation data of the power grid equipment.

[0043] Specifically, the environmental data and the operation data of the power grid equipment are fused to ensure that the environmental data and the power grid equipment data can correspond at the same time point, so as to provide a unified data basis for subsequent fault prediction, specifically as follows:

[0044] The environmental data and the operation data of the power grid equipment are time-synchronized to construct a synchronized data set, denoted as wherein, denotes the synchronized data set at time point t, denotes the i-th environmental data collected at time point t, denotes the j-th operation data collected at time point t, T denotes the total number of time points, I denotes the total number of environmental data types, and J denotes the total number of operation data types.

[0045] Further, the synchronized environmental data and the operation data of the power grid equipment are weighted and fused to consider the influence of different environmental factors on the operation state of the power grid equipment. The environmental data and the equipment data will be combined according to the preset weight to generate a fused data set for subsequent analysis, specifically as follows:

[0046]

[0047] wherein, denotes the fused data set at time point t, denotes the preset weight coefficient of the i-th environmental data, denotes the preset weight coefficient of the j-th operation data.

[0048] Step S3: Based on the fused data, identify the potential mode of the power grid fault and predict the fault occurrence time.

[0049] Specifically, based on the fused data set Feature extraction is performed, specifically as follows:

[0050]

[0051] wherein, is the extracted feature dataset, containing environment and equipment state features related to power grid faults, represents current data at time point t, represents temperature data at time point t, and represents a time decay parameter (the degree of decay of the control feature value over time. This decay effect can simulate the dynamic response delay between power grid equipment and environmental changes, preventing the influence of outdated data), represents voltage data at time point t, represents humidity data at time point t, and represents a weight coefficient, used to adjust the comprehensive influence of the current-temperature feature and the voltage-humidity feature.

[0052] It should be noted that the formula combines equipment current, voltage, and equipment temperature, humidity, and other environmental factors, while considering time decay, so that the feature not only reflects the current power grid state, but also embodies the dynamic changes over a period of time. The time decay term (such as ) can make the most recent data have a greater impact on the feature, consistent with the dynamic response characteristics of power grid equipment; by introducing and two weight coefficients, the contribution of the current-temperature and voltage-humidity features to the overall feature can be flexibly adjusted according to the priority of different equipment or environments. This dynamic weighting method allows the feature extraction function to adapt to different operating states, environmental changes, and equipment characteristics; using a Gaussian-type decay function to consider the time dependence of time series data can avoid using simple historical data average or linear weighted average methods, and is more consistent with the actual application of equipment response characteristics, especially considering that the response of equipment to environmental changes may be delayed over time.

[0053] Predicting the fault type, specifically as follows:

[0054]

[0055] wherein, represents the predicted fault type, represents the kth feature in the feature dataset K represents the total number of features, represents the preset contribution of the kth feature to fault type prediction.

[0056] Further, the predicted failure occurrence time is specifically as follows:

[0057]

[0058] wherein, represents the predicted failure occurrence time, represents the starting time, represents the preset time offset coefficient of the kth feature, reflecting the influence weight of the feature on the failure time.

[0059] In combination with the predicted failure type and the predicted failure occurrence time , the risk assessment is specifically as follows:

[0060]

[0061] wherein, represents the risk value of the failure occurrence, represents the preset failure risk factor.

[0062] Step S4: The failure warning information and the adjustment strategy are fed back to the user terminal in real time, the load change situation of the user after receiving the feedback is monitored in real time, and dynamic adjustment is performed to guide the user to reasonably adjust the power load or take energy-saving measures to reduce the burden of the power grid.

[0063] Specifically, based on the risk value of the failure occurrence , a risk value threshold is preset, and if the risk value of the failure occurrence is greater than the risk value threshold, the failure warning information and the load scheduling strategy are generated, and the specific process is as follows:

[0064]

[0065] wherein, represents the load adjustment amount at time point t, represents the power grid load at time point t, represents the target load calculated according to the failure warning and the load scheduling strategy.

[0066] The calculated load adjustment feedback information and the failure warning strategy are transmitted to the user terminal in real time through the communication network of the low-voltage power grid. In order to ensure the accuracy and timeliness of the feedback, the communication process should have low delay, high reliability, and support the access of different terminal devices.

[0067] Further, the load change situation of the user after receiving the feedback is monitored in real time, and dynamic adjustment is performed, the dynamic adjustment including load priority allocation and device maintenance, the load priority allocation referring to preferential use of emergency load, postponing use of non-emergency load, and temporarily shutting down unnecessary devices, and the device maintenance referring to adjusting the device use state according to the early warning information.

[0068] If the user does not adjust the load according to the suggestion, secondary reminding is performed, and a feedback correction strategy is provided. Embodiment

[0069] Please refer to Figure 2 In the embodiment 2, a low-voltage power grid fault early warning system for a user terminal is provided, which includes: a data acquisition and synchronization module, configured to acquire environmental data (temperature, humidity) around the user terminal and operation data (current, voltage) of power grid equipment in real time, and perform time synchronization on the data, so as to ensure that different types of data correspond at the same time point, thereby providing a unified basis for subsequent data fusion and fault prediction; a data fusion and feature extraction module, configured to perform weighted fusion on the environmental data and the power grid equipment data, and generate a fusion data set. Then, based on the fusion data set, key features (such as current, temperature, humidity, etc.) related to power grid faults are extracted, thereby providing basic data for fault prediction and risk assessment; a fault prediction and risk assessment module, configured to predict the type of power grid fault based on the extracted feature data, and assess the risk value of the fault in combination with the time prediction of the fault. Through the module, the system can identify the fault mode and potential risks in advance, and provide guidance for load adjustment and early warning strategy; a load scheduling and early warning feedback module, configured to generate fault early warning information and load adjustment strategy according to the risk assessment result, and transmit the information to the user terminal in real time through a low-voltage power grid communication network. The module ensures that the user can receive the fault early warning and load adjustment suggestion in time, so as to reduce the burden on the power grid; a load dynamic monitoring and adjustment module, configured to monitor the load change situation of the user terminal after receiving the feedback in real time. If the user does not adjust the load according to the suggestion, the system will perform secondary reminding and provide a correction strategy. The module ensures that the load adjustment strategy is effectively implemented, and dynamically adjusts according to the load change of the user. Embodiment

[0070] In the embodiment 3, a low-voltage power grid fault early warning method for a user terminal is provided, and a simulation experiment is performed to scientifically demonstrate the beneficial effects of the application.

[0071] A simulation scenario is designed to test the fault prediction and load adjustment effect of low-voltage power grid under different environmental conditions. The experiment selects a certain low-voltage power grid area, selects 10 user terminals and their surrounding environmental data (such as temperature, humidity) and power grid equipment operation data (such as current, voltage). All data are collected in real time through installed temperature and humidity sensors, power transformers and voltage transformers. The system uses data fusion and analysis algorithms to predict and fault early warning of the operation state of the power grid.

[0072] The specific implementation process is as follows:

[0073] 1. Data acquisition:

[0074] Before the experiment starts, first obtain the temperature and humidity data around the 10 user terminals through user authorization. These data are collected in real time by temperature and humidity sensors.

[0075] At the same time, the current and voltage data of the power grid equipment are collected through current transformers and voltage transformers. All sensors are connected to the central data processing system in real time, and the data is transmitted to the data storage and analysis platform.

[0076] 2. Data synchronization and fusion:

[0077] Time synchronization is performed on all collected data to ensure that temperature and humidity data and power grid equipment current and voltage data are recorded at the same time point at each moment. After the synchronous data set is constructed, a weighted fusion method is used to process each data.

[0078] The environmental data (such as temperature, humidity) and the operation data of the power grid equipment (such as current, voltage) are weighted according to the preset weight to obtain a fused data set.

[0079] 3. Feature extraction and fault prediction:

[0080] Based on the fused data set, features related to power grid faults are extracted, such as current, temperature, voltage, and humidity data. By setting a time decay coefficient, the dynamic response delay between equipment and environment is reasonably considered.

[0081] A machine learning-based prediction algorithm is used to predict the type and occurrence time of power grid faults, and further generate fault risk assessment results.

[0082] 4. Load adjustment and early warning feedback:

[0083] According to the predicted fault risk value, when the system identifies that the risk value exceeds the threshold value, fault warning information and load scheduling strategy are generated. These information are transmitted to the user terminal in real time through the communication network of the low-voltage power grid.

[0084] The user terminal adjusts the power grid load according to the received feedback, preferentially uses the emergency load, postpones the use of the non-emergency load, and ensures stable operation of the power grid.

[0085] 5. Data monitoring and adjustment:

[0086] After load adjustment, the system monitors the load change of the user in real time, and carries out secondary reminding and feedback correction strategy on the user who does not adjust the load according to the suggestion.

[0087] Through a series of operations, the experiment aims to verify the real-time performance, accuracy and effectiveness of the system in predicting power grid failure and adjusting load under various environmental conditions.

[0088] Table 1 Low-voltage power grid failure warning and load adjustment data

[0089] Time point User terminal temperature (°C) User terminal humidity (%) Current (A) Voltage (V) Predicted fault type Load adjustment amount (kW) 2024-12-01 00:00 25.4 60 10.2 220 Short circuit 3.5 2024-12-01 00:10 26.1 62 10.5 218 Short circuit 3.8 2024-12-01 00:20 26.8 63 11.0 217 Short circuit 4.0 2024-12-01 00:30 27.3 65 11.3 216 Short circuit 4.2 2024-12-01 00:40 28.0 67 11.6 215 Short circuit 4.5

[0090] As can be seen from Table 1, by collecting the temperature, humidity of the user terminal and the current and voltage data of the power grid equipment, the running status of the power grid equipment can be monitored in real time; through data fusion and weighted processing, the system can accurately identify the failure mode at different time points, and predict and optimize the load distribution of the power grid through the change of the load adjustment amount, to avoid the occurrence of failure.

[0091] In Table 1, with the passage of time, the temperature, humidity, and current, voltage data gradually change. In terms of failure prediction, as the environmental temperature and humidity increase, the current gradually increases and the voltage slightly decreases, and the system timely identifies the potential short-circuit failure risk.

[0092] The load adjustment amount gradually increases with the increase of the failure risk value, from 3.5kW to 4.7kW, indicating that the system can provide real-time feedback of the load adjustment demand to ensure stable operation of the power grid.

[0093] The present application provides a precise power grid state evaluation basis by weighted fusion of environmental data (such as temperature, humidity) and power grid equipment operation data (such as current, voltage), compared with the traditional method of simply relying on power grid equipment data, this fusion method can provide more comprehensive and accurate failure prediction under the influence of environmental factors; the time synchronization mechanism is introduced to ensure that the power grid equipment and environmental data correspond at the same time point, thereby avoiding the prediction error caused by asynchronous data, at the same time, through the setting of weight coefficient, the influence of different environmental factors on the power grid equipment can be effectively reflected, and the prediction accuracy is improved.

[0094] When the fault risk value exceeds the preset threshold value, the system can guide the user to adjust the load in real time through the load adjustment strategy, and through the change of the load adjustment amount in the data, the response speed and effectiveness of the system in actual application can be clearly seen, the burden of the power grid is avoided, and the safety and stability of the power grid are improved.

[0095] Through the above data analysis, it can be seen that the present application has significant advantages in many aspects, including fault prediction accuracy, load scheduling flexibility and system response speed; compared with the prior art, the present application can significantly improve the effect of power grid fault warning and load adjustment through the deep fusion of environmental data and equipment data and the dynamic adjustment strategy, reduce the risk of power grid fault occurrence, and ensure the smooth operation of the power grid.

[0096] It should be noted that, in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0097] Finally, it should be noted that: the above only for the preferred embodiments of the present application, and not for limiting the present application, although the present application is described in detail with reference to the foregoing embodiments, for those skilled in the art, it still can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for early warning of low voltage network failure oriented to user terminals, characterized in that, The method comprises the following steps: Step S1: collecting environmental data around the user terminal in real time during the operation of the low-voltage power grid; collecting real-time operation data of power grid equipment; Step S2: fusing the environmental data and the real-time operation data of the power grid equipment; Step S3: identifying potential modes of power grid failure based on the fused data, and predicting the failure occurrence time; Step S4: feeding back the failure warning information and adjustment strategy to the user terminal in real time, and monitoring the load change of the user terminal after receiving the feedback in real time, and dynamically adjusting; The specific implementation process of step S3 comprises: Based on the fusion dataset Feature extraction is performed based on the fusion dataset, as follows: wherein, is the feature dataset after extraction, denotes the current data at time point t, denotes the temperature data at time point t, and denotes the time decay parameter, denotes the voltage data at time point t, denotes the humidity data at time point t, and denotes the weight coefficient, T denotes the total number of time points; Predicting the failure type, specifically as follows: wherein, represents a predicted failure type, represents a feature dataset , k represents the kth feature in the feature dataset, K represents the total number of features, represents a preset contribution degree of the kth feature to the failure type prediction; The specific implementation process of step S3 further comprises: Predicting the failure occurrence time, specifically as follows: wherein, represents a predicted failure occurrence time, represents a start time, represents a preset time offset coefficient of the kth feature; in combination with a predicted failure type and a predicted time of failure occurrence to perform a risk assessment, in particular as follows: wherein, represents a risk value of failure occurrence, represents a preset failure risk factor; The specific implementation process of step S4 comprises: Risk value based on fault occurrence , a preset risk value threshold, if the risk value based on fault occurrence is greater than the risk value threshold, a fault warning information and a load scheduling strategy are generated, specifically as follows: wherein, denotes a load adjustment amount at a time point t, denotes a grid load at a time point t, denotes a target load calculated according to a fault warning and load scheduling strategy; Through the communication network of the low-voltage power grid, the calculated load adjustment feedback information and the failure warning strategy are transmitted to the user terminal in real time.

2. A low voltage power grid failure warning method for a user terminal according to claim 1, characterized in that, The specific implementation process of step S1 comprises: After user authorization, environmental data of the environment where the user terminal is located is collected in real time during the operation of the low-voltage power grid, the environmental data includes temperature data and humidity data, and the temperature data and humidity data are collected by a temperature and humidity sensor; Collecting the operation data of the power grid equipment, the operation data includes current data and voltage data, the current data is collected by a current transformer, and the voltage data is collected by a voltage transformer.

3. A low voltage power grid failure warning method for a user terminal according to claim 2, characterized in that, The specific implementation process of step S2 comprises: Fusing the environmental data and the operation data of the power grid equipment, specifically as follows: time-synchronizing the environment data and the operation data of the power grid equipment, constructing a synchronized data set, denoted as wherein, denotes the synchronized data set at time point t, denotes the i-th environment data collected at time point t, denotes the j-th operation data collected at time point t, T denotes the total number of time points, I denotes the total number of environment data types, and J denotes the total number of operation data types. The synchronized environmental data and the operation data of the power grid equipment are weighted and fused, specifically as follows: wherein, denotes a fusion dataset at a time point t, denotes a preset weight coefficient of the i-th environment data, denotes a preset weight coefficient of the j-th operation data.

4. A low voltage power grid failure warning method for a user terminal according to claim 3, characterized in that, The specific implementation process of step S4 further comprises: Monitoring the load change of the user terminal after receiving the feedback in real time, and dynamically adjusting, the dynamic adjustment includes assigning load priority and device maintenance, the load priority refers to preferentially using emergency load, postponing the use of non-emergency load, and temporarily shutting down unnecessary devices, and the device maintenance refers to adjusting the device usage state according to the warning information; If the user does not adjust the load as suggested, secondary reminders and feedback correction strategies are provided.

5. A user terminal-oriented low-voltage power grid fault early warning system based on the user terminal-oriented low-voltage power grid fault early warning method according to any one of claims 1 to 4, characterized in that: Further comprising: A data collection and synchronization module for collecting environmental data of the user terminal and operation data of the power grid equipment in real time, and performing time synchronization; A data fusion and feature extraction module for weighting and fusing the environmental data and the power grid equipment data to generate a fused data set, and extracting features based on the fused data set; A failure prediction and risk assessment module for predicting the type of power grid failure based on the extracted feature data, and assessing the risk value of the failure in combination with the time prediction of the failure; A load scheduling and warning feedback module for generating failure warning information and load adjustment strategy according to the risk assessment result, and transmitting to the user terminal in real time through the communication network of the low-voltage power grid; A load dynamic monitoring and adjustment module for monitoring the load change of the user terminal after receiving the feedback in real time; if the user does not adjust the load as suggested, secondary reminders and correction strategies are provided. 6.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The computer program is executed by the processor to realize the steps of the user terminal-oriented low-voltage power grid fault early warning method according to any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the user terminal-oriented low-voltage power grid fault early warning method according to any one of claims 1-4.

Images