A ring main unit fault rapid early warning method and system

Abstract

This application relates to the field of ring main unit (RNB) engineering, and more particularly to a method and system for rapid early warning of RNB faults. The method includes acquiring operating environment data collected by preset sensors within the RNB housing, and generating an environmental disturbance factor vector based on the operating environment data; filtering the environmental disturbance factor vector based on preset thresholds to obtain an abnormal disturbance factor vector. This application achieves multi-dimensional and comprehensive monitoring of the RNB operating environment, enabling timely identification of potential fault factors such as gas leaks, abnormal humidity, and mechanical vibrations. Compared to single monitoring methods, it effectively eliminates monitoring blind spots and avoids missed fault reports. Through signal processing, it filters out noise interference and extracts effective abnormal features, providing highly reliable data support for fault early warning and significantly improving system sensitivity.

Description

Technical Field

[0001] This application relates to the field of ring main unit engineering, and in particular to a method and system for rapid early warning of ring main unit faults. Background Technology

[0002] In power distribution systems, ring main units (RMS) are critical control and protection devices, and their operational status directly affects the stability of the power grid and the reliability of power supply. When a RMS fails, it can easily trigger regional power outages, causing significant economic losses and social impact. Therefore, it is necessary to establish an effective fault early warning mechanism to significantly reduce the incidence of power outages by identifying and addressing potential faults early, thereby improving the reliability and continuity of the power supply system.

[0003] In existing technologies, ring main unit fault early warning mainly adopts a monitoring scheme based on a single sensor, which judges faults by collecting local state parameters of the equipment. However, this method has obvious technical defects: due to the lack of comprehensive consideration of environmental disturbance factors, it is difficult to accurately assess the combined impact on the equipment's operating status, which often leads to delayed early warning response or missed fault reports, seriously affecting the practical value of the early warning system.

[0004] Therefore, there is an urgent need for a rapid early warning method and system for ring main unit faults. Summary of the Invention

[0005] Therefore, it is necessary to provide a reliable, timely and accurate method and system for rapid early warning of ring main unit faults to address the aforementioned technical problems.

[0006] The technical solution of this invention is as follows:

[0007] A method for rapid early warning of ring main unit faults, the method comprising:

[0008] The system acquires operating environment data collected by each preset sensor inside the ring main unit housing, and generates an environmental disturbance factor vector based on the operating environment data.

[0009] The environmental disturbance factor vector is filtered based on a preset threshold to obtain the abnormal disturbance factor vector;

[0010] The device response data collected by each preset sensor inside the ring main unit is obtained, and the device response vector is obtained by combining them. Based on the device response vector and the abnormal disturbance factor vector, a time delay input vector is generated.

[0011] The time delay input vector is processed based on a preset neural network ring main unit response prediction model, and a predicted response vector is output. The device response amplitude is then generated based on the predicted response vector.

[0012] Calculate the coupling strength score between the device response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map;

[0013] Based on the device response magnitude and the sum of the active path edge weights, the risk level and associated early warning level strategy are output.

[0014] Specifically, the step of acquiring operating environment data collected by each preset sensor inside the ring main unit housing, and generating an environmental disturbance factor vector based on the operating environment data, includes:

[0015] Acquire operating environment data collected by various preset sensors inside the ring main unit housing;

[0016] The operating environment data is combined to construct an environmental disturbance factor vector.

[0017] Specifically, the step of filtering the environmental disturbance factor vector based on a preset threshold to obtain the abnormal disturbance factor vector includes:

[0018] The environmental disturbance factor vector is filtered based on a preset threshold to obtain abnormal disturbance characteristics;

[0019] The aforementioned abnormal perturbation features are integrated to generate an abnormal perturbation factor vector.

[0020] Specifically, the step of acquiring equipment response data collected by each preset sensor inside the ring main unit housing, obtaining an equipment response vector by combining them, and generating a time delay input vector based on the equipment response vector and the abnormal disturbance factor vector includes:

[0021] Acquire the device response data collected by each preset sensor inside the ring main unit housing, and obtain the device response vector by combining them;

[0022] Based on the correlation analysis of the device response vector and the abnormal disturbance factor vector, a cross-correlation function is constructed;

[0023] The peak position of the cross-correlation function is calculated and determined, the corresponding time delay parameters are extracted, and a time delay input vector is constructed based on the time delay parameters.

[0024] Specifically, the preset neural network ring main unit response prediction model processes the time delay input vector, outputs a predicted response vector, and generates the device response amplitude based on the predicted response vector, including:

[0025] The time delay input vector is processed based on a preset neural network ring main unit response prediction model, and the predicted response vector is output.

[0026] The device response amplitude is calculated based on the difference between the predicted value in the predicted response vector and the preset device response benchmark value.

[0027] Specifically, the step of calculating the coupling strength score between the device response vector and the environmental disturbance factor vector, constructing a response risk map based on the coupling strength score, and obtaining the sum of active path edge weights based on the response risk map includes:

[0028] Calculate the coupling strength score between the device response vector and the environmental disturbance factor vector;

[0029] Historical ring main unit fault data and simulated ring main unit experimental data are obtained, and a response risk map is constructed based on the coupling strength score, the historical ring main unit fault data and the simulated ring main unit experimental data;

[0030] The sum of active path edge weights is calculated based on the response risk graph.

[0031] Specifically, the step of outputting a risk level and associated early warning level strategy based on the sum of the device response magnitude and the active path edge weights includes:

[0032] The comprehensive fault score of the ring main unit is calculated based on the sum of the device response amplitude and the active path edge weights.

[0033] Based on the comprehensive fault score of the ring main unit, a risk level is assessed and generated.

[0034] Match the associated early warning level strategy according to the risk level.

[0035] Specifically, a rapid early warning system for ring main unit faults is also provided, the system comprising:

[0036] The environmental disturbance vector generation module is used to acquire the operating environment data collected by each preset sensor inside the ring main unit housing, and generate an environmental disturbance factor vector based on the operating environment data.

[0037] An abnormal disturbance vector acquisition module is used to filter the environmental disturbance factor vector based on a preset threshold to obtain the abnormal disturbance factor vector.

[0038] The time delay input vector generation module is used to acquire the equipment response data collected by each preset sensor inside the ring main unit housing, obtain the equipment response vector by combining them, and generate the time delay input vector based on the equipment response vector and the abnormal disturbance factor vector.

[0039] The device response amplitude generation module is used to process the time delay input vector based on a preset neural network ring network cabinet response prediction model, output a predicted response vector, and generate the device response amplitude based on the predicted response vector.

[0040] The active path weight acquisition module is used to calculate the coupling strength score between the device response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map;

[0041] The early warning level strategy output module is used to output the risk level and associated early warning level strategy based on the device response magnitude and the sum of the active path edge weights.

[0042] Specifically, the environmental disturbance vector generation module is also used to: acquire operating environment data collected by each preset sensor inside the ring main unit housing; and combine the operating environment data to construct an environmental disturbance factor vector.

[0043] Specifically, the abnormal disturbance vector acquisition module is further configured to: filter the environmental disturbance factor vector based on a preset threshold to obtain abnormal disturbance features; and integrate the abnormal disturbance features to generate an abnormal disturbance factor vector.

[0044] Specifically, the time delay input vector generation module is further used to: acquire equipment response data collected by each preset sensor inside the ring main unit housing, and obtain equipment response vectors by combination; construct a cross-correlation function based on the correlation analysis of the equipment response vector and the abnormal disturbance factor vector; calculate and determine the peak position of the cross-correlation function, extract the corresponding time delay parameters, and construct a time delay input vector according to the time delay parameters.

[0045] Specifically, the device response amplitude generation module is further configured to: process the time delay input vector based on a preset neural network ring main unit response prediction model, and output a predicted response vector; and calculate and generate the device response amplitude based on the difference between the predicted value in the predicted response vector and the preset device response benchmark value.

[0046] Specifically, the active path weight acquisition module is further configured to: calculate the coupling strength score between the device response vector and the environmental disturbance factor vector; acquire historical ring main unit fault data and simulated ring main unit experimental data, and construct a response risk map based on the coupling strength score, the historical ring main unit fault data and the simulated ring main unit experimental data; and calculate the sum of active path edge weights based on the response risk map.

[0047] Specifically, the early warning level strategy output module is also used to: calculate a comprehensive fault score for the ring main unit based on the device response amplitude and the sum of the active path edge weights; evaluate and generate a risk level based on the comprehensive fault score of the ring main unit; and match the associated early warning level strategy according to the risk level.

[0048] Optionally, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps described in the above-described method for rapid early warning of ring main unit faults.

[0049] Optionally, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps described in the above-described method for rapid early warning of ring main unit faults.

[0050] This invention relates to machine learning and deep learning technologies, and the technical effects achieved are as follows:

[0051] (1) The above-mentioned rapid early warning method and system for ring main unit faults sequentially acquires the operating environment data collected by each preset sensor inside the ring main unit housing, and generates an environmental disturbance factor vector based on the operating environment data; filters the environmental disturbance factor vector based on a preset threshold to obtain an abnormal disturbance factor vector; acquires the equipment response data collected by each preset sensor inside the ring main unit housing, obtains the equipment response vector by combination, and generates a time delay input vector based on the equipment response vector and the abnormal disturbance factor vector; processes the time delay input vector based on a preset neural network ring main unit response prediction model, outputs a predicted response vector, and generates the equipment response amplitude based on the predicted response vector; The coupling strength score between the device response vector and the environmental disturbance factor vector is calculated, and a response risk map is constructed based on the coupling strength score. The sum of active path edge weights is obtained from the response risk map. Based on the device response amplitude and the sum of active path edge weights, the risk level and associated early warning level strategy are output, realizing multi-dimensional and comprehensive monitoring of the ring main unit's operating environment. It can promptly identify potential fault factors such as gas leaks, abnormal humidity, and mechanical vibration. Compared with single monitoring methods, it effectively eliminates monitoring blind spots and avoids missed fault reports. Through signal processing, noise interference is filtered out, and effective abnormal features are extracted, providing highly reliable data support for fault early warning and significantly improving system sensitivity.

[0052] (2) By constructing a cross-correlation function to calculate the time delay characteristics of environmental disturbance factors and equipment response, a time delay input vector is formed and input into the LSTM neural network model to realize the time-series prediction of equipment dynamic response. This technical solution innovatively breaks through the dependence of traditional prediction models on real-time monitoring data and can identify the fault development trend in advance. In specific implementation, mechanical acoustic features are extracted by short-time Fourier transform and combined with the time delay input vector to effectively predict potential fault risks such as wear of mechanical parts;

[0053] (3) By combining the sum of edge weights of active paths in the response risk map with the device response amplitude, a comprehensive fault score for the ring main unit is obtained, and the risk level is assessed and a matching early warning level strategy is established accordingly. This achieves a comprehensive quantitative assessment and graded early warning of the overall fault risk of the ring main unit, significantly improving the accuracy of risk identification and the timeliness of early warning. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating a rapid early warning method for ring main unit faults in one embodiment;

[0055] Figure 2 This is a structural block diagram of a ring main unit fault rapid early warning system in one embodiment;

[0056] Figure 3 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0057] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0058] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0059] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0060] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0061] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0062] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0063] In one embodiment, a terminal is provided, the terminal being configured to: acquire operating environment data collected by preset sensors within the ring main unit housing, and generate an environmental disturbance factor vector based on the operating environment data; filter the environmental disturbance factor vector based on a preset threshold to obtain an abnormal disturbance factor vector; acquire equipment response data collected by preset sensors within the ring main unit housing, obtain an equipment response vector by combining the data, and generate a time delay input vector based on the equipment response vector and the abnormal disturbance factor vector; process the time delay input vector based on a preset neural network ring main unit response prediction model, output a predicted response vector, and generate an equipment response amplitude based on the predicted response vector; calculate the coupling strength score between the equipment response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map; and output a risk level and associated early warning level strategy based on the equipment response amplitude and the sum of active path edge weights.

[0064] The terminal may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.

[0065] In one embodiment, such as Figure 1 As shown, a method for rapid early warning of ring main unit faults is provided, the method comprising:

[0066] Step S100: Obtain the operating environment data collected by each preset sensor inside the ring main unit housing, and generate an environmental disturbance factor vector based on the operating environment data;

[0067] Step S200: Filter the environmental disturbance factor vector based on a preset threshold to obtain the abnormal disturbance factor vector;

[0068] Step S300: Obtain the equipment response data collected by each preset sensor inside the ring main unit housing, obtain the equipment response vector by combination, and generate the time delay input vector based on the equipment response vector and the abnormal disturbance factor vector;

[0069] Step S400: Process the time delay input vector based on the preset neural network ring network cabinet response prediction model, output the predicted response vector, and generate the equipment response amplitude according to the predicted response vector;

[0070] Step S500: Calculate the coupling strength score between the device response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map;

[0071] Step S600: Based on the device response amplitude and the sum of the active path edge weights, output the risk level and the associated early warning level strategy.

[0072] This application is based on a rapid early warning method and system for ring main unit (RNB) faults. It sequentially acquires operating environment data collected by preset sensors within the RNB housing, and generates an environmental disturbance factor vector based on this data. The environmental disturbance factor vector is then filtered based on a preset threshold to obtain an abnormal disturbance factor vector. Equipment response data collected by preset sensors within the RNB housing is acquired and combined to obtain an equipment response vector. A time delay input vector is generated based on the equipment response vector and the abnormal disturbance factor vector. The time delay input vector is processed based on a preset neural network RNB response prediction model to output a predicted response vector, and the equipment response amplitude is generated based on the predicted response vector. Finally, the coupling strength score between the equipment response vector and the environmental disturbance factor vector is calculated, and based on the... The coupling strength score constructs a response risk map, and the sum of active path edge weights is obtained based on the response risk map. Based on the device response amplitude and the sum of active path edge weights, a risk level and associated early warning level strategy are output, enabling multi-dimensional and comprehensive monitoring of the ring main unit's operating environment. This allows for timely identification of potential fault factors such as gas leaks, abnormal humidity, and mechanical vibrations. Compared to single monitoring methods, this effectively eliminates monitoring blind spots and avoids missed fault reports. Signal processing filters out noise interference and extracts effective abnormal features, providing highly reliable data support for fault early warning and significantly improving system sensitivity. By constructing a cross-correlation function to calculate the time delay characteristics of environmental disturbance factors and device response, a time delay input vector is formed and input into an LSTM neural network model to achieve time-series prediction of the device's dynamic response. This innovative technical solution breaks through the dependence of traditional prediction models on real-time monitoring data and can identify fault development trends in advance. In practical implementation, mechanical acoustic signature features are extracted using short-time Fourier transform and combined with the time-delay input vector to effectively predict potential fault risks such as wear and tear of mechanical components. By combining the sum of edge weights of active paths in the response risk map with the equipment response amplitude, a comprehensive fault score for the ring main unit is obtained, and the risk level is assessed and a corresponding early warning strategy is matched accordingly. This achieves a comprehensive quantitative assessment and graded early warning of the overall fault risk of the ring main unit, significantly improving the accuracy of risk identification and the timeliness of early warning.

[0073] In one embodiment, step S100: acquiring operating environment data collected by each preset sensor inside the ring main unit housing, and generating an environmental disturbance factor vector based on the operating environment data, including:

[0074] Step S100: Obtain the operating environment data collected by each preset sensor inside the ring main unit housing, and generate an environmental disturbance factor vector based on the operating environment data;

[0075] Step S110: Obtain the operating environment data collected by each preset sensor inside the ring main unit housing;

[0076] Step S120: Combine the operating environment data to construct an environmental disturbance factor vector.

[0077] In this embodiment, the collection of operating environment data is mainly achieved by installing sensors on the surface of the ring main unit shell and in key internal areas (such as switch contacts, busbar connections, and mechanical transmission parts). Specifically, the sensor types include: gas leak sensors, distributed humidity probes, and low-frequency micro-vibration detection devices.

[0078] Furthermore, the sensor setup method is as follows:

[0079] Gas Leak Sensor: Miniature sensors are installed at points prone to SF6 gas leaks (such as sealing rings and pipe joints), using a distributed layout (one sensor installed every 5 cm) to collect SF6 concentration data, which is recorded as follows. (Unit: ppm, t is time). This type of sensor has high accuracy and high sensitivity, and can detect trace amounts of SF6 leakage. To ensure data accuracy, the sensor should be calibrated regularly. The calibration cycle can be set according to the frequency of equipment use and environmental conditions, for example, every 3 to 6 months.

[0080] Distributed humidity probe: A patch-type humidity sensor is installed on the surface of a metal component (such as a busbar bracket) inside the cabinet. It is fixed using magnets or a bracket to collect relative humidity data, which is recorded as follows: (Unit: %RH). Humidity probes should have fast response and anti-interference capabilities, enabling accurate humidity measurement in complex electromagnetic environments. Furthermore, the probes should have a certain level of protection to prevent damage from water vapor condensation. To improve the reliability of humidity monitoring, a redundant acquisition design can be adopted, i.e., multiple humidity probes are installed in key areas, and the acquired data is processed using a data fusion algorithm to obtain more accurate humidity values.

[0081] Low-frequency micro-vibration detection device: Vibration sensors are installed at both ends of the cabinet drive shaft, at the connecting rod hinge, and at the bolt heads to capture abnormal stress changes and collect vibration acceleration, which is recorded as follows. Microseismic detection devices should possess broadband and high resolution to capture minute vibration signals. Simultaneously, the device should have good noise immunity, capable of distinguishing between vibrations generated during normal equipment operation and abnormal vibrations. For low-frequency microseismic detection devices, a reasonable sampling frequency should be set; generally, it is recommended that the sampling frequency be no less than 10 times the vibration frequency to ensure complete acquisition of vibration signal characteristics. Furthermore, the acquired vibration data should be analyzed in real time, and wavelet transform signal processing methods should be used to extract characteristic parameters (vibration acceleration) of the vibration signal for subsequent fault diagnosis.

[0082] In this embodiment, the environmental disturbance factor is defined as a time series vector: Each component corresponds to a type of environmental disturbance data.

[0083] In one embodiment, step S200: filtering the environmental disturbance factor vector based on a preset threshold to obtain an abnormal disturbance factor vector includes:

[0084] Step S210: Filter the environmental disturbance factor vector based on a preset threshold to obtain abnormal disturbance characteristics;

[0085] Step S220: Integrate the abnormal perturbation features to generate an abnormal perturbation factor vector.

[0086] In this embodiment, the preset threshold is set as follows:

[0087]

[0088] in, This is the statistical average of historical environmental data. The standard deviation (j=1, 2, 3 corresponds to the three types of signals in the environmental disturbance factor vector: gas concentration, humidity, and vibration acceleration) is given. Let be the preset threshold for the j-th type of signal at time t. This is an adaptive coefficient that changes with time t and is used to adjust the preset threshold. The degree of leniency. This preset threshold formula is used to determine a dynamically changing threshold to judge whether the currently acquired signal belongs to an abnormal situation.

[0089] Furthermore, the adaptive coefficient The calculation is performed using the sliding window mean method, as follows:

[0090]

[0091] Where α is the adjustment coefficient (e.g., 0.1), The window length (e.g., 1 hour). and These are the average values ​​of the current time and a past time (current time minus window length), respectively. This represents the standard deviation at the current moment.

[0092] This calculation method combines the statistical mean of the historical environmental data. and the standard deviation And introduce the adaptive coefficient This can make the preset threshold It can adjust according to changes in the environment and fluctuations in data. Specifically, at time T1, the historical data is t-1, t-2, and so on up to tn, which corresponds to the dynamic preset threshold for T1; at time T2, the historical data is T1, t-1, t-2, and so on up to tn, which corresponds to the dynamic preset threshold for T2. This allows the preset threshold to be dynamically adjusted according to real-time environmental data, thereby improving the accuracy of judging abnormal situations.

[0093] Furthermore, the preset threshold The method for normalizing to dimensionless parameters is as follows:

[0094] in, This is the preset threshold for the j-th type of signal at time t after normalization.

[0095] Furthermore, the method for calculating the normalized value for each signal component is as follows:

[0096]

[0097] in, It is the standardized value of the j-th type signal at time t. It is the actual acquired value of the j-th type signal at time t (e.g., It refers to gas concentration. It's humidity. (This refers to vibration acceleration). This formula is used to standardize the acquired actual signal value, converting it into a dimensionless value. The standardized value can then be more easily compared with a preset threshold to determine if the signal is abnormal.

[0098] Furthermore, for each signal component, a comparison is made. and ,like > These are identified as anomalous perturbation features and extracted, ultimately integrated into an anomalous perturbation factor vector, set as follows:

[0099]

[0100] in, Let be the vector of anomalous perturbation factors at time t. This is an indicator function that takes the value 1 when the condition is met and 0 otherwise. > The value is 1 when the condition is met, and 0 otherwise. Based on the comparison between the standardized value and the preset threshold, abnormal features are extracted from the original acquired signals in the environmental disturbance factor vector. Only when the standardized value exceeds the dynamic threshold will the corresponding original signal value be retained in the abnormal feature vector for subsequent analysis and processing.

[0101] In one embodiment, step S300: acquiring equipment response data collected by each preset sensor inside the ring main unit housing, obtaining an equipment response vector by combining them, and generating a time delay input vector based on the equipment response vector and the abnormal disturbance factor vector, including:

[0102] Step S310: Obtain the equipment response data collected by each preset sensor inside the ring main unit housing, and obtain the equipment response vector by combining them;

[0103] Step S320: Based on the correlation analysis of the device response vector and the abnormal disturbance factor vector, construct a cross-correlation function;

[0104] Step S330: Calculate and determine the peak position of the cross-correlation function, extract the corresponding time delay parameters, and construct a time delay input vector based on the time delay parameters.

[0105] In this embodiment, the collected equipment response data includes the temperature of the load switch contacts: (Unit: °C), Busbar node hotspot temperature: (Unit: °C) Sound characteristics of mechanical transmission: frequency domain feature vector extracted by short-time Fourier transform. The data collection process is as follows:

[0106] Load switch contact temperature: Install high-precision temperature sensors, such as thermocouples or thermistors, at the load switch contacts. These sensors should have fast response and high accuracy, capable of measuring contact temperature changes in real time. The sensors are connected to a data acquisition system via wired or wireless means, which collects contact temperature data at a certain sampling frequency (e.g., once every 10 seconds). To ensure data reliability, ensure good contact between the sensor and the contacts during installation to avoid measurement errors due to poor contact. Simultaneously, the sensors should be calibrated regularly; the calibration cycle can be determined based on the frequency and importance of equipment use, for example, every 36 months.

[0107] Busbar node hotspot temperature: For busbar nodes, especially critical areas prone to hotspots, install infrared or fiber optic temperature sensors. Infrared temperature sensors can measure temperature non-contactly, while fiber optic temperature sensors have the advantage of strong resistance to electromagnetic interference. These sensors collect busbar node temperature data in real time and transmit it to the data acquisition system. The sampling frequency can be set according to actual conditions, such as sampling once every 15 seconds. During data acquisition, the influence of the busbar operating environment, such as interference from surrounding electromagnetic fields, must be considered. For infrared temperature sensors, ensure that the measurement line of sight is unobstructed to obtain accurate temperature data.

[0108] Sound characteristics of mechanical transmission: High-precision acoustic sensors, such as piezoelectric or condenser microphones, are installed in key moving components like gearboxes, bearings, and drive shafts to capture sound signals generated during mechanical transmission. The acoustic sensors transmit the collected sound signals to a data acquisition device, which samples the sound signals at a high frequency (e.g., tens of thousands of samples per second) to ensure the capture of detailed features. The acquired sound signals are time-domain signals. To extract voiceprint features, a Short-Time Fourier Transform (STFT) is used to process the sound signals. The STFT converts the time-domain signal into a frequency-domain signal. By performing Fourier transforms on the sound signals within different time windows, a time-varying frequency-domain feature vector is obtained. When performing STFT (Simultaneous Transmission Tunneling), it is crucial to appropriately select the size of the time window and the movement step size to balance time resolution and frequency resolution. For example, a time window size of 50 milliseconds and a movement step size of 10 milliseconds can be chosen to effectively capture changes in the sound signal while obtaining sufficient frequency resolution. All the aforementioned sensors employ the IEEE 1588 precision clock protocol to avoid data timestamp errors.

[0109] In this embodiment, the device response vector By combining the above three types of equipment response parameters, the operating status of key equipment inside the ring main unit can be comprehensively reflected. Real-time monitoring and analysis of equipment response vectors can promptly detect abnormal operating conditions, providing strong support for fault early warning and maintenance.

[0110] Furthermore, in order to limit the search range, reduce unnecessary calculations, improve analysis efficiency, and focus on finding the correlation between disturbances and device responses within a time range where causal relationships may exist during the subsequent extraction of time delay parameters, a time window needs to be defined. ,in It is the moment when the disturbance occurs. This is the maximum time delay search range, used to search for possible time delay relationships between disturbances and equipment responses on the time axis. It is set to 0.01~0.5 seconds, since the duration of vibration signals from bearing failure impacts is typically <0.5 seconds. It is necessary to cover the transient process of fault impact.

[0111] Furthermore, by calculating the cross-correlation function, the correlation between the environmental disturbance factor vector and the equipment response vector under different time delays can be found. The time delay variable corresponding to the peak position of the cross-correlation function represents the possible time delay relationship between the two, which helps determine the dwell time of the equipment response after an abnormal disturbance occurs. The formula for the cross-correlation function is set as follows:

[0112]

[0113] in, Let the j-th component of the environmental disturbance factor vector and the k-th component of the device response have a time delay of The cross-correlation function at time E is the expected value. Let be the value of the j-th component in the environmental disturbance factor vector at time t. yes The mean, The time delay variable represents the time delay of the device response vector relative to the environmental disturbance factor vector. For the k-th component of the device response vector in time The value, It is the k-th component of the device response vector in time. The mean.

[0114] Furthermore, to determine the optimal delay estimate between the j-th component of the environmental disturbance factor and the k-th component of the equipment response vector, so as to determine the dwell time of the equipment response after an abnormal disturbance occurs, the time delay variable corresponding to the peak position of the cross-correlation function is set as follows:

[0115]

[0116] in, This represents the optimal time delay estimate between the j-th component of the environmental disturbance factor and the k-th component of the equipment response. The time delay variable when the function reaches its maximum value value.

[0117] Furthermore, in order to incorporate the time delay relationship between environmental disturbance factors and device response vectors into the model input, and to more accurately model the dynamic relationship between them for subsequent neural network model prediction, the formula for constructing the time-delayed input vector is set as follows:

[0118] set up It is a column vector, which can be written as:

[0119]

[0120] in, Let be the input vector with time delay at time t. For the first disturbance factor The optimal time delay between time t and a certain device response vector is subtracted from the time t. The value after that is the same for subsequent values.

[0121] In one embodiment, step S400: processing the time delay input vector based on a preset neural network ring main unit response prediction model, outputting a predicted response vector, and generating the device response amplitude based on the predicted response vector, including:

[0122] Step S410: Process the time delay input vector based on the preset neural network ring main unit response prediction model, and output the predicted response vector;

[0123] Step S420: Calculate and generate the device response amplitude based on the difference between the predicted value in the predicted response vector and the preset device response benchmark value.

[0124] In this embodiment, the preset neural network ring network cabinet response prediction model includes a training set, an input layer, an output layer, and a hidden layer, as shown below:

[0125] Training set: The input features of the training set are time-delayed input vectors, i.e., the calculated... The training set contains the values ​​of historical environmental disturbance factors at different time delays, reflecting the dynamic temporal correlation between historical disturbances and equipment responses. The labels of the training set are the corresponding historical equipment response vectors. As the "target value" for model learning, it is used to train the neural network to fit the mapping relationship between "time-delayed input vector → device response vector", so that the model can learn how disturbances affect the device response through historical data.

[0126] Input layer: Input vector is The number of neurons in the input layer and They have the same dimension, that is, 9 neurons (assuming they are the 9 elements mentioned above).

[0127] Hidden layers: can capture multi-layer structures, including:

[0128] First hidden layer: Uses a Long Short-Term Memory (LSTM) network as the non-linear mapping function. It is part of the LSTM layer. LSTM layers help handle long-term dependencies in time series data; the number of neurons can be adjusted according to the actual situation, for example, set to 32 neurons.

[0129] The second hidden layer: Add a fully connected layer (Denselayer) to further process the data output from the LSTM layer. The number of neurons is set to 16; the activation function can be the ReLU (Rectified Linear Unit) function, i.e. This helps to accelerate model convergence.

[0130]

[0131] in, It is the predicted vector of the device response at time t. It is the nonlinear mapping function of the LSTM network. These are the parameters of the neural network model.

[0132] Output layer: Output vector is Its elements are the predicted values ​​of the equipment response. The equipment response includes the load switch contact temperature. Busbar node hotspot temperature and mechanical transmission acoustic characteristics ,but

[0133] The number of neurons in the output layer is the same as the dimension of the device response vector, for example, 3 neurons.

[0134] Furthermore, it is necessary to determine the normal range of the equipment's response. For example, for the temperature of the load switch contacts. ,

[0135] Assuming its normal operating temperature range is ,in That is the lowest normal temperature. That is the highest normal temperature. and Similarly, these normal range values ​​are determined through the equipment manufacturer's specifications or long-term operational experience data.

[0136] Furthermore, the method for calculating the device response amplitude is as follows:

[0137]

[0138] in, It is the device response amplitude. It is the predicted vector of the device response at time t. This is the equipment response baseline value within the normal range (which can be taken as...). ), It is the upper limit of the normal range. It is the lower limit of the normal range.

[0139] In one embodiment, step S500: calculating the coupling strength score between the device response vector and the environmental disturbance factor vector, constructing a response risk map based on the coupling strength score, and obtaining the sum of active path edge weights based on the response risk map, including:

[0140] Step S510: Calculate the coupling strength score between the device response vector and the environmental disturbance factor vector;

[0141] Step S520: Obtain historical ring main unit fault data and simulated ring main unit experimental data, and construct a response risk map based on the coupling strength score, the historical ring main unit fault data and the simulated ring main unit experimental data;

[0142] Step S530: Calculate the sum of active path edge weights based on the response risk graph.

[0143] In this embodiment, the coupling strength score is calculated using the Pearson correlation coefficient formula, and is set as follows:

[0144]

[0145] in, Let be the Pearson correlation coefficient between the j-th component of the environmental disturbance factor vector and the k-th component of the equipment response vector. for covariance, for The standard deviation is used to measure the dispersion of a set of data.

[0146] Furthermore, the coupling strength score is calculated as follows:

[0147]

[0148] in, To score the coupling strength of the ring main unit, the Pearson correlation coefficient is converted into a score of 0-100. exp() represents the Pearson correlation coefficient. The exponent is taken, and the exponential function can convert the correlation coefficient between (-1) and 1 into a positive number, which facilitates subsequent calculations; m and n are index variables used to traverse all disturbance factor components and equipment response components; the denominator is the sum of the exponents of all possible Pearson correlation coefficients. This formula converts the Pearson correlation coefficient into a score of 0-100 through the softmax function, which is used to intuitively evaluate the correlation strength between disturbance factors and equipment responses.

[0149] Furthermore, the steps for constructing the response risk map are as follows:

[0150] (1) Data collection:

[0151] ①Historical Data Collection: Collect historical warning events and actual fault case data from sources such as equipment operation records and maintenance logs. This data includes information such as the type of equipment failure, the time of failure, and abnormal phenomena before the failure.

[0152] ②Simulated data collection: Conduct simulated anomaly experiments to simulate various disturbances that may cause equipment failure, such as gas leakage, humidity changes, mechanical vibration, etc., and record the equipment's response data under these simulated anomalies, including temperature changes, sound characteristics, electrical signal fluctuations, etc.

[0153] (2) Graph initialization:

[0154] ① Disturbance factor nodes: including “SF6 leakage”, “internal wall condensation”, and “structural loosening”.

[0155] ② Equipment response nodes: "Contact temperature rise", "Busbar hot spot", "Abnormal mechanical noise".

[0156] ③ Risk nodes: These are the final results of the fault evolution, such as "insulation failure", "short circuit", "mechanical failure", etc.

[0157] (3) Edge weight determination: Based on historical fault cases, simulated ring network cabinet experimental data and ring network cabinet coupling strength score, initial weights are assigned to the edges between nodes.

[0158] ① The method for calculating the probability of risk transmission is as follows:

[0159]

[0160] in, Let be the edge weight from node j to node k, and let represent the probability of risk propagation. The frequency of occurrence from node j to node k is obtained from historical failure cases and simulated ring main unit experimental data. Let $k$ be the out-degree of node $k$, which is the number of edges originating from node $k$. For all possible edges originating from node k The values ​​are summed to normalize the process so that the sum of the edge weights originating from node j is 1 (or between 0 and 1).

[0161] ②Calculate the risk propagation probability Directly used as edge weight ,Right now = .

[0162] ③ Based on the currently active disturbance factors and equipment response nodes (such as "SF6 leakage + contact temperature rise"), search for all possible paths from the disturbance factor node to the equipment response node in the response risk map. The active path is defined as the path from the starting node to the target node.

[0163] ④ For each path, calculate the sum of its edge weights. For example, path a passes through node (in It is the starting node. If the target node is a certain node, then the sum of the edge weights of path a is:

[0164]

[0165] in, This represents the sum of edge weights for active path a. It also represents the distance from node n1 to node n. i+1 The edge weights. The summation symbol in the formula. Indicates path Sum the edge weights between all adjacent nodes.

[0166] In one embodiment, step S600: Based on the device response magnitude and the sum of the active path edge weights, output the risk level and associated warning level strategy, including:

[0167] Step S610: Calculate the comprehensive fault score of the ring main unit based on the sum of the device response amplitude and the active path edge weights;

[0168] Step S620: Based on the comprehensive fault score of the ring main unit, assess and generate a risk level;

[0169] Step S630: Match the associated early warning level strategy according to the risk level.

[0170] In this embodiment, by combining the sum of edge weights of active paths in the response risk graph with the device response amplitude, the comprehensive fault score setting for the ring main unit is obtained as follows:

[0171]

[0172] in, This represents the sum of edge weights for path a after normalization. For the normalized response amplitude of the i-th device, α and β are weighting coefficients, primarily relying on the in-depth understanding of device failure mechanisms and risk factors by experts in the relevant field. For example, for α (the weighting coefficient of the sum of active path edge weights), experts consider the importance of risk propagation paths during device failure. If experts believe that risk propagation paths play a key role in the occurrence of failure, then the value of α may be large. For β (the weighting coefficient of the device response amplitude value), experts determine it based on the importance of the device response amplitude to failure assessment. If the device response amplitude (such as temperature rise, vibration amplitude, etc.) has an important indicative role in the occurrence and development of failure, then the value of β may be large. Through this method of determining weighting coefficients based on expert experience, a reasonable comprehensive score for device failure can be obtained by comprehensively considering risk propagation paths and the actual response of the device.

[0173] In a specific implementation, assume there are currently two active paths with summed edge weights of respectively. and Regarding the equipment response amplitude, the amplitude value A of "contact temperature rise" is... 触头温升 =20°C, amplitude value A of "busbar hot spot" 母线热斑 =15°C, let... , .

[0174] Therefore, S = 0.6 × (0.4 + 0.3) + 0.4 × (20 + 15) = 14.42

[0175] Furthermore, the steps for assessing and generating risk levels are as follows:

[0176] (1) Assess risk level: Divide risk level ranges: Based on historical data and experience, divide different risk level ranges. For example: low risk: S<10; medium risk: 10≤S<20; high risk: S≥20.

[0177] (2) Determine the current risk level: Based on the calculated comprehensive fault score S, determine the risk level of the current operating status. For example, in the above embodiment, S=14.42 is calculated, so the current risk level is medium.

[0178] (3) Automatic matching of early warning level strategy:

[0179] ① Define the early warning level strategy:

[0180] Low-risk early warning strategy: It may only be necessary to record the current status and conduct routine monitoring, without taking any special measures;

[0181] Medium-risk early warning strategy: Issue early warning notices, increase monitoring frequency, and arrange personnel to conduct preliminary inspections.

[0182] High-risk early warning strategy: Immediately issue an emergency alarm, take emergency measures such as shutting down or switching to backup equipment, and organize professional personnel to conduct a comprehensive inspection and maintenance;

[0183] Based on the risk level assessed, the system automatically matches the corresponding early warning level strategy. For example, for a medium-risk level, the system automatically issues an early warning notification and increases the monitoring frequency.

[0184] ② Self-optimization mechanism:

[0185] The results of early warning responses (such as "no fault occurred after an emergency warning") are fed back to the response risk graph. Based on the feedback, the edge weights between relevant nodes are adjusted. For example, if maintenance measures are taken on a high-risk path and no fault occurs, the weights between relevant nodes on that path can be appropriately reduced to reflect the reduced risk.

[0186] In this embodiment, through steps such as multi-dimensional data acquisition, anomaly identification, latency analysis, neural network prediction, risk map construction, and comprehensive risk assessment, comprehensive monitoring of the ring main unit's operating status and rapid early warning of faults are achieved. Through dynamic adjustment and self-learning mechanisms, the accuracy and adaptability of early warnings are continuously improved, ensuring the reliable operation of the ring main unit in complex environments.

[0187] In one embodiment, such as Figure 2 As shown, a rapid early warning system for ring main unit faults is also provided, the system comprising:

[0188] The environmental disturbance vector generation module is used to acquire the operating environment data collected by each preset sensor inside the ring main unit housing, and generate an environmental disturbance factor vector based on the operating environment data.

[0189] An abnormal disturbance vector acquisition module is used to filter the environmental disturbance factor vector based on a preset threshold to obtain the abnormal disturbance factor vector.

[0190] The time delay input vector generation module is used to acquire the equipment response data collected by each preset sensor inside the ring main unit housing, obtain the equipment response vector by combining them, and generate the time delay input vector based on the equipment response vector and the abnormal disturbance factor vector.

[0191] The device response amplitude generation module is used to process the time delay input vector based on a preset neural network ring network cabinet response prediction model, output a predicted response vector, and generate the device response amplitude based on the predicted response vector.

[0192] The active path weight acquisition module is used to calculate the coupling strength score between the device response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map;

[0193] The early warning level strategy output module is used to output the risk level and associated early warning level strategy based on the device response magnitude and the sum of the active path edge weights.

[0194] In another embodiment, the environmental disturbance vector generation module is further configured to: acquire operating environment data collected by each preset sensor inside the ring main unit housing; and combine the operating environment data to construct an environmental disturbance factor vector.

[0195] In another embodiment, the abnormal disturbance vector acquisition module is further configured to: filter the environmental disturbance factor vector based on a preset threshold to obtain abnormal disturbance features; and integrate the abnormal disturbance features to generate an abnormal disturbance factor vector.

[0196] In another embodiment, the time delay input vector generation module is further configured to: acquire equipment response data collected by each preset sensor inside the ring main unit housing, and obtain equipment response vectors by combination; construct a cross-correlation function based on the correlation analysis of the equipment response vector and the abnormal disturbance factor vector; calculate and determine the peak position of the cross-correlation function, extract the corresponding time delay parameters, and construct a time delay input vector according to the time delay parameters.

[0197] In another embodiment, the device response amplitude generation module is further configured to: process the time delay input vector based on a preset neural network ring main unit response prediction model, and output a predicted response vector; and calculate and generate the device response amplitude based on the difference between the predicted value in the predicted response vector and the preset device response benchmark value.

[0198] In another embodiment, the active path weight acquisition module is further configured to: calculate the coupling strength score between the device response vector and the environmental disturbance factor vector; acquire historical ring main unit fault data and simulated ring main unit experimental data, and construct a response risk map based on the coupling strength score, the historical ring main unit fault data and the simulated ring main unit experimental data; and calculate the sum of active path edge weights based on the response risk map.

[0199] In another embodiment, the early warning level strategy output module is further configured to: calculate a comprehensive fault score for the ring main unit based on the device response magnitude and the sum of the active path edge weights; evaluate and generate a risk level based on the comprehensive fault score for the ring main unit; and match an associated early warning level strategy according to the risk level.

[0200] In one embodiment, such as Figure 3 As shown, a computer device is also provided, including a memory and a processor. The memory stores a computer program and an operating system. When the processor executes the computer program, it implements the steps described in the machine vision-based separator sieve surface separation and detection method. The computer device also includes a system bus, internal memory, network structure, display screen, and input devices.

[0201] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps described in the above-described method for rapid early warning of ring main unit faults.

[0202] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0203] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0204] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0205] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0206] This application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0207] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0208] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0209] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographic device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0210] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0211] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0212] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0213] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0214] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

[0215] One embodiment of this application also provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above-described methods.

[0216] The computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above description is an example of a computer device and does not constitute a limitation on the computer device. It may include more or fewer components than described above, or a combination of certain components, or different components, such as input / output devices, network access devices, etc.

[0217] The processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0218] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard drive or RAM. In other embodiments, the memory may be an external storage device of the computer device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory may include both internal and external storage units of the computer device. The memory is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory can also be used to temporarily store data that has been output or will be output.

[0219] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0220] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for rapid early warning of ring main unit faults, characterized in that, The method includes: The system acquires operating environment data collected by each preset sensor inside the ring main unit housing, and generates an environmental disturbance factor vector based on the operating environment data. The environmental disturbance factor vector is filtered based on a preset threshold to obtain the abnormal disturbance factor vector; The system acquires equipment response data collected by various preset sensors within the ring main unit housing. The equipment response data includes load switch contact temperature, busbar node hot spot temperature, and mechanical transmission noise characteristics. The system obtains an equipment response vector by combining these data. Based on the correlation analysis between the equipment response vector and the abnormal disturbance factor vector, a cross-correlation function is constructed. The peak position of the cross-correlation function is calculated and determined. The corresponding time delay parameter is extracted, and a time delay input vector is constructed based on the time delay parameter. The time delay input vector is processed based on a preset neural network ring main unit response prediction model, and a predicted response vector is output. The device response amplitude is then generated based on the predicted response vector. Calculate the coupling strength score between the device response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map; Based on the device response magnitude and the sum of the active path edge weights, the risk level and associated early warning level strategy are output.

2. The rapid early warning method for ring main unit faults according to claim 1, characterized in that, The step of acquiring operating environment data collected by each preset sensor inside the ring main unit housing, and generating an environmental disturbance factor vector based on the operating environment data, includes: Acquire operating environment data collected by various preset sensors inside the ring main unit housing; The operating environment data is combined to construct an environmental disturbance factor vector.

3. The rapid early warning method for ring main unit faults according to claim 1, characterized in that, The step of filtering the environmental disturbance factor vector based on a preset threshold to obtain the abnormal disturbance factor vector includes: The environmental disturbance factor vector is filtered based on a preset threshold to obtain abnormal disturbance characteristics; The aforementioned abnormal perturbation features are integrated to generate an abnormal perturbation factor vector.

4. The rapid early warning method for ring main unit faults according to claim 1, characterized in that, The preset neural network ring main unit response prediction model processes the time delay input vector, outputs a predicted response vector, and generates the device response amplitude based on the predicted response vector, including: The time delay input vector is processed based on a preset neural network ring main unit response prediction model, and the predicted response vector is output. The device response amplitude is calculated based on the difference between the predicted value in the predicted response vector and the preset device response benchmark value.

5. The rapid early warning method for ring main unit faults according to claim 1, characterized in that, The calculation of the coupling strength score between the device response vector and the environmental disturbance factor vector, the construction of a response risk map based on the coupling strength score, and the acquisition of the sum of active path edge weights based on the response risk map include: Calculate the coupling strength score between the device response vector and the environmental disturbance factor vector; Historical ring main unit fault data and simulated ring main unit experimental data are obtained, and a response risk map is constructed based on the coupling strength score, the historical ring main unit fault data and the simulated ring main unit experimental data; The sum of active path edge weights is calculated based on the response risk graph.

6. The rapid early warning method for ring main unit faults according to claim 1, characterized in that, The strategy for outputting a risk level and associated early warning level based on the sum of the device response magnitude and the active path edge weights includes: The comprehensive fault score of the ring main unit is calculated based on the sum of the device response amplitude and the active path edge weights. Based on the comprehensive fault score of the ring main unit, a risk level is assessed and generated. Match the associated early warning level strategy according to the risk level.

7. A rapid early warning system for ring main unit faults, characterized in that, The system includes: The environmental disturbance vector generation module is used to acquire the operating environment data collected by each preset sensor inside the ring main unit housing, and generate an environmental disturbance factor vector based on the operating environment data. An abnormal disturbance vector acquisition module is used to filter the environmental disturbance factor vector based on a preset threshold to obtain the abnormal disturbance factor vector. The time delay input vector generation module is used to acquire equipment response data collected by various preset sensors inside the ring main unit housing. The equipment response data includes load switch contact temperature, bus node hot spot temperature, and mechanical transmission noise characteristics. The module obtains the equipment response vector by combining the data. Based on the correlation analysis between the equipment response vector and the abnormal disturbance factor vector, a cross-correlation function is constructed. The peak position of the cross-correlation function is calculated and determined, and the corresponding time delay parameters are extracted. The time delay input vector is constructed based on the time delay parameters. The device response amplitude generation module is used to process the time delay input vector based on a preset neural network ring network cabinet response prediction model, output a predicted response vector, and generate the device response amplitude based on the predicted response vector. The active path weight acquisition module is used to calculate the coupling strength score between the device response vector and the environmental disturbance factor vector, construct a response risk map based on the coupling strength score, and obtain the sum of active path edge weights based on the response risk map; The early warning level strategy output module is used to output the risk level and associated early warning level strategy based on the device response magnitude and the sum of the active path edge weights.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images