Electrical equipment fault prediction method and system, electronic equipment and storage medium

Abstract

The invention discloses an electrical equipment fault prediction method and system, electronic equipment and a storage medium, and the method comprises the steps: carrying out the data collection processing of a key node of electrical equipment, obtaining a loop resistance data flow, carrying out the feature extraction and time sequence analysis processing of the loop resistance data flow, and obtaining an analysis result, and performing fault prediction processing on the analysis result according to a preset alarm threshold value to obtain early warning information, and performing alarm display on the early warning information through a remote monitoring interface. The embodiment of the invention can improve the operation safety and reliability of the electrical equipment, and can be widely applied to the technical field of equipment detection.

Description

Technical Field

[0001] This application relates to the field of equipment testing technology, and in particular to a method, system, electronic device and storage medium for predicting electrical equipment faults. Background Technology

[0002] In related technologies, the main methods for assessing the condition of high-voltage equipment connection points include offline loop resistance testing and infrared thermography. However, in practical applications, it has been found that while offline loop resistance testing can directly measure resistance values, it requires power outages, which is time-consuming and labor-intensive, and cannot provide real-time or continuous monitoring, making it difficult to detect dynamic changes or the true state under load. Infrared thermography, while capable of detecting overheating, is an indirect method; temperature is affected by various factors such as ambient temperature, load current, and heat dissipation conditions, making it difficult to accurately assess resistance values. Furthermore, it typically involves periodic manual inspections and cannot provide continuous monitoring or early warning capabilities. In summary, the technical problems existing in these technologies need to be addressed. Summary of the Invention

[0003] The main objective of this application is to propose a method, system, electronic device, and storage medium for predicting electrical equipment faults, which can provide early warning of electrical equipment faults and improve equipment safety.

[0004] To achieve the above objectives, one aspect of this application proposes a method for predicting electrical equipment faults, the method comprising:

[0005] Data acquisition and processing are performed on key nodes of electrical equipment to obtain loop resistance data stream;

[0006] Feature extraction and timing analysis are performed on the loop resistance data stream to obtain the analysis results;

[0007] Based on a preset alarm threshold, the analysis results are processed for fault prediction to obtain early warning information;

[0008] The warning information is displayed via a remote monitoring interface.

[0009] In some embodiments, the step of acquiring and processing data from key nodes of electrical equipment to obtain a loop resistance data stream includes the following steps:

[0010] Based on the high-voltage environment and equipment structure, loop resistance measurement sensors are installed at key nodes of the electrical equipment.

[0011] The sampling frequency and acquisition accuracy are set according to the type, voltage level, and maintenance strategy of the electrical equipment.

[0012] The loop resistance measurement sensor performs online measurement and processing of the loop resistance of the key node according to the sampling frequency and the acquisition accuracy to obtain the loop resistance data stream.

[0013] In some embodiments, the step of performing feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results includes the following steps:

[0014] The loop resistance data stream is subjected to integrity and validity verification processing to obtain verification data;

[0015] The verification data is subjected to loop resistance change characteristic analysis to obtain change characteristic parameters;

[0016] The change pattern analysis is performed on the change feature parameters based on the pre-trained time series analysis model to obtain the analysis results.

[0017] In some embodiments, performing integrity and validity verification processing on the loop resistance data stream to obtain verification data includes the following steps:

[0018] Perform data packet integrity verification on the loop resistance data stream to obtain a complete data packet;

[0019] The complete data packet is subjected to data payload validity verification processing according to the sensor's operating range to obtain the verification data.

[0020] The verification data is stored in the data cache area based on the timestamp.

[0021] In some embodiments, before performing change pattern analysis on the change feature parameters according to the pre-trained time series analysis model, the method further includes pre-training the time series analysis model, specifically including the following steps:

[0022] Retrieve the historical data sequence of loop resistance from the data buffer for a preset window;

[0023] The historical data sequence of the loop resistance is preprocessed to obtain preprocessed data;

[0024] The preprocessed data is subjected to time series forecasting processing using the exponential smoothing method to obtain the forecasted data.

[0025] Fault mode data is constructed based on historical fault data;

[0026] The fault mode data and the prediction data are determined as the training dataset, and the training dataset is input into the time series analysis model to output the classification result;

[0027] The classification results are used to calculate the function loss based on the labels of the fault mode data, and the parameters of the time series analysis model are adjusted based on the loss value.

[0028] In some embodiments, the step of performing fault prediction processing on the analysis results based on a preset alarm threshold to obtain early warning information includes the following steps:

[0029] Based on the preset alarm threshold, the loop resistance value in the analysis result is analyzed to obtain the current loop status;

[0030] The current circuit state is input into the fault prediction model for prediction processing to obtain the remaining lifetime;

[0031] The warning information is obtained by performing rule matching processing on the preset alarm threshold, the current circuit state, and the remaining lifetime according to the alarm rule base.

[0032] In some embodiments, the step of performing rule matching processing on the preset alarm threshold, the current circuit state, and the remaining lifetime according to the alarm rule base to obtain the warning information includes the following steps:

[0033] The alarm level is obtained by matching the current circuit state and the remaining lifetime according to the preset alarm threshold.

[0034] The alarm content is generated by processing the alarm level according to the alarm rule base.

[0035] The warning information is determined based on the alarm level and the alarm content.

[0036] To achieve the above objectives, another aspect of this application proposes an electrical equipment fault prediction system, the system comprising:

[0037] The first module is used to collect and process data from key nodes of electrical equipment to obtain loop resistance data stream.

[0038] The second module is used to perform feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results.

[0039] The third module is used to perform fault prediction processing on the analysis results based on a preset alarm threshold to obtain early warning information.

[0040] The fourth module is used to display the warning information through a remote monitoring interface.

[0041] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0042] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0043] The embodiments of this application include at least the following beneficial effects: This application provides a method, system, electronic device, and storage medium for predicting electrical equipment faults. This solution obtains a loop resistance data stream by collecting and processing data from key nodes of the electrical equipment. It then performs feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results. Based on a preset alarm threshold, it performs fault prediction processing on the analysis results to obtain early warning information. The early warning information is displayed through a remote monitoring interface. The embodiments of this application can perform online non-contact monitoring of the loop resistance of high-voltage electrical equipment. By continuously collecting data, it dynamically identifies minor degradations, provides early warnings, and provides early warning information to guide optimized maintenance strategies by predicting fault conditions, thereby improving equipment safety. Attached Figure Description

[0044] Figure 1 This is a flowchart of an electrical equipment fault prediction method provided in an embodiment of this application;

[0045] Figure 2 This is a schematic diagram of the structure of an electrical equipment fault prediction system provided in an embodiment of this application;

[0046] Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of systems and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0048] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0049] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0051] High-voltage electrical equipment is a core component of the power system, and its safe and stable operation is crucial for ensuring the reliability of the power grid. Equipment failures often originate from abnormalities in critical nodes such as contactors, circuit breaker contacts, or busbar connections, especially due to increased circuit resistance caused by corrosion, loosening, or wear. This can lead to localized overheating, which in severe cases may cause equipment burnout or even trigger a large-scale power outage.

[0052] Among related technologies, offline loop resistance testing and infrared thermography are used to assess the condition of high-voltage equipment connection points. Offline loop resistance testing can directly measure resistance values, but its biggest drawback is that it requires power outages, which is time-consuming and labor-intensive, and it cannot provide real-time, continuous monitoring, making it difficult to detect dynamic changes or the true state under load. Infrared thermography can detect overheating, but it is an indirect method. Temperature is affected by various factors such as ambient temperature, load current, and heat dissipation conditions, making it difficult to accurately assess resistance values. Furthermore, it is usually performed periodically by manual inspection, failing to provide continuous monitoring and early warning capabilities. In addition, preventative maintenance based on fixed cycles cannot accurately reflect the actual degree of equipment degradation, potentially leading to under- or over-maintenance.

[0053] In view of this, this application provides an electrical equipment fault prediction method, system, electronic device, and storage medium. This solution obtains a loop resistance data stream by collecting and processing data from key nodes of the electrical equipment. It then performs feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results. Based on a preset alarm threshold, it performs fault prediction processing on the analysis results to obtain early warning information. The early warning information is displayed through a remote monitoring interface. This application embodiment enables online non-contact monitoring of the loop resistance of high-voltage electrical equipment. By continuously collecting data, it dynamically identifies minor degradations, provides early warnings, and provides early warning information to guide optimized maintenance strategies by predicting fault conditions, thereby improving equipment safety.

[0054] This application provides a method for predicting electrical equipment faults, relating to the field of equipment testing technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the electrical equipment fault prediction method, but is not limited to the above forms.

[0055] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0056] Figure 1 This is an optional flowchart of an electrical equipment fault prediction method provided in an embodiment of this application. Figure 1 The method may include, but is not limited to, steps S101 to S104.

[0057] Step S101: Data acquisition and processing are performed on the key nodes of the electrical equipment to obtain the loop resistance data stream;

[0058] Step S102: Perform feature extraction and time-series analysis on the loop resistance data stream to obtain the analysis results;

[0059] Step S103: Perform fault prediction processing on the analysis results according to the preset alarm threshold to obtain early warning information;

[0060] Step S104: Display the warning information via the remote monitoring interface.

[0061] Steps S101 to S104 of this embodiment involve installing dedicated online loop resistance measurement sensors at predetermined key nodes of the high-voltage electrical equipment and collecting loop resistance data streams from these key nodes in real time. This embodiment can also use wireless data transmission technology to synchronously and stably transmit the real-time collected loop resistance data streams from the key nodes to a remote monitoring and analysis system. This remote monitoring and analysis system has data reception, buffering, and preliminary verification functions to ensure the integrity and reliability of data transmission. In the remote monitoring and analysis system, a module integrating intelligent analysis algorithms performs time-series analysis and feature extraction on the pre-verified loop resistance data stream, dynamically identifying the analysis results. These results include the loop resistance variation pattern over time, degradation trends, and abnormal signals. Then, based on the identified variation patterns, degradation trends, and abnormal signals, combined with preset alarm thresholds and fault prediction models, differentiated early warning information for potential fault risks of the high-voltage electrical equipment is generated and published, and displayed through a remote monitoring interface or communication interface.

[0062] One of the above technical solutions has the following advantages or beneficial effects: The embodiments of this application can improve the operational safety of electrical equipment by continuously, non-contactly or with low impact monitoring of the circuit resistance of high-voltage electrical equipment, and by combining intelligent analysis for early warning and predictive maintenance.

[0063] In some embodiments, the step of acquiring and processing data from key nodes of electrical equipment to obtain a loop resistance data stream includes the following steps:

[0064] Based on the high-voltage environment and equipment structure, loop resistance measurement sensors are installed at key nodes of the electrical equipment.

[0065] The sampling frequency and acquisition accuracy are set according to the type, voltage level, and maintenance strategy of the electrical equipment.

[0066] The loop resistance measurement sensor performs online measurement and processing of the loop resistance of the key node according to the sampling frequency and the acquisition accuracy to obtain the loop resistance data stream.

[0067] In this embodiment, at critical nodes such as connection contacts, circuit breaker contacts, or busbar connections in high-voltage electrical equipment, installation locations are selected based on the high-voltage environment and equipment structure. Online loop resistance measurement sensors are installed, employing non-contact or low-impact measurement principles based on magnetic field, temperature, or acoustic physical effects to indirectly monitor the loop resistance status of critical nodes. These sensors are designed to operate safely and reliably in high-voltage, high-current environments and continuously acquire raw data streams reflecting the loop resistance status of the node. The acquired data stream is a continuous, time-varying physical quantity signal, which will subsequently be used to calculate or evaluate the loop resistance. Real-time acquisition means that the sensors continuously acquire data at a predetermined frequency to promptly capture any changes in loop resistance, including slow degradation or sudden anomalies. Specifically, loop resistance problems in high-voltage electrical equipment typically occur at connection points along the current flow path, such as the moving and stationary contacts of circuit breakers, the blades and fingers of disconnecting switches, and connection joints between busbars. These are critical nodes subjected to high currents and prone to overheating and degradation. When installing online measurement sensors at these locations, the optimal installation position needs to be carefully selected based on the specific high-voltage environment and equipment structure. Since direct contact measurement poses safety hazards and may affect the normal operation of equipment under high-voltage energized conditions, this application employs sensors based on non-contact or low-impact measurement principles. For example, the sensors can be based on magnetic field effects, such as indirectly assessing resistance changes by measuring changes in the locally enhanced magnetic field generated near a high-impedance connection point; or on temperature effects, such as using infrared sensors or thermocouple arrays to non-contactly measure the surface temperature of the connection point, where high temperatures are often a direct manifestation of increased Joule heating due to high loop resistance; or on acoustic physical effects, such as monitoring specific acoustic characteristics generated at the connection point during current flow or switching processes using ultrasonic or audio sensors, such as vibrations caused by micro-discharges or poor contact, where these acoustic signals may be related to contact status and resistance values. These sensors do not directly measure resistance values ​​but rather measure other physical quantities related to resistance changes, achieving indirect monitoring of the circuit resistance status of key nodes through subsequent data processing and model calculations.

[0068] Meanwhile, the sampling frequency and acquisition accuracy of the loop resistance data stream acquired in this application embodiment are set according to the type, voltage level, and maintenance strategy of the high-voltage electrical equipment. Since the dynamic characteristics of loop resistance, its impact on equipment operating status, and the purpose of monitoring vary depending on the type, voltage level, and desired maintenance strategy of the high-voltage electrical equipment, the sampling frequency and acquisition accuracy of the loop resistance data stream need to be specifically set based on these factors. For example, for critical circuit breakers with extremely high requirements for operating speed and reliability, a higher sampling frequency may be needed to capture instantaneous changes in contact resistance during the opening and closing process; for important bus joints, there may be more focus on slow temperature rises or magnetic field changes over long periods, and the sampling frequency can be relatively low, but higher acquisition accuracy is required to distinguish minute signs of degradation. A high sampling frequency helps capture finer signal changes and transient events, while high accuracy ensures the reliability of measurement results and the accuracy of trend analysis. These parameter settings aim to balance data volume, processing load, and monitoring effectiveness, ensuring effective identification of potential equipment failure risks.

[0069] In some embodiments, the step of performing feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results includes the following steps:

[0070] The loop resistance data stream is subjected to integrity and validity verification processing to obtain verification data;

[0071] The verification data is subjected to loop resistance change characteristic analysis to obtain change characteristic parameters;

[0072] The change pattern analysis is performed on the change feature parameters based on the pre-trained time series analysis model to obtain the analysis results.

[0073] In this embodiment, after acquiring the loop resistance data stream, it can be wirelessly transmitted to a remote monitoring and analysis system for analysis. During the analysis, the system performs integrity and validity checks on the loop resistance data stream to obtain verification data. Wirelessly transmitted data is typically organized into data packets. Each data packet contains at least two main parts: a data payload, i.e., the raw measurement data actually acquired by the sensor; and information for data integrity verification, such as a cyclic redundancy check (CRC), checksum, or data packet sequence number. Upon receiving each data packet, the remote monitoring and analysis system first performs data integrity checks on this additional information, such as recalculating the CRC and comparing it with the received CRC. If they match, the data packet is considered undamaged during transmission. For data payloads that pass the integrity check, the system further performs a data validity check to determine if the data value is reasonable. For example, if the sensor measures temperature, it checks whether the temperature value is within the sensor's operating range or the reasonable temperature range for device operation. If an extreme value outside this range is received, it may be considered invalid data. Simultaneously, the system also performs necessary unit conversions or formatting on valid data. Finally, these qualified data payloads, which have undergone integrity and validity checks, are stored in the data buffer of the remote monitoring and analysis system along with the timestamps generated by the sensors during their original acquisition or by the system when it received the data packets. The original acquisition timestamps are used first to preserve the original time information of the data; if none are available, the receiving timestamps are used. The data buffer is used for temporary data storage for subsequent time-series analysis and processing.

[0074] In some embodiments, before performing change pattern analysis on the change feature parameters according to the pre-trained time series analysis model, the method further includes pre-training the time series analysis model, specifically including the following steps:

[0075] Retrieve the historical data sequence of loop resistance from the data buffer for a preset window;

[0076] The historical data sequence of the loop resistance is preprocessed to obtain preprocessed data;

[0077] The preprocessed data is subjected to time series forecasting processing using the exponential smoothing method to obtain the forecasted data.

[0078] Fault mode data is constructed based on historical fault data;

[0079] The fault mode data and the prediction data are determined as the training dataset, and the training dataset is input into the time series analysis model to output the classification result;

[0080] The classification results are used to calculate the function loss based on the labels of the fault mode data, and the parameters of the time series analysis model are adjusted based on the loss value.

[0081] R smooth (t)=αR(t)+(1-α)R smooth (t-Δt)

[0082] In this embodiment, a historical data sequence of loop resistance with a preset time window length is obtained from the data buffer. The historical data sequence is preprocessed, including data cleaning, smoothing, or noise reduction. Then, the smoothed loop resistance value is calculated using the exponential smoothing method. The formula for the exponential smoothing method is as follows:

[0083] Where R(t) represents the current original value, R smooth (t-Δt) represents the smoothed value at the previous moment, Δt is the sampling interval, and α represents the smoothing coefficient set according to monitoring requirements, satisfying 0<α≤1. To analyze the trend and pattern of loop resistance, this embodiment extracts a historical data sequence with a preset time window from the data buffer. For example, this time window may be one hour, one day, one week, or longer, depending on the rate of change of interest. This historical data sequence undergoes further preprocessing to remove residual noise or uneven fluctuations, better revealing its underlying trend. Then, fault mode data is constructed based on historical fault data. This fault mode data is used to train and optimize the intelligent analysis algorithm module, which constitutes a multi-dimensional, high-fidelity historical dataset. Specifically, it can include feature sequences characterizing the dynamic evolution of loop resistance under different known fault modes of high-voltage electrical equipment. For example, but not limited to, time series data showing a quasi-linear or non-linear continuous slow increase in loop resistance value caused by progressive oxidation or corrosion of contact surfaces or slow decay of clamping force of connecting parts; or, time series data showing a sharp step increase, narrow pulse spike, or significant abnormal fluctuation in loop resistance value caused by sudden loosening of connecting bolts, severe arc erosion of contacts, or instantaneous intrusion of foreign objects into the critical conductive path; and, feature data showing intermittent and irregular jumps in loop resistance value between normal and abnormal states due to unstable contact conditions.

[0084] To enhance the accuracy and robustness of fault diagnosis, fault mode data can also integrate other physical sensing parameters that are synchronous with or closely related to changes in loop resistance. These parameters may include: temperature measurements or temperature rise trends at critical fault nodes (such as contacts and connections) during periods of abnormal loop resistance, to characterize the intrinsic relationship between heating and resistance degradation; real-time or historical fluctuation data of the load current flowing through the loop, to analyze the dependence of abnormal resistance on current magnitude or variation; and, under suitable monitoring configurations, specific vibration signal spectrum or amplitude data generated by loosening of the equipment's mechanical structure or partial discharge activity, as well as acoustic signature data of abnormal discharge captured by acoustic sensors. Simultaneously, environmental parameters at the time of fault occurrence, such as ambient temperature and humidity, can also be incorporated into the dataset as auxiliary discriminative information.

[0085] The time-series analysis model in this application employs a Long Short-Term Memory (LSTM) network. This network is trained and optimized based on pre-collected and processed historical operating data, fault mode data, and related training datasets of high-voltage electrical equipment. This LSTM network is specifically designed for processing time-series data. Its input is a feature sequence extracted from the loop resistance data stream, such as a smoothed loop resistance value sequence and its rate of change within a time window. The LSTM network learns and captures the time dependencies and latent patterns in the input feature sequence through its internal gating mechanisms, including input gates, forget gates, and output gates, as well as memory units. After processing by the LSTM layers, a final fully connected layer outputs a probability distribution vector through a Softmax activation function. This vector assigns a probability value to each predefined loop resistance change pattern. Therefore, the current change pattern of the loop resistance is ultimately determined by identifying the specific change pattern description corresponding to the highest probability value in the output probability vector, thereby transforming the numerical output of the LSTM model into a classified equipment operating state or degradation mode. Furthermore, the classification results are used to calculate the loss function based on the labels of the fault mode data. The loss function can be the cross-entropy loss function or the mean squared error loss function, etc. The parameters of the time series analysis model are adjusted according to the calculated loss value, thereby training the model.

[0086] After training the time-series analysis model, this embodiment of the application performs change pattern analysis on the changing characteristic parameters using the time-series analysis model. This embodiment of the application extracts one or more parameters reflecting the characteristics of loop resistance changes from the processed data. These characteristic parameters include at least the average value and trend slope within the current window. By inputting the extracted characteristic parameters into the time-series analysis model, the time-series analysis model is trained and optimized based on historical operating data of high-voltage electrical equipment, typical fault mode data, and training datasets. Based on the output of the intelligent analysis algorithm model, the current change pattern of the loop resistance is determined. This change pattern includes small normal fluctuations, continuous cumulative changes, accelerated deterioration, or abnormal sudden changes.

[0087] In some embodiments, the step of performing fault prediction processing on the analysis results based on a preset alarm threshold to obtain early warning information includes the following steps:

[0088] Based on the preset alarm threshold, the loop resistance value in the analysis result is analyzed to obtain the current loop status;

[0089] The current circuit state is input into the fault prediction model for prediction processing to obtain the remaining lifetime;

[0090] The warning information is obtained by performing rule matching processing on the preset alarm threshold, the current circuit state, and the remaining lifetime according to the alarm rule base.

[0091] In this embodiment, based on the analysis results and extracted feature parameters, a judgment can be made by comparing with the preset multi-level alarm thresholds for loop resistance. If an accelerated degradation trend is identified or the loop resistance value continues to approach the danger threshold, the fault prediction model is invoked. Based on the current state and historical data, the fault prediction model predicts the time required for the loop resistance to reach the preset danger threshold, i.e., the remaining lifetime. Based on the current loop resistance state, whether the alarm threshold is exceeded, and the predicted remaining lifetime, combined with the preset configurable alarm rule base, the warning level and warning content to be issued are determined. According to the determined warning level and content, warning messages or interface display information are generated and pushed through remote monitoring interfaces, SMS, email, or other set communication interfaces.

[0092] In one feasible embodiment, when the analysis results indicate that the loop resistance is showing an accelerated degradation trend or its value is continuously approaching a preset danger threshold, the system triggers the invocation of the fault prediction model. Specifically, this fault prediction model may employ a sequence-to-single-value regression prediction architecture based on a Long Short-Term Memory (LSTM) network. This model is trained with a large amount of historical data encompassing the entire process of equipment operation from normal operation to reaching the danger threshold or experiencing a failure. This LSTM model uses an instantaneous parameter representing the "current state" and a recent loop resistance time series reflecting the degradation process as its joint input. Through its complex internal network structure and patterns learned from numerous historical degradation cases, the LSTM model can comprehensively analyze this input information and predict the time required for the loop resistance to develop from its current value to the preset "danger threshold" under the current degradation trend, i.e., outputting an estimated remaining lifetime. Subsequently, the system determines the final warning level and specific warning content to be issued based on the actual value of the current loop resistance, whether this value has exceeded one or more preset alarm thresholds, and the estimated remaining lifetime output by the fault prediction model, combined with a preset configurable alarm rule base.

[0093] In some embodiments, the step of performing rule matching processing on the preset alarm threshold, the current circuit state, and the remaining lifetime according to the alarm rule base to obtain the warning information includes the following steps:

[0094] The alarm level is obtained by matching the current circuit state and the remaining lifetime according to the preset alarm threshold.

[0095] The alarm content is generated by processing the alarm level according to the alarm rule base.

[0096] The warning information is determined based on the alarm level and the alarm content.

[0097] In this embodiment, the alarm rule base allows users or maintenance personnel to flexibly configure combinations of conditions to trigger different levels of alarms based on experience and equipment importance. For example, a Level 1 alarm can be issued when the loop resistance value exceeds the Level 1 warning threshold but the predicted remaining lifespan is still long; a Level 3 critical alarm is issued if the loop resistance value exceeds the Level 2 alarm threshold and the predicted remaining lifespan is less than a preset number of days; and a Level 4 danger alarm is immediately triggered when the loop resistance value directly exceeds the danger threshold or an unpredictable abnormal change occurs. Finally, the system generates standardized warning messages or prominent visual alarm information on the remote monitoring interface according to the determined warning levels and content, and pushes them to relevant personnel through various communication interfaces to ensure that potential risks are responded to and handled promptly. The preset multi-level alarm thresholds and alarm rules for loop resistance are set or dynamically adjusted based on the type of high-voltage electrical equipment, rated parameters, operating environment, historical operating data, and maintenance experience. The safety thresholds for loop resistance and the corresponding alarm rules are not universal standards but need to be customized according to the specific conditions of the high-voltage electrical equipment. Specifically, the setting of thresholds and rules takes into account the type of equipment, rated parameters, actual operating environment, and long-term historical operating data and maintenance experience. For example, a device with a lower rated current may have a lower dangerous resistance threshold than a device with a higher rated current. The normal fluctuation range and typical degradation curves shown in long-term operating history data can help set more precise thresholds. Furthermore, these thresholds and rules can be dynamically adjusted; for example, based on new data collected during equipment operation or feedback from maintenance personnel, the thresholds or rules can be fine-tuned to better reflect the actual degradation of the equipment, improving the accuracy and effectiveness of early warnings. The fault prediction model in this application is constructed based on the degradation mechanism model of high-voltage electrical equipment or historical degradation data. The calculation of remaining life is related to the current circuit resistance state, the identified changing trend, and the dangerous threshold.

[0098] The solutions of this application embodiment will be described in detail and explained below with reference to specific application examples:

[0099] This application embodiment can be applied to the detection of high-voltage electrical equipment. To achieve uninterrupted online monitoring of the loop resistance at critical connection points of high-voltage electrical equipment, this application embodiment first requires the installation of dedicated online loop resistance measurement sensors at these predetermined critical nodes. These sensors are designed to operate safely and reliably in high-voltage, high-current environments and are capable of continuously acquiring raw data streams reflecting the loop resistance state of the node. The acquired data stream is a continuous, time-varying physical quantity signal, which will subsequently be used to estimate or evaluate the loop resistance. Real-time acquisition means that the sensors continuously acquire data at a predetermined frequency to promptly capture any changes in the loop resistance, including slow degradation or sudden anomalies. Then, the real-time acquired loop resistance data stream of the critical nodes is synchronously and stably sent to a remote monitoring and analysis system. The remote monitoring and analysis system has data reception, buffering, and preliminary verification functions to ensure the integrity and reliability of data transmission. Considering that high-voltage electrical equipment is usually installed in outdoor environments and involves high-voltage safety isolation, using wired methods to transmit sensor data faces challenges such as complex wiring, high costs, and insulation safety. Therefore, embodiments of this invention employ wireless data transmission technologies, such as Wi-Fi, Zigbee, LoRa, and 4G / 5G, to synchronously and stably transmit loop resistance data streams collected by sensors distributed at different key nodes to a remote monitoring and analysis system located in a secure area. The wireless transmission module is typically integrated into the sensor unit or a nearby aggregation unit, responsible for data encapsulation and transmission. The remote monitoring and analysis system has a dedicated data receiving interface capable of receiving data packets from various sensors. The received data is first temporarily stored in a buffer to handle network fluctuations or system overload. Simultaneously, the system performs preliminary verification on the received data, such as checking the sequence number, length, and timestamp of the data packets, to ensure the integrity and reliability of the data during transmission. Embodiments of this application perform time-series analysis and feature extraction on the pre-verified loop resistance data stream, and based on the analysis results, dynamically identify the loop resistance variation patterns, degradation trends, and abnormal signals over time. This module retrieves the pre-verified loop resistance data stream from the data buffer and performs in-depth time-series analysis on it. The purpose of time-series analysis is to understand the patterns of data change over time. This includes, but is not limited to, trend analysis, periodic analysis, and volatility analysis. Based on time-series analysis, the module extracts key features reflecting the state and changes in loop resistance from the data stream. These features may be statistics, rates of change, frequency domain characteristics, or parameters extracted based on a specific model. Based on these extracted features, the intelligent analysis algorithm can dynamically identify the current change pattern of the loop resistance, determine whether there is a deterioration trend, and detect whether there are abnormal signals.Based on the identified change patterns, deterioration trends, and abnormal signals, combined with preset alarm thresholds and fault prediction models, differentiated early warning information for potential fault risks of the high-voltage electrical equipment is generated and released, and displayed through a remote monitoring interface or communication interface.

[0100] Please see Figure 2 This application also provides an electrical equipment fault prediction system, which can implement the above-mentioned electrical equipment fault prediction method. The system includes:

[0101] The first module 201 is used to collect and process data from key nodes of electrical equipment to obtain loop resistance data stream.

[0102] The second module 202 is used to perform feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results.

[0103] The third module 203 is used to perform fault prediction processing on the analysis results according to a preset alarm threshold to obtain early warning information;

[0104] The fourth module 204 is used to display the warning information through a remote monitoring interface.

[0105] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0106] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned method for predicting electrical equipment faults. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0107] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0108] Please see Figure 3 , Figure 3 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0109] The processor 301 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0110] The memory 302 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 302 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 302 and called and executed by the processor 301 to implement an electrical equipment fault prediction method according to an embodiment of this application.

[0111] Input / output interface 303 is used to implement information input and output;

[0112] The communication interface 304 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0113] Bus 305 transmits information between various components of the device (e.g., processor 301, memory 302, input / output interface 303, and communication interface 304);

[0114] The processor 301, memory 302, input / output interface 303, and communication interface 304 are connected to each other within the device via bus 305.

[0115] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for predicting electrical equipment faults.

[0116] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0117] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0118] This application provides a method, system, electronic device, and storage medium for predicting electrical equipment faults. The solution involves acquiring and processing data from key nodes of the electrical equipment to obtain a loop resistance data stream. Feature extraction and time-series analysis are then performed on the loop resistance data stream to obtain analysis results. Based on a preset alarm threshold, fault prediction processing is applied to the analysis results to generate early warning information. This warning information is then displayed via a remote monitoring interface. This application enables online non-contact monitoring of the loop resistance of high-voltage electrical equipment. By continuously acquiring data, it dynamically identifies minor degradations, provides early warnings, and guides optimized maintenance strategies by predicting fault conditions, thereby improving equipment safety.

[0119] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0120] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0121] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0123] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0124] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0125] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of the units described above 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 systems or units may be electrical, mechanical, or other forms.

[0126] The units described above 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.

[0127] Furthermore, the functional units in the various embodiments of this application 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.

[0128] 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, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0129] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for predicting faults in electrical equipment, characterized in that, The method includes the following steps: Data acquisition and processing are performed on key nodes of electrical equipment to obtain loop resistance data stream; Feature extraction and timing analysis are performed on the loop resistance data stream to obtain the analysis results; Based on a preset alarm threshold, the analysis results are processed for fault prediction to obtain early warning information; The warning information is displayed via a remote monitoring interface.

2. The method according to claim 1, characterized in that, The process of acquiring and processing data from key nodes of electrical equipment to obtain a loop resistance data stream includes the following steps: Based on the high-voltage environment and equipment structure, loop resistance measurement sensors are installed at key nodes of the electrical equipment. The sampling frequency and acquisition accuracy are set according to the type, voltage level, and maintenance strategy of the electrical equipment. The loop resistance measurement sensor performs online measurement and processing of the loop resistance of the key node according to the sampling frequency and the acquisition accuracy to obtain the loop resistance data stream.

3. The method according to claim 1, characterized in that, The process of feature extraction and time-series analysis of the loop resistance data stream to obtain analysis results includes the following steps: The loop resistance data stream is subjected to integrity and validity verification processing to obtain verification data; The verification data is subjected to loop resistance change characteristic analysis to obtain change characteristic parameters; The change pattern analysis is performed on the change feature parameters based on the pre-trained time series analysis model to obtain the analysis results.

4. The method according to claim 3, characterized in that, The process of performing integrity and validity verification on the loop resistance data stream to obtain verification data includes the following steps: Perform data packet integrity verification on the loop resistance data stream to obtain a complete data packet; The complete data packet is subjected to data payload validity verification processing according to the sensor's operating range to obtain the verification data. The verification data is stored in the data cache area based on the timestamp.

5. The method according to claim 3, characterized in that, Before performing change pattern analysis on the change feature parameters based on the pre-trained time series analysis model, the method further includes pre-training the time series analysis model, specifically including the following steps: Retrieve the historical data sequence of loop resistance from the data buffer for a preset window; The historical data sequence of the loop resistance is preprocessed to obtain preprocessed data; The preprocessed data is subjected to time series forecasting processing using the exponential smoothing method to obtain the forecasted data. Fault mode data is constructed based on historical fault data; The fault mode data and the prediction data are determined as the training dataset, and the training dataset is input into the time series analysis model to output the classification result; The classification results are used to calculate the function loss based on the labels of the fault mode data, and the parameters of the time series analysis model are adjusted based on the loss value.

6. The method according to claim 1, characterized in that, The step of performing fault prediction processing on the analysis results based on a preset alarm threshold to obtain early warning information includes the following steps: Based on the preset alarm threshold, the loop resistance value in the analysis result is analyzed to obtain the current loop status; The current circuit state is input into the fault prediction model for prediction processing to obtain the remaining lifetime; The warning information is obtained by performing rule matching processing on the preset alarm threshold, the current circuit state, and the remaining lifespan according to the alarm rule base.

7. The method according to claim 6, characterized in that, The step of performing rule matching processing on the preset alarm threshold, the current circuit state, and the remaining lifetime according to the alarm rule base to obtain the warning information includes the following steps: The alarm level is obtained by matching the current circuit state and the remaining lifetime according to the preset alarm threshold. The alarm content is generated by processing the alarm level according to the alarm rule base. The warning information is determined based on the alarm level and the alarm content.

8. An electrical equipment fault prediction system, characterized in that, The system includes: The first module is used to collect and process data from key nodes of electrical equipment to obtain loop resistance data stream. The second module is used to perform feature extraction and time-series analysis on the loop resistance data stream to obtain analysis results. The third module is used to perform fault prediction processing on the analysis results based on a preset alarm threshold to obtain early warning information. The fourth module is used to display the warning information through a remote monitoring interface.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images