Power equipment state early warning method and device based on big data and computer equipment

Abstract

The invention relates to a power equipment state early warning method and device based on big data and computer equipment. The method comprises the following steps: acquiring a multi-source real-time operation data set and an environment working condition real-time data set of power equipment, and determining equipment key state parameter data and equipment operation stress parameter data; performing dynamic stress and life coupling evaluation on the key state parameter data of the equipment to obtain dynamic stress and life coupling relation data of the equipment; performing equipment state degradation acceleration effect analysis on the environment working condition real-time data set to obtain degradation-caused acceleration effect data of environment stress; and according to the degradation acceleration effect data of the environmental stress, the dynamic stress of the equipment and the service life coupling relation data, performing adaptive adjustment on a dynamic early warning threshold value of the key state parameter data of the equipment, generating a dynamic early warning logic strategy of the power equipment, and executing state early warning of the power equipment. By adopting the method, the early warning efficiency of the state of the power equipment can be improved.

Description

Technical Field

[0001] This application relates to the field of power equipment monitoring technology, and in particular to a power equipment status early warning method, device, computer equipment, computer-readable storage medium and computer program product based on big data. Background Technology

[0002] With the deepening of smart grid construction, the reliable operation of power equipment has become crucial to ensuring power supply security. Against this backdrop, big data-based power equipment status early warning technology has emerged and is gradually becoming a core tool for operation and maintenance management. Current technologies generally rely on various sensors installed on the equipment to continuously collect multi-source status variables such as oil chromatography data, partial discharge signals, temperature, and load current, thereby constructing a vast historical operational database. By employing algorithms such as threshold comparison, trend analysis, and machine learning, the aim is to identify abnormal patterns deviating from normal ranges from the data and issue early warning signals before equipment performance deteriorates to the point of failure. This approach signifies a significant shift in operation and maintenance strategies from reactive maintenance to predictive maintenance, improving the intelligence level of the power grid to a certain extent.

[0003] In related technologies, most power equipment condition early warning systems rely on fixed thresholds or static models trained from historical data. These models implicitly assume that the equipment operates under a relatively stable average stress environment. However, in reality, stress factors such as load, start-stop frequency, and ambient temperature of power equipment fluctuate continuously and drastically. A piece of equipment deemed healthy under light load conditions will experience an exponential acceleration in insulation aging and mechanical fatigue accumulation when subjected to a short-term emergency overload. Static early warning models cannot perceive the instantaneous impact of current operating stress on equipment lifespan, nor can they dynamically adjust the sensitivity and lead time of early warnings accordingly, thus reducing the efficiency of power equipment condition early warning and requiring improvement.

[0004] Therefore, there is an urgent need for a method, device, computer equipment, computer-readable storage medium, and computer program product for early warning of power equipment status based on big data, which can improve the efficiency of early warning of power equipment status. Summary of the Invention

[0005] Therefore, it is necessary to provide a big data-based method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the efficiency of early warning of power equipment status, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a method for early warning of power equipment status based on big data, including:

[0007] Acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets;

[0008] Based on the equipment operating stress parameter data, a dynamic stress and life coupling evaluation is performed on the key state parameter data of the equipment to obtain the dynamic stress and life coupling relationship data of the equipment.

[0009] Based on the coupling relationship data between the dynamic stress and lifespan of the equipment, the degradation acceleration effect analysis of the equipment condition is performed on the real-time environmental condition dataset to obtain the degradation acceleration effect data caused by environmental stress.

[0010] Based on the degradation acceleration effect data of the environmental stress and the coupling relationship data between the dynamic stress and lifespan of the equipment, the dynamic early warning threshold of the key state parameters of the equipment is adaptively adjusted, and a dynamic early warning logic strategy for the power equipment is generated.

[0011] Based on the dynamic early warning logic strategy of the power equipment, execute the power equipment status early warning.

[0012] In one embodiment, determining the key equipment state parameter data and equipment operating stress parameter data from the multi-source real-time operating dataset and the real-time environmental condition dataset includes:

[0013] Based on the multi-source real-time operation dataset and the environmental condition real-time dataset, data quality verification and abnormal data point cleaning are performed to obtain the equipment operation data sequence;

[0014] Key state parameters and operating stress parameters are extracted from the equipment operation data sequence to obtain key state parameter data and operating stress parameter data, respectively.

[0015] In one embodiment, the method further includes:

[0016] Acquire historical full lifecycle degradation data of power equipment;

[0017] Based on the equipment operating stress parameter data, a dynamic stress and lifespan coupling assessment is performed on the equipment key state parameter data and the historical full lifespan degradation data to obtain equipment dynamic stress and lifespan coupling relationship data.

[0018] Based on the dynamic stress and lifespan coupling data of the equipment, a quantitative analysis of the impact of environmental stress on the aging rate of the equipment's insulation materials and the fatigue strength of the mechanical structure is performed on the real-time environmental operating data to obtain data on the accelerated degradation effect caused by environmental stress.

[0019] Based on the environmental stress-induced accelerated degradation effect data, the remaining reliable lifespan of the equipment under the current operating stress is predicted using the equipment's key state parameter data and the historical full life cycle degradation data, thus obtaining the equipment's remaining reliable lifespan data under dynamic stress.

[0020] In one embodiment, the step of performing dynamic stress-life coupling assessment on the key state parameter data of the equipment to obtain dynamic stress-life coupling relationship data of the equipment includes:

[0021] The stress parameter time series decomposition was performed on the stress parameter data of the equipment operation to extract the transient peak value, root mean square value and cumulative effect of the stress parameter, and obtain multi-dimensional time series characteristic data of stress.

[0022] Based on the stress multi-dimensional time-series characteristic data, the response delay and hysteresis effect of the key state parameters of the equipment under the corresponding stress are modeled to obtain the stress response delay model of the state parameters.

[0023] Based on the state parameter stress response delay model, the equipment state degradation rate curves under different stress levels are fitted to the historical full life cycle degradation data of the power equipment to obtain a cluster of state degradation rate curves under multiple stress levels.

[0024] Based on the set of state degradation rate curves under the multi-stress levels, the equivalent aging acceleration under the current comprehensive stress is calculated on the key state parameter data of the equipment to obtain the current equivalent aging acceleration data.

[0025] Based on the set of degradation rate curves under the multi-stress levels and the current equivalent aging acceleration data, a dynamic stress and lifespan coupling assessment is performed to obtain the dynamic stress and lifespan coupling relationship data of the equipment.

[0026] In one embodiment, the step of predicting the remaining reliable lifespan of the equipment under current operating stress by analyzing the equipment's key state parameter data and historical full lifecycle degradation data to obtain the equipment's remaining reliable lifespan data under dynamic stress includes:

[0027] Based on the environmental stress-induced degradation acceleration effect data, the current health index of the equipment's insulation and mechanical performance is calculated from the key state parameter data of the equipment to obtain the current comprehensive health index data of the equipment.

[0028] Based on the current comprehensive health index data of the equipment, Monte Carlo simulation of the degradation trajectory of the health index under the action of future stress spectrum is performed on the historical full life cycle degradation data to obtain the equipment health status degradation trajectory simulation dataset.

[0029] Based on the simulation dataset of the equipment health status degradation trajectory, the probability distribution of the time point when the equipment health status first touches the preset warning boundary is calculated to obtain the probability distribution data of the equipment warning time point.

[0030] The earliest and latest warning times under different confidence levels are extracted from the probability distribution data of the equipment warning time points to obtain the confidence interval data of the equipment's remaining reliable lifespan.

[0031] Based on the probability distribution data of the equipment warning time points and the confidence interval data of the equipment's remaining reliable lifespan, the remaining reliable lifespan interval of the equipment under the current operating stress is predicted to obtain the remaining reliable lifespan interval data of the equipment under dynamic stress.

[0032] In one embodiment, the step of calculating the probability distribution of the time point when the device health status first touches the preset warning boundary based on the device health status degradation trajectory simulation dataset, to obtain the device warning time point probability distribution data, includes:

[0033] Based on the simulation dataset of the device health status degradation trajectory, the intersection point detection between each simulation trajectory and the preset multi-level warning threshold boundary is performed to obtain the multi-level warning threshold trigger time point sequence for each simulation trajectory.

[0034] The time sequence of the multi-level warning thresholds for each simulated trajectory is statistically analyzed, and the average time, time standard deviation, and quantile of the time distribution for each level of warning threshold are calculated.

[0035] Based on the average time, time standard deviation, and quantiles of the time distribution for each level of warning threshold, a curve is constructed showing the relationship between device status warning time and warning probability with time on the horizontal axis and cumulative touch probability on the vertical axis.

[0036] Based on the relationship curve, the earliest and latest possible times when the device status reaches the warning threshold at each level under the preset confidence level are extracted to form the probability distribution data of device warning time points.

[0037] Secondly, this application also provides a power equipment status early warning device based on big data, comprising:

[0038] The acquisition module is used to acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and to determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets.

[0039] The evaluation module is used to perform dynamic stress and life coupling evaluation on the key state parameter data of the equipment based on the equipment operating stress parameter data, and obtain the dynamic stress and life coupling relationship data of the equipment.

[0040] The analysis module is used to perform equipment condition degradation acceleration effect analysis on the real-time environmental condition dataset based on the dynamic stress and life coupling relationship data of the equipment, and obtain degradation acceleration effect data of environmental stress.

[0041] The strategy generation module is used to adaptively adjust the dynamic early warning threshold of the key state parameter data of the equipment based on the degradation acceleration effect data of the environmental stress and the coupling relationship data of the equipment dynamic stress and life, and generate a dynamic early warning logic strategy for the power equipment.

[0042] The power equipment status early warning module is used to execute power equipment status early warnings according to the dynamic early warning logic strategy of the power equipment.

[0043] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0044] Acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets;

[0045] Based on the equipment operating stress parameter data, a dynamic stress and life coupling evaluation is performed on the key state parameter data of the equipment to obtain the dynamic stress and life coupling relationship data of the equipment.

[0046] Based on the coupling relationship data between the dynamic stress and lifespan of the equipment, the degradation acceleration effect analysis of the equipment condition is performed on the real-time environmental condition dataset to obtain the degradation acceleration effect data caused by environmental stress.

[0047] Based on the degradation acceleration effect data of the environmental stress and the coupling relationship data between the dynamic stress and lifespan of the equipment, the dynamic early warning threshold of the key state parameters of the equipment is adaptively adjusted, and a dynamic early warning logic strategy for the power equipment is generated.

[0048] Based on the dynamic early warning logic strategy of the power equipment, execute the power equipment status early warning.

[0049] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0050] Acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets;

[0051] Based on the equipment operating stress parameter data, a dynamic stress and life coupling evaluation is performed on the key state parameter data of the equipment to obtain the dynamic stress and life coupling relationship data of the equipment.

[0052] Based on the coupling relationship data between the dynamic stress and lifespan of the equipment, the degradation acceleration effect analysis of the equipment condition is performed on the real-time environmental condition dataset to obtain the degradation acceleration effect data caused by environmental stress.

[0053] Based on the degradation acceleration effect data of the environmental stress and the coupling relationship data between the dynamic stress and lifespan of the equipment, the dynamic early warning threshold of the key state parameters of the equipment is adaptively adjusted, and a dynamic early warning logic strategy for the power equipment is generated.

[0054] Based on the dynamic early warning logic strategy of the power equipment, execute the power equipment status early warning.

[0055] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0056] Acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets;

[0057] Based on the equipment operating stress parameter data, a dynamic stress and life coupling evaluation is performed on the key state parameter data of the equipment to obtain the dynamic stress and life coupling relationship data of the equipment.

[0058] Based on the coupling relationship data between the dynamic stress and lifespan of the equipment, the degradation acceleration effect analysis of the equipment condition is performed on the real-time environmental condition dataset to obtain the degradation acceleration effect data caused by environmental stress.

[0059] Based on the degradation acceleration effect data of the environmental stress and the coupling relationship data between the dynamic stress and lifespan of the equipment, the dynamic early warning threshold of the key state parameters of the equipment is adaptively adjusted, and a dynamic early warning logic strategy for the power equipment is generated.

[0060] Based on the dynamic early warning logic strategy of the power equipment, execute the power equipment status early warning.

[0061] The aforementioned power equipment status early warning methods, devices, computer equipment, computer-readable storage media, and computer program products based on big data achieve accurate perception of equipment health status and proactive risk early warning through dynamic stress and lifespan coupled assessment and adaptive threshold adjustment mechanisms. They also integrate multi-source operating data and environmental condition information in real time, deeply analyzing the equipment's status degradation trajectory and remaining reliable lifespan under current and predictable stress spectra, and dynamically adjusting early warning thresholds and strategies accordingly. This effectively overcomes the insufficient adaptability of fixed thresholds under varying operating conditions, thereby significantly improving the accuracy and timeliness of early warnings. Furthermore, it transforms operation and maintenance decisions from passive response to proactive intervention, providing core technical support for the full lifecycle management of equipment and effectively improving the efficiency of power equipment status early warning. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is an application environment diagram of a power equipment status early warning method based on big data in one embodiment;

[0064] Figure 2 This is a flowchart illustrating a power equipment status early warning method based on big data in one embodiment;

[0065] Figure 3 This is a flowchart illustrating a power equipment status early warning method based on big data in another embodiment;

[0066] Figure 4 This is a structural block diagram of a power equipment status early warning device based on big data in one embodiment;

[0067] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0068] 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 and not intended to limit the scope of this application.

[0069] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0070] The power equipment status early warning method based on big data provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server.

[0071] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0072] In one exemplary embodiment, such as Figure 2 As shown, a method for early warning of power equipment status based on big data is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S202 to S210. Wherein:

[0073] Step S202: Obtain the multi-source real-time operation dataset and the real-time environmental condition dataset of the power equipment, and determine the key state parameter data and the operating stress parameter data of the equipment from the multi-source real-time operation dataset and the real-time environmental condition dataset.

[0074] Specifically, a comprehensive collection of real-time operating data and environmental condition data for power equipment is conducted. The data is collected from multiple sensors, including but not limited to transformer oil chromatography sensors, equipment partial discharge ultra-high frequency sensors, equipment body temperature distribution fiber optic sensors, equipment vibration acceleration sensors, environmental temperature and humidity sensors, and load current and voltage sensors. The data collection process must cover various core operating parameters of the equipment during operation and key environmental condition information, thereby forming a multi-source real-time operating dataset for power equipment and a real-time environmental condition dataset. Subsequently, the acquired multi-source real-time operating dataset for power equipment undergoes in-depth processing, focusing on the extraction of key state parameters and operating stress parameters. Data extraction algorithms are used to accurately separate key state parameter data reflecting the core operating state of the equipment, as well as operating stress parameter data reflecting the stress the equipment experiences during operation, from the multi-source real-time operating data, providing fundamental data support for subsequent evaluation and analysis. Key state parameter data includes, but is not limited to, the dissolved gas content ratio in transformer oil, the amplitude and phase of partial discharge, and the hot spot temperature value of the equipment. Operating stress parameter data includes, but is not limited to, the transient value of the equipment load rate, and the frequency and intensity of start-up and shutdown operations.

[0075] Step S204: Based on the equipment operating stress parameter data, perform dynamic stress and life coupling evaluation on the key state parameter data of the equipment to obtain the dynamic stress and life coupling relationship data of the equipment.

[0076] Specifically, using equipment operating stress parameter data as the core basis, dynamic stress and life coupling assessment is carried out on key equipment state parameter data. During the assessment process, it is necessary to establish a dynamic correlation between stress and equipment life. Through the calculation and analysis of the coupling relationship between the two, dynamic stress and life coupling relationship data of the equipment is generated.

[0077] Step S206: Based on the coupling relationship data between equipment dynamic stress and lifespan, analyze the accelerated degradation effect of equipment condition on the real-time environmental condition dataset to obtain data on the accelerated degradation effect of environmental stress.

[0078] Specifically, by combining data on the coupling relationship between dynamic stress and lifespan of equipment, we analyze the accelerated degradation effect of equipment based on real-time environmental operating data, explore the influence mechanism of environmental operating factors on the rate of equipment degradation, quantify the degree to which environmental stress leads to accelerated equipment degradation, and thus obtain data on the accelerated degradation effect caused by environmental stress.

[0079] Step S208: Based on the data on the accelerated degradation effect of environmental stress and the coupling relationship between equipment dynamic stress and lifespan, the dynamic early warning threshold of the key state parameters of the equipment is adaptively adjusted, and a dynamic early warning logic strategy for the power equipment is generated.

[0080] Specifically, the threshold adjustment module then integrates data on the accelerated degradation effect of environmental stress with data on the coupling relationship between equipment dynamic stress and lifespan. It dynamically and adaptively adjusts the warning thresholds corresponding to the key state parameters of the equipment. Through an adaptive algorithm, the warning thresholds are optimized in real time to ensure that the thresholds can dynamically adapt to changes in equipment operating status and environmental conditions, generating dynamic adaptive warning threshold data for the equipment. At the same time, the threshold adjustment module performs a warning strategy logic mapping based on the dynamic adaptive warning threshold data, combining the dynamic thresholds with specific warning logic to clarify the warning triggering conditions and warning level determination rules corresponding to different thresholds, ultimately forming a dynamic warning logic strategy for the power equipment.

[0081] Step S210: Execute power equipment status warning according to the dynamic early warning logic strategy of power equipment.

[0082] Specifically, based on the dynamic early warning logic strategy for power equipment, a dynamic early warning execution engine for power equipment is developed, capable of implementing the early warning logic. This engine needs to have the functions of receiving data in real time, quickly matching early warning strategies, and promptly triggering early warning signals. Subsequently, the designed dynamic early warning execution engine for power equipment is deployed to the power equipment status monitoring center to achieve real-time monitoring and early warning of the power equipment status. When the equipment status reaches the early warning threshold, the engine can quickly execute the early warning operation and promptly transmit the early warning information to relevant personnel.

[0083] The aforementioned big data-based power equipment condition early warning method achieves accurate perception of equipment health status and proactive risk warning through dynamic stress and lifespan coupling assessment and adaptive threshold adjustment mechanism. It also integrates multi-source operating data and environmental condition information in real time to deeply analyze the equipment's condition degradation trajectory and remaining reliable lifespan under current and predictable stress spectrum, and dynamically adjusts the early warning threshold and strategy accordingly. This effectively overcomes the problem of insufficient adaptability of fixed thresholds under varying operating conditions, thereby effectively improving the accuracy and timeliness of early warning and transforming operation and maintenance decisions from passive response to proactive intervention. It provides core technical support for the full life cycle management of equipment, thus effectively improving the efficiency of power equipment condition early warning.

[0084] In one exemplary embodiment, such as Figure 3 As shown, key equipment state parameter data and equipment operating stress parameter data are determined from multi-source real-time operational datasets and real-time environmental condition datasets, including:

[0085] Based on the multi-source real-time operation dataset and the real-time environmental condition dataset, data quality verification and abnormal data point cleaning are performed to obtain the equipment operation data sequence;

[0086] Key state parameters and operating stress parameters are extracted from the equipment operation data sequence to obtain key state parameter data and operating stress parameter data, respectively.

[0087] Specifically, a data quality verification process is initiated for multi-source real-time operational datasets and real-time environmental condition datasets. Multiple verification methods, including data integrity verification, data consistency verification, and data accuracy verification, are employed to identify anomalous data points in the datasets. For example, by comparing the differences between data fluctuation ranges and normal thresholds, and analyzing the rationality of data time-series changes, anomalous data points such as missing data, erroneous data, and redundant data are accurately located. Subsequently, anomaly data cleaning algorithms are used to process the identified anomalous data points. Missing data is supplemented using appropriate interpolation algorithms, while erroneous and redundant data are removed or corrected. Ultimately, a high-quality equipment operation data sequence is obtained, providing a reliable data foundation for subsequent parameter extraction. Finally, parameter extraction was performed on the high-quality equipment operation data sequence. Based on the operating mechanism of power equipment and the needs of fault diagnosis, the extraction range of key state parameters and operating stress parameters was determined. Key state parameters include the ratio of dissolved gas content in transformer oil that reflects the insulation state of the transformer, the amplitude and phase of partial discharge that reflects the equipment discharge fault, and the hot spot temperature that characterizes the overheating risk of the equipment. Operating stress parameters include the transient value of the equipment load rate that reflects the changes in equipment load, and the frequency and intensity of start-stop operations that reflect the intensity of equipment operation. The parameter extraction algorithm was used to extract key state parameter data and operating stress parameter data from the high-quality equipment operation data sequence to ensure that the extracted parameter data can accurately reflect the operating state and stress conditions of the equipment.

[0088] In this embodiment, the introduction of data quality verification and abnormal data point cleaning processes effectively removes abnormal data from the dataset, ensuring the accuracy and reliability of high-quality equipment operation data sequences. This avoids deviations in subsequent parameter extraction and analysis results due to data quality issues, thus improving the accuracy of data processing. Furthermore, the targeted extraction of key state parameters and operating stress parameters can accurately screen parameter data that are of core significance for equipment status assessment and fault early warning, reducing the interference of redundant data on subsequent analysis. At the same time, it ensures that the extracted parameters can directly serve equipment status assessment and early warning work, further improving the accuracy and effectiveness of the early warning system.

[0089] In one exemplary embodiment, such as Figure 3 As shown, the method also includes:

[0090] Step S302: Obtain historical full lifecycle degradation data of power equipment;

[0091] Step S304: Based on the equipment operating stress parameter data, perform dynamic stress and life coupling assessment on the equipment key state parameter data and historical full life cycle degradation data to obtain the equipment dynamic stress and life coupling relationship data.

[0092] Step S306: Based on the coupling relationship data of equipment dynamic stress and life, perform a quantitative analysis of the impact of environmental stress on the aging rate of equipment insulation materials and the fatigue strength of mechanical structure using real-time environmental condition data, and obtain data on the accelerated degradation effect caused by environmental stress.

[0093] Step S308: Based on the environmental stress-induced degradation acceleration effect data, predict the remaining reliable lifespan of the equipment under the current operating stress by analyzing the key state parameter data and historical full life cycle degradation data of the equipment, and obtain the remaining reliable lifespan data of the equipment under dynamic stress.

[0094] Specifically, firstly, a connection is established with a cloud database through a data interface to retrieve historical full-lifecycle degradation data of the power equipment. This degradation data needs to cover the equipment's condition degradation records under different operating stages and stress conditions, including historical changes in key equipment condition parameters, historical records of equipment failures, and historical information on equipment maintenance and repair. Next, a dynamic stress and lifespan coupling assessment is conducted. Using equipment operating stress parameter data as the core input, and combining it with key equipment condition parameter data and historical full-lifecycle degradation data, a dynamic stress and lifespan coupling assessment model is constructed. This model can be obtained by fitting historical data. The model needs to consider the dynamic changes in equipment operating stress and the impact mechanism of stress changes on equipment lifespan. Through quantitative analysis of the relationship between equipment operating stress and equipment condition degradation and lifespan loss, the lifespan loss rate and condition degradation trend of the equipment under the current operating stress are calculated, thus obtaining dynamic stress and lifespan coupling relationship data. This data can accurately reflect the dynamic correlation between equipment lifespan and condition under the current stress conditions.

[0095] Subsequently, an analysis of the accelerated degradation effect caused by environmental stress was conducted. Based on the coupling relationship data of equipment dynamic stress and life, in-depth analysis of real-time environmental operating data was carried out. The focus was on exploring the influence of environmental stress factors on the aging rate of equipment insulation materials and the fatigue strength of mechanical structures, thereby obtaining data on the accelerated degradation effect caused by environmental stress. This data can clearly show the accelerating effect of environmental factors on the equipment degradation process.

[0096] Finally, the remaining reliable lifespan of the equipment is predicted. The assessment and analysis module constructs a prediction model for the remaining reliable lifespan based on the data of accelerated degradation caused by environmental stress, combined with the key state parameter data of the equipment and the historical full life cycle degradation data of the power equipment. The prediction model for the remaining reliable lifespan can be obtained through machine learning technology. By assessing the current state of the equipment and predicting the future degradation trend, the remaining time range in which the equipment can maintain reliable operation under the current operating stress is calculated, thereby obtaining the remaining reliable lifespan data of the equipment under dynamic stress.

[0097] In this embodiment, a dynamic stress-life model is constructed by integrating historical equipment data with design benchmarks, and environmental stress acceleration effect analysis is incorporated to achieve a comprehensive and accurate assessment of the equipment's health status. Its final output is upgraded from traditional single-point life prediction to prediction of the remaining reliable lifespan under dynamic stress, thereby effectively reducing the risk of sudden equipment failures and ensuring stable operation.

[0098] In an exemplary embodiment, dynamic stress and lifespan coupling assessment is performed on key state parameter data of the equipment to obtain dynamic stress and lifespan coupling relationship data, including:

[0099] The stress parameter time series decomposition of the equipment operation stress parameter data is performed to extract the transient peak value, root mean square value and cumulative effect of the stress parameter, so as to obtain multi-dimensional time series characteristic data of stress.

[0100] Based on the multi-dimensional temporal characteristic data of stress, the response delay and hysteresis effect of the key state parameters of the equipment under the corresponding stress are modeled, and the stress response delay model of the state parameters is obtained.

[0101] Based on the state parameter stress response delay model, the equipment state degradation rate curves under different stress levels are fitted to the historical full life cycle degradation data of power equipment to obtain a cluster of state degradation rate curves under multiple stress levels.

[0102] Based on the cluster of state degradation rate curves under multiple stress levels, the equivalent aging acceleration under the current comprehensive stress is calculated from the key state parameter data of the equipment to obtain the current equivalent aging acceleration data.

[0103] Based on the set of degradation rate curves under multiple stress levels and the current equivalent aging acceleration data, a dynamic stress and lifespan coupling assessment is performed to obtain data on the dynamic stress and lifespan coupling relationship of the equipment.

[0104] Specifically, firstly, time series analysis is performed on the equipment operating stress parameter data. A time series decomposition algorithm is used to decompose the equipment operating stress parameter data into different components, including trend terms, periodic terms, and random terms. Through decomposition, the patterns of stress parameter changes over time are explored in depth. Based on the time series decomposition, key characteristic indicators of stress parameters are extracted, including transient peak values ​​that reflect the instantaneous peak values ​​of stress changes, root mean square values ​​that reflect the average level of stress changes, and cumulative effect quantities that reflect the cumulative effect of stress. Through the calculation and organization of the above characteristic indicators, multi-dimensional time series characteristic data of stress are formed.

[0105] Next, a state parameter stress response delay model is constructed. Based on multi-dimensional time-series stress characteristic data and combined with key state parameter data of the equipment, the response law of key state parameters of the equipment under corresponding stress is analyzed. By establishing a mathematical model, the above response delay and hysteresis effect are quantitatively described. The time delay of the state parameter to start responding after the stress change occurs, the time period for the response to reach a steady state, and the degree of influence of the hysteresis effect are clarified, thus obtaining the state parameter stress response delay model.

[0106] Subsequently, condition degradation rate curve fitting under multiple stress levels was performed. Based on the state parameter stress response delay model and combined with the historical full life cycle degradation data of power equipment, equipment condition degradation records corresponding to different stress levels in the historical data were selected. For each stress level, historical degradation data of key equipment state parameters were extracted, and curve fitting algorithms were used to fit the condition degradation data under different stress levels to obtain the equipment condition degradation rate curve corresponding to each stress level. By sorting and classifying the condition degradation rate curves under multiple stress levels, a cluster of condition degradation rate curves under multiple stress levels was formed.

[0107] Next, the current equivalent aging acceleration data is calculated. Taking the set of state degradation rate curves under multiple stress levels as a reference, and combining the current key state parameter data of the equipment, the comprehensive stress level currently borne by the equipment is analyzed. By comparing the difference between the current comprehensive stress level and different stress levels in the set of curves, the equivalent aging calculation method is adopted to equate the aging effect of the current comprehensive stress on the equipment to the aging effect under a certain standard stress level in the set of curves, and then the current equivalent aging acceleration data is calculated.

[0108] Finally, by combining the set of degradation rate curves under multiple stress levels with the current equivalent aging acceleration data, a dynamic stress and life coupling assessment model is constructed. Through quantitative analysis of the relationship between the current stress state, aging acceleration and life loss of the equipment, the life loss and remaining life trend of the equipment under the current dynamic stress conditions are calculated, thereby obtaining the dynamic stress and life coupling relationship data of the equipment.

[0109] In this embodiment, by analyzing the multi-dimensional characteristics of stress and constructing a state response delay model, the law of equipment state change is accurately characterized; then, by utilizing the degradation curve clusters and equivalent aging acceleration under different stresses, the coupling relationship between dynamic stress and life is accurately modeled.

[0110] In an exemplary embodiment, the remaining reliable lifespan of the equipment under current operating stress is predicted by analyzing key equipment state parameter data and historical full lifecycle degradation data, resulting in remaining reliable lifespan data under dynamic stress, including:

[0111] Based on the data on the accelerated degradation effect caused by environmental stress, the current health index of the equipment's insulation and mechanical properties is calculated from the key state parameter data of the equipment, and the current comprehensive health index data of the equipment is obtained.

[0112] Based on the current comprehensive health index data of the equipment, Monte Carlo simulation of the degradation trajectory of the health index under the action of future stress spectrum is performed on the historical full life cycle degradation data to obtain the equipment health status degradation trajectory simulation dataset.

[0113] Based on the simulation dataset of equipment health status degradation trajectory, the probability distribution of the time point when the equipment health status first touches the preset warning boundary is calculated to obtain the probability distribution data of the equipment warning time point.

[0114] The earliest and latest warning times under different confidence levels are extracted from the probability distribution data of equipment warning time points to obtain the confidence interval data of the remaining reliable life of the equipment.

[0115] Based on the probability distribution data of equipment warning time points and the confidence interval data of equipment remaining reliable life, the remaining reliable life interval of equipment under the current operating stress is predicted, and the remaining reliable life interval data of equipment under dynamic stress is obtained.

[0116] Specifically, based on data on the accelerated degradation effect caused by environmental stress, and combined with key equipment status parameter data, an equipment health index assessment model is constructed. This model must cover two core dimensions: equipment insulation performance and mechanical performance. Through quantitative analysis of parameters related to equipment insulation performance (such as the ratio of dissolved gas content in transformer oil and the degree of aging of insulation materials) and parameters related to mechanical performance (such as equipment vibration acceleration and mechanical structure fatigue strength), sub-indices for equipment insulation performance and mechanical performance are calculated. Subsequently, based on the weights of the impact of equipment insulation performance and mechanical performance on the overall operational reliability of the equipment, a weighted fusion algorithm is used to fuse the two sub-indices, resulting in a comprehensive equipment health index that fully reflects the current health status of the equipment.

[0117] Next, based on the current comprehensive health index data of the equipment and combined with the historical full life cycle degradation data of the power equipment, the probability model and parameters of the equipment health status degradation are determined. Subsequently, the Monte Carlo simulation method is used to generate a large number of random simulation samples that conform to the probability model. Each sample corresponds to a health status degradation trajectory of the equipment under the action of the future stress spectrum. By calculating and organizing all simulation samples, the equipment health status degradation trajectory simulation dataset is obtained.

[0118] Subsequently, based on the simulated dataset of equipment health status degradation trajectories, a preset warning boundary is set. This warning boundary needs to be determined based on the critical state of safe equipment operation and historical fault data. Then, the intersection point detection of each simulated trajectory and the preset warning boundary is performed to identify the time point when each simulated trajectory first touches the preset warning boundary, forming a sequence of warning time points for each simulated trajectory. Based on the sequence of warning time points for all simulated trajectories, a probability statistical method is used to calculate the probability distribution characteristics of the warning time points, including probability density function, cumulative distribution function, etc., to obtain the probability distribution data of equipment warning time points.

[0119] Then, based on the probability distribution data of the equipment warning time points, a reasonable confidence level (such as 90% confidence level, 95% confidence level, etc.) is determined. Through statistical analysis of the probability distribution data, the earliest and latest possible times when the equipment first touches the warning boundary under the given confidence level are calculated. By determining the earliest and latest warning times under different confidence levels, the confidence interval data of the equipment's remaining reliable lifespan is obtained.

[0120] Finally, by combining the probability distribution data of equipment warning time points with the confidence interval data of the equipment's remaining reliable life, and comprehensively considering factors such as the dynamic change characteristics of current operating stress, the accelerated degradation effect caused by environmental stress, and the current health status of the equipment, a comprehensive analysis of the equipment's future degradation trend and the probability distribution of warning time is conducted to determine the remaining time range in which the equipment can maintain reliable operation under the current operating stress, thereby obtaining the equipment's remaining reliable life interval data under dynamic stress.

[0121] In this embodiment, by combining the health index with Monte Carlo simulation, the equipment status is comprehensively assessed and multiple possible degradation trajectories are generated. This enables interval-based prediction of the remaining reliable lifespan of the equipment and probability distribution of early warning time points, effectively improving the foresight and reliability of equipment operation and maintenance.

[0122] In an exemplary embodiment, based on the device health status degradation trajectory simulation dataset, the probability distribution of the time point when the device health status first reaches the preset warning boundary is calculated to obtain device warning time point probability distribution data, including:

[0123] Based on the simulation dataset of equipment health status degradation trajectory, the intersection point detection between each simulation trajectory and the preset multi-level warning threshold boundary is performed to obtain the multi-level warning threshold trigger time sequence for each simulation trajectory;

[0124] The time sequence of the multi-level warning thresholds for each simulated trajectory was statistically analyzed, and the average time, time standard deviation, and quantiles of the time distribution for each level of warning threshold were calculated.

[0125] Based on the average time, time standard deviation, and quantiles of the time distribution for each warning threshold, a curve is constructed to show the relationship between device status warning time and warning probability, with time as the horizontal axis and cumulative hit probability as the vertical axis.

[0126] Based on the relationship curve, the earliest and latest possible times when the device status reaches the warning threshold at each level under the preset confidence level are extracted to form the probability distribution data of the device warning time point.

[0127] Specifically, the evaluation and analysis module first retrieves preset multi-level warning threshold boundaries based on the simulated dataset of equipment health status degradation trajectories. These multi-level warning threshold boundaries need to be set based on different fault risk levels of the equipment, including mild warning thresholds, moderate warning thresholds, and severe warning thresholds, etc. Each level of threshold needs to correspond to different health status critical values ​​of the equipment. Subsequently, for each simulated trajectory, a trajectory and threshold boundary cross-detection algorithm is used to detect the intersection points of the simulated trajectory with the warning threshold boundaries of each level during the degradation process, and record the time point corresponding to each intersection point to form a sequence of multi-level warning threshold triggering time points for each simulated trajectory. This sequence can reflect the situation of each simulated trajectory triggering the warning thresholds of each level at different time points. Next, statistical analysis of the multi-level warning threshold trigger times was conducted. Based on the multi-level warning threshold trigger time sequence of each simulated trajectory, statistical work was carried out according to the warning threshold level. For each warning threshold level, the time point data of all simulated trajectories triggering that threshold were collected. Statistical calculation methods were used to calculate the average trigger time, time standard deviation, and quantiles of the time distribution (such as the 25th, 50th, and 75th quantiles) corresponding to that warning threshold level. The average trigger time reflects the average time level of the overall equipment triggering that warning threshold level, the time standard deviation reflects the dispersion of the trigger time, and the quantiles reflect the central tendency and dispersion range of the trigger time distribution. The calculation of the above statistical parameters provides a statistical basis for the subsequent construction of probability relationship curves. Next, a device status warning time-probability relationship curve is constructed. Based on the average touch time, time standard deviation, and quantile of the time distribution corresponding to each warning threshold, the horizontal and vertical axes of the curve are determined, with the horizontal axis set to time and the vertical axis set to cumulative touch probability. By fitting the probability distribution of touch time data, a device status warning time-probability relationship curve with time as the horizontal axis and cumulative touch probability as the vertical axis is generated. This curve should be able to clearly show the trend of cumulative probability change of the device touching the corresponding warning threshold at different time points. For example, as time goes by, the cumulative touch probability gradually increases until it reaches 100%, and the slope of the curve can reflect the rate of change of the probability of the device touching the warning threshold.Finally, extract the early warning time data under high confidence and form probability distribution data. According to the early warning time - probability relationship curve of the equipment status, set a specified high confidence level (such as 90% confidence level, 95% confidence level, etc.), and this confidence level needs to be determined according to the reliability requirements of the operation of power equipment; through the analysis of the early warning time - probability relationship curve, extract the earliest possible time and the latest possible time when the equipment status touches each level of early warning threshold under this high confidence level. Among them, the earliest possible time corresponds to the minimum time point when the cumulative touch probability reaches this confidence level, and the latest possible time corresponds to the maximum time point when the cumulative touch probability reaches this confidence level; integrate the earliest early warning time, the latest early warning time under high confidence corresponding to each level of early warning threshold, and the corresponding cumulative touch probability data to form the probability distribution data of the equipment early warning time point, which can comprehensively reflect the early warning time distribution of the equipment under different confidence levels and different early warning threshold levels.

[0128] In this embodiment, through the analysis of multi - level early warning thresholds and their probability distributions, a high - confidence early warning time interval is generated, realizing a more refined and reliable hierarchical early warning of equipment failure risks.

[0129] In an exemplary embodiment, the dynamic early warning logic strategy of power equipment mainly includes three core links:

[0130] First, construct an adaptive adjustment model for dynamic early warning thresholds. This model takes the environmental stress - induced degradation acceleration effect, the remaining reliable life interval of the equipment, and the dynamic stress - life coupling relationship as the core inputs to realize the real - time optimization of the early warning thresholds. When the environmental stress intensifies or the remaining life shortens, the system automatically lowers the early warning threshold to give an early warning in advance; otherwise, it appropriately raises the threshold to reduce false alarms.

[0131] Second, optimize the generated dynamic thresholds. Eliminate the threshold fluctuations through a smoothing filter algorithm to ensure the smooth continuity of the threshold curve; at the same time, perform logical consistency verification to verify the reasonable association between the threshold and the equipment status parameters and avoid logical conflicts.

[0132] Finally, establish an early warning strategy logic mapping system. Divide multi - level early warning levels according to the optimized thresholds, and formulate corresponding early warning information generation rules and linkage control strategies. Different early warning levels will trigger differentiated operation and maintenance responses, including operations such as sending early warning notifications, upgrading monitoring modes, and starting protection mechanisms, forming a closed - loop management.

[0133] This strategy significantly improves the accuracy and operation and maintenance efficiency of the early warning system through the organic combination of threshold dynamic adjustment, data optimization processing, and hierarchical response mechanisms.

[0134] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0135] Based on the same inventive concept, this application also provides a big data-based power equipment status early warning device for implementing the aforementioned big data-based power equipment status early warning method. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more big data-based power equipment status early warning device embodiments provided below can be found in the limitations of the big data-based power equipment status early warning method described above, and will not be repeated here.

[0136] In one exemplary embodiment, such as Figure 4 As shown, a power equipment status early warning device based on big data is provided, including:

[0137] The acquisition module 402 is used to acquire the multi-source real-time operation dataset and the real-time environmental condition dataset of the power equipment, and to determine the key state parameter data and the operating stress parameter data of the equipment from the multi-source real-time operation dataset and the real-time environmental condition dataset.

[0138] The evaluation module 404 is used to perform dynamic stress and life coupling evaluation on the key state parameter data of the equipment based on the equipment operating stress parameter data, and obtain the dynamic stress and life coupling relationship data of the equipment.

[0139] Analysis module 406 is used to perform equipment condition degradation acceleration effect analysis on real-time environmental condition datasets based on equipment dynamic stress and life coupling relationship data, and obtain degradation acceleration effect data of environmental stress.

[0140] The strategy generation module 408 is used to adaptively adjust the dynamic early warning threshold of key state parameter data of equipment based on the degradation acceleration effect data of environmental stress and the coupling relationship data of equipment dynamic stress and life, and generate dynamic early warning logic strategy for power equipment.

[0141] The power equipment status early warning module 410 is used to execute power equipment status early warning according to the dynamic early warning logic strategy of power equipment.

[0142] In an exemplary embodiment, the acquisition module 402 is specifically used to perform data quality verification and abnormal data point cleaning based on the multi-source real-time operation dataset and the environmental condition real-time dataset to obtain the equipment operation data sequence; and to extract key state parameters and operating stress parameters from the equipment operation data sequence to obtain equipment key state parameter data and equipment operating stress parameter data, respectively.

[0143] In an exemplary embodiment, the evaluation module 404 is further configured to acquire historical full life cycle degradation data of the power equipment; and to perform dynamic stress and life coupling evaluation on the key state parameter data and historical full life cycle degradation data of the equipment based on the equipment operating stress parameter data, thereby obtaining dynamic stress and life coupling relationship data of the equipment.

[0144] Analysis module 406 is also used to perform quantitative impact analysis on the aging rate of equipment insulation materials and the fatigue strength of mechanical structures based on the coupling relationship data of equipment dynamic stress and life, and obtain environmental stress-induced degradation acceleration effect data; based on the environmental stress-induced degradation acceleration effect data, it predicts the remaining reliable life range of equipment under the current operating stress based on the equipment key state parameter data and historical full life cycle degradation data, and obtains the equipment remaining reliable life range data under dynamic stress.

[0145] In an exemplary embodiment, the evaluation module 404 is further configured to perform stress parameter time series decomposition on the equipment operating stress parameter data, extract the transient peak value, root mean square value, and cumulative effect of the stress parameters, and obtain multi-dimensional time series characteristic data of stress; based on the multi-dimensional time series characteristic data of stress, model the response delay and hysteresis effect of the state parameters under the corresponding stress on the key state parameter data of the equipment, and obtain the state parameter stress response delay model; based on the state parameter stress response delay model, fit the equipment state degradation rate curves under different stress levels on the historical full life cycle degradation data of the power equipment, and obtain a cluster of state degradation rate curves under multiple stress levels; based on the cluster of state degradation rate curves under multiple stress levels, calculate the equivalent aging acceleration under the current comprehensive stress on the key state parameter data of the equipment, and obtain the current equivalent aging acceleration data; based on the cluster of state degradation rate curves under multiple stress levels and the current equivalent aging acceleration data, perform dynamic stress and life coupling evaluation, and obtain the dynamic stress and life coupling relationship data of the equipment.

[0146] In an exemplary embodiment, the analysis module 406 is further configured to calculate the current health index of the equipment's insulation and mechanical performance based on the environmental stress-induced degradation acceleration effect data, thereby obtaining the equipment's current comprehensive health index data; based on the equipment's current comprehensive health index data, perform Monte Carlo simulation of the degradation trajectory of the health index under future stress spectrum based on historical full life cycle degradation data, thereby obtaining a simulation dataset of the equipment's health status degradation trajectory; based on the simulation dataset of the equipment's health status degradation trajectory, calculate the probability distribution of the time point at which the equipment's health status first touches the preset warning boundary, thereby obtaining the equipment's warning time point probability distribution data; extract the earliest and latest warning times at different confidence levels from the equipment's warning time point probability distribution data, thereby obtaining the confidence interval data of the equipment's remaining reliable lifespan; and based on the equipment's warning time point probability distribution data and the confidence interval data of the equipment's remaining reliable lifespan, predict the equipment's remaining reliable lifespan interval under the current operating stress, thereby obtaining the equipment's remaining reliable lifespan interval data under dynamic stress.

[0147] In an exemplary embodiment, the analysis module 406 is further configured to perform intersection point detection between each simulated trajectory and the preset multi-level warning threshold boundary based on the equipment health status degradation trajectory simulation dataset, thereby obtaining a sequence of multi-level warning threshold arrival time points for each simulated trajectory; statistically analyze the sequence of multi-level warning threshold arrival time points for each simulated trajectory, and calculate the average time, time standard deviation, and quantile of the time distribution for each level of warning threshold; based on the average time, time standard deviation, and quantile of the time distribution for each level of warning threshold, construct a relationship curve between equipment status warning time and warning probability with time as the horizontal axis and cumulative arrival probability as the vertical axis; and extract the earliest and latest possible times for equipment status to arrive at each level of warning threshold under a preset confidence level based on the relationship curve, thereby forming equipment warning time point probability distribution data.

[0148] The modules in the aforementioned big data-based power equipment status early warning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0149] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores multi-source real-time operational datasets of the power equipment and real-time environmental condition datasets. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a power equipment status early warning method based on big data.

[0150] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0151] In one exemplary embodiment, a computer device is 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 of the method described above.

[0152] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0153] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0156] 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 application.

[0157] 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 this patent application. 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 early warning of power equipment status based on big data, characterized in that, The method includes: Acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets; Based on the equipment operating stress parameter data, a dynamic stress and life coupling evaluation is performed on the key state parameter data of the equipment to obtain the dynamic stress and life coupling relationship data of the equipment. Based on the coupling relationship data between the dynamic stress and lifespan of the equipment, the degradation acceleration effect analysis of the equipment condition is performed on the real-time environmental condition dataset to obtain the degradation acceleration effect data caused by environmental stress. Based on the degradation acceleration effect data of the environmental stress and the coupling relationship data between the dynamic stress and lifespan of the equipment, the dynamic early warning threshold of the key state parameters of the equipment is adaptively adjusted, and a dynamic early warning logic strategy for the power equipment is generated. Based on the dynamic early warning logic strategy of the power equipment, execute the power equipment status early warning.

2. The method according to claim 1, characterized in that, The step of determining key equipment state parameter data and equipment operating stress parameter data from the multi-source real-time operating dataset and the real-time environmental condition dataset includes: Based on the multi-source real-time operation dataset and the environmental condition real-time dataset, data quality verification and abnormal data point cleaning are performed to obtain the equipment operation data sequence; Key state parameters and operating stress parameters are extracted from the equipment operation data sequence to obtain key state parameter data and operating stress parameter data, respectively.

3. The method according to claim 1, characterized in that, The method further includes: Acquire historical full lifecycle degradation data of power equipment; Based on the equipment operating stress parameter data, a dynamic stress and lifespan coupling assessment is performed on the equipment key state parameter data and the historical full lifespan degradation data to obtain equipment dynamic stress and lifespan coupling relationship data. Based on the dynamic stress and lifespan coupling data of the equipment, a quantitative analysis of the impact of environmental stress on the aging rate of the equipment's insulation materials and the fatigue strength of the mechanical structure is performed on the real-time environmental operating data to obtain data on the accelerated degradation effect caused by environmental stress. Based on the environmental stress-induced accelerated degradation effect data, the remaining reliable lifespan of the equipment under the current operating stress is predicted using the equipment's key state parameter data and the historical full life cycle degradation data, thus obtaining the equipment's remaining reliable lifespan data under dynamic stress.

4. The method according to claim 3, characterized in that, The dynamic stress-life coupling evaluation of the key state parameter data of the equipment, to obtain the dynamic stress-life coupling relationship data of the equipment, includes: The stress parameter time series decomposition was performed on the stress parameter data of the equipment operation to extract the transient peak value, root mean square value and cumulative effect of the stress parameter, and obtain multi-dimensional time series characteristic data of stress. Based on the stress multi-dimensional time-series characteristic data, the response delay and hysteresis effect of the key state parameters of the equipment under the corresponding stress are modeled to obtain the stress response delay model of the state parameters. Based on the state parameter stress response delay model, the equipment state degradation rate curves under different stress levels are fitted to the historical full life cycle degradation data of the power equipment to obtain a cluster of state degradation rate curves under multiple stress levels. Based on the set of state degradation rate curves under the multi-stress levels, the equivalent aging acceleration under the current comprehensive stress is calculated on the key state parameter data of the equipment to obtain the current equivalent aging acceleration data. Based on the set of degradation rate curves under the multi-stress levels and the current equivalent aging acceleration data, a dynamic stress and lifespan coupling assessment is performed to obtain the dynamic stress and lifespan coupling relationship data of the equipment.

5. The method according to claim 3, characterized in that, The process of predicting the remaining reliable lifespan of the equipment under current operating stress by analyzing the key state parameter data and historical full life cycle degradation data of the equipment, to obtain the remaining reliable lifespan data of the equipment under dynamic stress, includes: Based on the environmental stress-induced degradation acceleration effect data, the current health index of the equipment's insulation and mechanical performance is calculated from the key state parameter data of the equipment to obtain the current comprehensive health index data of the equipment. Based on the current comprehensive health index data of the equipment, Monte Carlo simulation of the degradation trajectory of the health index under the action of future stress spectrum is performed on the historical full life cycle degradation data to obtain the equipment health status degradation trajectory simulation dataset. Based on the simulation dataset of the equipment health status degradation trajectory, the probability distribution of the time point when the equipment health status first touches the preset warning boundary is calculated to obtain the probability distribution data of the equipment warning time point. The earliest and latest warning times under different confidence levels are extracted from the probability distribution data of the equipment warning time points to obtain the confidence interval data of the equipment's remaining reliable lifespan. Based on the probability distribution data of the equipment warning time points and the confidence interval data of the equipment's remaining reliable lifespan, the remaining reliable lifespan interval of the equipment under the current operating stress is predicted to obtain the remaining reliable lifespan interval data of the equipment under dynamic stress.

6. The method according to claim 5, characterized in that, The step of calculating the probability distribution of the time point when the device's health status first reaches the preset warning boundary based on the device health status degradation trajectory simulation dataset, and obtaining the device warning time point probability distribution data, includes: Based on the simulation dataset of the device health status degradation trajectory, the intersection point detection between each simulation trajectory and the preset multi-level warning threshold boundary is performed to obtain the multi-level warning threshold trigger time point sequence for each simulation trajectory. The time sequence of the multi-level warning thresholds for each simulated trajectory is statistically analyzed, and the average time, time standard deviation, and quantile of the time distribution for each level of warning threshold are calculated. Based on the average time, time standard deviation, and quantiles of the time distribution for each level of warning threshold, a curve is constructed showing the relationship between device status warning time and warning probability with time on the horizontal axis and cumulative touch probability on the vertical axis. Based on the relationship curve, the earliest and latest possible times when the device status reaches the warning threshold at each level under the preset confidence level are extracted to form the probability distribution data of device warning time points.

7. A power equipment status early warning device based on big data, characterized in that, The device includes: The acquisition module is used to acquire multi-source real-time operation datasets and environmental condition real-time datasets of power equipment, and to determine key state parameter data and operating stress parameter data of equipment from the multi-source real-time operation datasets and the environmental condition real-time datasets. The evaluation module is used to perform dynamic stress and life coupling evaluation on the key state parameter data of the equipment based on the equipment operating stress parameter data, and obtain the dynamic stress and life coupling relationship data of the equipment. The analysis module is used to perform equipment condition degradation acceleration effect analysis on the real-time environmental condition dataset based on the dynamic stress and life coupling relationship data of the equipment, and obtain degradation acceleration effect data of environmental stress. The strategy generation module is used to adaptively adjust the dynamic early warning threshold of the key state parameter data of the equipment based on the degradation acceleration effect data of the environmental stress and the coupling relationship data of the equipment dynamic stress and life, and generate a dynamic early warning logic strategy for the power equipment. The power equipment status early warning module is used to execute power equipment status early warnings according to the dynamic early warning logic strategy of the power equipment.

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.

10. A computer program product, comprising a computer program, 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