A transformer operation state intelligent monitoring method and system

Abstract

The embodiment of the application provides a kind of transformer operating state intelligent monitoring method and system, it is related to transformer operating state monitoring technical field, method includes obtaining the internal operation information of transformer, external environment information and power grid operating condition;Based on the internal operation information, the external environment information and the power grid operating condition, the expected response parameter corresponding to the internal operation information of the transformer is generated;The internal operation information and the expected response parameter are evaluated, and a plurality of deviation indexes are obtained;According to a plurality of the deviation indexes and the preset fault feature library, whether the transformer exists anomaly is judged;In the case where the transformer exists anomaly, according to a plurality of the deviation indexes and the preset fault feature library, early warning information is output.The application can improve the timeliness and accuracy of transformer fault early warning.

Description

Technical Field

[0001] This application relates to the field of transformer operating status monitoring technology, and more specifically, to an intelligent monitoring method and system for transformer operating status. Background Technology

[0002] In related technologies, transformers, as core equipment in power systems, are crucial to the reliability of the power grid due to their stable operation. Traditional methods for monitoring transformer operating conditions often rely on manual inspections or analysis of single parameters, making it difficult to detect potential faults in a timely manner. While existing technologies can monitor issues such as abnormal oil temperature, insulation aging, or partial discharge, they lack real-time analysis capabilities that can adapt to changing conditions for multifaceted operating data, leading to untimely fault warnings and even erroneous judgments. Especially with the increasing complexity of modern power grid structures, such as the integration of large amounts of renewable energy, the operating environment faced by transformers has become more dynamic and volatile than ever before, posing a severe challenge to traditional intelligent monitoring systems. In power grid environments with a large number of distributed renewable energy sources connected to the grid, transformers frequently experience rapidly changing load cycles and increased harmonic currents. This causes fluctuations in their internal operating information (such as temperature, oil gas, and partial discharge) to be highly similar to and superimposed with early, hidden fault signals (such as minor winding deformation, fatigue cracks at lead connections, and slight local insulation degradation). In this situation, traditional intelligent monitoring systems struggle to accurately distinguish between normal operating fluctuations caused by changes in the power grid structure and weak abnormal signals caused by the nascent stages of actual internal faults. For example, rapid load changes causing fluctuations in oil and winding temperatures may mask weak overheating signals; the thermodynamic response caused by load changes may be confused with trace gas growth caused by faults; and background discharge signals caused by grid harmonic interference may highly overlap with partial discharge signals generated by early insulation defects. This leads to frequent false alarms from the system, reducing the trust of maintenance personnel, and may even cause the system to miss real early faults, resulting in serious consequences. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes an intelligent monitoring method and system for transformer operating status, aiming to solve the technical problem that existing transformer operating status monitoring methods are unable to identify early hidden faults inside transformers in real time and accurately when facing complex and ever-changing power grid environments, resulting in untimely fault warnings, frequent false warnings, and even missed reports of real faults.

[0004] In a first aspect, embodiments of this application provide an intelligent monitoring method for the operating status of a transformer, including:

[0005] To acquire internal operating information of the transformer, external environmental information, and power grid operating status;

[0006] Based on the internal operating information, the external environment information, and the power grid operating status, the expected response parameters corresponding to the internal operating information of the transformer are generated.

[0007] The deviation between the internal operating information and the expected response parameters is evaluated to obtain multiple deviation indices;

[0008] Based on multiple deviation indices and a preset fault feature library, determine whether the transformer is abnormal;

[0009] In the event of an abnormality in the transformer, an early warning message is output based on multiple deviation indices and a preset fault feature library.

[0010] According to some embodiments of this application, generating the expected response parameters corresponding to the internal operating information of the transformer based on the internal operating information, the external environment information, and the power grid operating status includes:

[0011] Based on the internal operating information, the external environmental information, and the power grid operating status, the instantaneous rate of change of the transformer oil temperature and the spectral characteristics of the partial discharge background noise are obtained.

[0012] Based on the instantaneous rate of change of the oil temperature and the internal operating information, the expected release amount of background gas from the transformer caused by the temperature change is calculated.

[0013] The transformer's oil temperature instantaneous change rate, the spectral characteristics of the partial discharge background noise, and the expected release amount are adjusted in real time according to a preset adaptive filter to generate expected response parameters corresponding to the transformer's internal operating information. The preset adaptive filter is used to adjust parameters or empirical coefficients.

[0014] According to some embodiments of this application, the step of obtaining the instantaneous rate of change of the transformer oil temperature and the spectral characteristics of the partial discharge background noise based on the internal operating information, the external environmental information, and the power grid operating status includes:

[0015] The current load current and cooling system operating status are obtained based on the internal operating information, the ambient temperature is obtained based on the external environmental information, and the amplitude of each harmonic current and voltage is obtained based on the power grid operating status.

[0016] Obtain the heat dissipation constant of the transformer itself and the response characteristics of the transformer core to harmonics of different preset frequencies;

[0017] The instantaneous rate of change of the transformer oil temperature is obtained by real-time calculation based on the current load current, the ambient temperature, the operating status of the cooling system, and the heat dissipation constant.

[0018] The spectral characteristics of the partial discharge background noise are calculated based on the amplitude of each harmonic current and voltage and the response characteristics.

[0019] According to some embodiments of this application, the step of calculating the expected release amount of background gas from the transformer due to temperature changes based on the instantaneous rate of change of the oil temperature and the internal operating information includes:

[0020] The solubility curve and diffusion rate of the background gas in the transformer are obtained based on the internal operating information, wherein the background gas includes at least one of the following: hydrogen, methane, ethane, ethylene, and acetylene;

[0021] Based on the instantaneous rate of change of oil temperature, the solubility curve, and the diffusion rate, the expected release amount caused by the temperature change is obtained.

[0022] According to some embodiments of this application, the deviation assessment of the internal operating information from the expected response parameters yields multiple deviation indices, including:

[0023] Multiple deviation values ​​are obtained by calculating the internal operating information and the expected response parameters;

[0024] Multiple deviation indices are obtained by calculating percentages based on multiple deviation differences and a preset standard deviation.

[0025] According to some embodiments of this application, the calculation of the internal operating information and the expected response parameters to obtain multiple deviation values ​​includes:

[0026] Obtain the oil temperature from the internal operating information and the expected oil temperature from the expected response parameters;

[0027] The difference between the oil temperature in the internal operating information and the expected oil temperature in the expected response parameters is calculated to obtain the oil temperature deviation difference.

[0028] The difference between the gas concentration in the internal operating information and the expected gas concentration in the expected response parameters is calculated to obtain the gas concentration deviation difference.

[0029] The difference between the intensity of a specific frequency component of the partial discharge signal in the internal operating information and the intensity of the frequency component of the expected partial discharge signal in the expected response parameters is calculated to obtain the deviation difference of the frequency component intensity of the partial discharge signal.

[0030] Multiple deviation values ​​are determined based on the oil temperature deviation value, the gas concentration deviation value, and the frequency component intensity deviation value of the partial discharge signal.

[0031] According to some embodiments of this application, determining whether the transformer is abnormal based on a plurality of deviation indices and a preset fault feature library includes:

[0032] If at least one of the deviation indices continues to exceed a first preset deviation threshold within a preset time, the transformer will be marked as a potential anomaly.

[0033] A pattern recognition algorithm is used to compare the fault problems of the transformer marked as potential anomalies with a preset fault feature database to determine whether the transformer is abnormal.

[0034] According to some embodiments of this application, when the transformer is abnormal, outputting early warning information based on multiple deviation indices and a preset fault feature library includes:

[0035] The features corresponding to the multiple deviation indices are respectively matched with the patterns in the preset fault feature library to calculate the matching degree, thereby obtaining multiple target matching degrees. The preset fault feature library includes multiple fault patterns.

[0036] Based on the multiple deviation indices and multiple target matching degrees, early warning information is output.

[0037] According to some embodiments of this application, the step of outputting early warning information based on a plurality of deviation indices and a plurality of target matching degrees includes:

[0038] When at least one of the deviation indices continuously exceeds a second preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than a first preset matching degree, an early warning message is output, wherein the early warning message is a reminder to pay attention;

[0039] When multiple deviation indices continuously exceed a third preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than a second preset matching degree, an early warning message is output, wherein the early warning message is a warning reminder;

[0040] When multiple deviation indices continuously exceed a fourth preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than a third preset matching degree, a warning message is output. The warning message is a danger alert. The second preset deviation threshold is less than the third preset deviation threshold, the third preset deviation threshold is less than the fourth preset deviation threshold, the first preset matching degree is less than the second preset matching degree, and the second preset matching degree is less than the third preset matching degree.

[0041] Secondly, this application also discloses an intelligent monitoring system for transformer operating status, comprising:

[0042] The acquisition module is used to acquire internal operating information of the transformer, external environmental information, and power grid operating status.

[0043] An adjustment and generation module is used to generate expected response parameters corresponding to the internal operating information of the transformer based on the internal operating information, the external environment information, and the power grid operating status.

[0044] The deviation assessment module is used to assess the deviation between the internal operating information and the expected response parameters, and obtain multiple deviation indices.

[0045] The judgment module is used to determine whether the transformer has any abnormalities based on multiple deviation indices and a preset fault feature library;

[0046] The output module is used to output early warning information based on multiple deviation indices and a preset fault feature library when the transformer is abnormal.

[0047] The technical solution according to the embodiments of this application has at least the following beneficial effects: The intelligent monitoring method for transformer operating status disclosed in this application acquires the transformer's internal operating information, external environmental information, and power grid operating status, and generates expected response parameters corresponding to the transformer's internal operating information based on this information. By evaluating the deviation between the actual internal operating information and the expected response parameters, multiple deviation indices are obtained, which can effectively distinguish between normal operating fluctuations caused by changes in the power grid structure and weak abnormal signals caused by the initiation of real internal faults. This solves the problem in the prior art where fault warnings are not timely or even misjudged due to the lack of real-time and situation-changing analysis capabilities for various operating data. Furthermore, based on these deviation indices and a preset fault feature library, the method determines whether the transformer has any abnormalities and outputs warning information when abnormalities are found. This can accurately identify early hidden faults and overcome the shortcomings of traditional monitoring systems that frequently issue false warnings or fail to report real faults in complex power grid environments. This method can significantly improve the timeliness and accuracy of transformer fault warnings, reduce the risk of misjudgment by maintenance personnel, and ensure the reliable operation of the power system.

[0048] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0049] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0050] Figure 1This is a flowchart illustrating an embodiment of the intelligent monitoring method for transformer operating status provided in this application.

[0051] Figure 2 This is a schematic diagram of an intelligent monitoring system for transformer operating status provided in one embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical methods, 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.

[0053] It should be noted that the meaning of "multiple" (or "more than") in the description of the embodiments of this application refers to two or more, and "greater than," "less than," "exceeding," etc. are understood to exclude the number itself, while "above," "below," "within," etc. are understood to include the number itself. If "first," "second," etc. are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0054] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. 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 of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: the existence of a alone, the existence of b alone, the existence of c alone, the simultaneous existence of a and b, the simultaneous existence of a and c, the simultaneous existence of b and c, or the simultaneous existence of a, b, and c, where a, b, and c can be single or multiple.

[0055] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0056] The intelligent monitoring method for transformer operating status provided in this application 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.; 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, content delivery networks (CDN), and big data and artificial intelligence platforms; the software can be an application that implements the intelligent monitoring method for transformer operating status, but is not limited to the above forms.

[0057] This application can be applied to numerous 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 devices, 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 communication networks. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices. It should be noted that in various specific embodiments of this invention, when processing is required based on data related to the characteristics of an object (e.g., user attributes or sets of attribute information), permission or consent from the corresponding object is obtained first, and the collection, use, and processing of this data comply with relevant laws and standards. Furthermore, when the embodiments of the present invention need to obtain the attribute information of an object, they will obtain the separate permission or separate consent of the corresponding object through pop-up windows or redirection to a confirmation page. After obtaining the separate permission or separate consent of the corresponding object, they will then obtain the relevant data of the object necessary for the embodiments of the present invention to operate normally.

[0058] See Figure 1 , Figure 1This is a flowchart illustrating an embodiment of the intelligent monitoring method for transformer operating status provided in this application. The intelligent monitoring method for transformer operating status provided in this application includes, but is not limited to, steps S110 to S150, which are described below.

[0059] Step S110: Obtain the transformer's internal operating information, external environmental information, and power grid operating status;

[0060] Step S120: Based on internal operating information, external environmental information, and power grid operating status, generate the expected response parameters corresponding to the transformer's internal operating information;

[0061] Step S130: Evaluate the deviation between the internal operating information and the expected response parameters to obtain multiple deviation indices;

[0062] Step S140: Determine whether the transformer is abnormal based on multiple deviation indices and a preset fault feature library;

[0063] Step S150: In the event of an abnormality in the transformer, output early warning information based on multiple deviation indices and a preset fault feature library.

[0064] It should be noted that "internal operating information" refers to various real-time operating data within the transformer, such as oil temperature, winding temperature, dissolved gas concentration in the oil (e.g., hydrogen, methane, ethane, ethylene, acetylene, etc.), partial discharge signal strength, and insulation resistance. This information directly reflects the transformer's internal health status. "External environmental information" refers to various data related to the external environment in which the transformer is located, such as ambient temperature, humidity, wind speed, and solar radiation intensity. This information affects the transformer's heat dissipation and insulation performance. "Grid operating status" refers to the operating parameters of the power grid to which the transformer is connected, such as load current, voltage, amplitude, frequency, and power factor of each harmonic current and voltage. These parameters directly affect the transformer's load and electrical stress. "Expected response parameters" refer to the theoretical or reference values ​​of the transformer's internal operating information predicted by a model under normal operating conditions, based on the current internal operating information, external environmental information, and grid operating status. Comparing the actual operating information with the expected response parameters allows for more accurate identification of anomalies. The "deviation index" is a quantitative indicator that measures the degree of difference between the actual operating information and the expected response parameters. A larger deviation index indicates a greater deviation between the actual operating state and the expected state, and a higher probability of anomalies. The "fault feature library" is a pre-built database containing characteristic information of various known transformer fault modes, such as the proportion of gas components in the oil, partial discharge characteristics, and temperature change trends corresponding to different fault types. By comparing the deviation index with the fault feature library, specific fault types can be identified.

[0065] It should be noted that the intelligent monitoring method for transformer operating status in this application first requires acquiring the transformer's internal operating information, external environmental information, and power grid operating status. This information can be acquired in various ways. For example, internal operating information can be collected in real time by various sensors installed inside the transformer, such as temperature sensors for oil and winding temperatures, gas sensors for monitoring dissolved gas concentrations in the oil, and partial discharge sensors for detecting partial discharge signals. External environmental information can be acquired through environmental monitoring stations installed outside the transformer, such as thermometers and hygrometers. Power grid operating status can be acquired through current transformers, voltage transformers, and power quality monitoring equipment connected to the power grid. These sensors and monitoring equipment transmit the collected data to a data acquisition unit, which then performs preliminary processing and storage. The generation of expected response parameters is one of the key steps in this application; it aims to establish a dynamic benchmark for evaluating the actual operating status of the transformer. Physical models or data-driven models can be used to predict the expected oil temperature, expected gas concentration, or expected partial discharge signal intensity of the transformer under current operating conditions. Specifically, the expected oil temperature of the transformer under stable operating conditions can be calculated using a thermodynamic model based on factors such as transformer design parameters, load conditions, and ambient temperature. For the gas concentration in the oil, the expected release of background gases can be predicted based on the transformer oil's solubility curve and diffusion rate, combined with oil temperature and load changes. For partial discharge signals, the spectral characteristics of the expected partial discharge background noise can be predicted based on grid harmonic background noise and the transformer's own response characteristics. These models can be trained and optimized using historical data to improve prediction accuracy.

[0066] In one embodiment, after obtaining the actual operating information and expected response parameters, it is necessary to compare the two to quantify their deviation. For example, the difference between the actual oil temperature and the expected oil temperature can be directly calculated to obtain the oil temperature deviation difference. Similarly, the difference between the actual gas concentration and the expected gas concentration can be calculated to obtain the gas concentration deviation difference; the difference between the intensity of a specific frequency component of the actual partial discharge signal and the intensity of the frequency component of the expected partial discharge signal can be calculated to obtain the frequency component intensity deviation difference of the partial discharge signal. These deviation differences can be further standardized, for example, by dividing by a preset standard deviation, to obtain dimensionless deviation indices, which facilitate comparison and comprehensive evaluation between different parameters. Then, after obtaining multiple deviation indices, they need to be compared with a preset fault feature library to determine whether the transformer is abnormal. For example, one or more deviation thresholds can be set. When one or more deviation indices continuously exceed these thresholds within a preset time, it is considered that the transformer may have a potential abnormality. Furthermore, pattern recognition algorithms, such as support vector machines (SVM), neural networks, or decision trees, can be used to compare the combination pattern of the current deviation indices with various fault patterns stored in the fault feature library. The fault feature database contains deviation index feature patterns corresponding to different fault types (such as winding overheating, insulation aging, partial discharge, etc.). Through pattern recognition, it can be determined whether the current deviation matches a known fault mode, thereby identifying whether the transformer is abnormal. Finally, when the system determines that the transformer is abnormal, it needs to promptly output early warning information to maintenance personnel. The output of early warning information can be graded according to the severity of the deviation index and its matching degree with the fault feature database. For example, when the deviation index is slight and has a low matching degree with a potential fault mode, a "pay attention reminder" can be output; when the deviation index is moderate and has a high matching degree with a fault mode, a "warning reminder" can be output; when the deviation index is severe and has an extremely high matching degree with an emergency fault mode, a "danger reminder" can be output. Early warning information can include the type of abnormality, possible causes, and suggested inspection measures, and is sent to relevant personnel through various means (such as SMS, email, audible and visual alarms, etc.) so that timely intervention measures can be taken.

[0067] It is worth noting that the intelligent monitoring method for transformer operating status in this application, by acquiring the transformer's internal operating information, external environmental information, and power grid operating status, and generating expected response parameters corresponding to the transformer's internal operating information based on this information, can establish a dynamic and highly adaptable benchmark. Unlike traditional methods that rely solely on fixed thresholds or single-parameter analysis, the scheme in this application can adjust the expected response parameters in real time, thereby more accurately reflecting the normal operating status of the transformer under complex and variable operating conditions. By evaluating the deviation between actual operating information and expected response parameters, multiple deviation indices are obtained, and combined with a preset fault feature library for anomaly judgment and early warning, this application can effectively distinguish between normal operating fluctuations caused by changes in power grid structure and weak abnormal signals caused by the budding of internal real faults. For example, when power grid harmonic interference increases, this application can predict and subtract the influence of background noise on partial discharge signals, thereby avoiding false warnings and improving the ability to identify early insulation defects. This method not only improves the timeliness and accuracy of fault warnings and reduces the false alarm rate, but also provides maintenance personnel with more specific and targeted warning information, thereby effectively avoiding the problems of missed or false alarms that may occur in traditional monitoring systems in complex power grid environments, and significantly improving the reliability and safety of transformer operation.

[0068] In this regard, this application further proposes the following steps for generating the expected response parameters corresponding to the transformer's internal operating information based on the aforementioned internal operating information, external environmental information, and power grid operating conditions:

[0069] Based on internal operating information, external environmental information, and power grid operating status, the instantaneous rate of change of transformer oil temperature and the spectral characteristics of partial discharge background noise are obtained.

[0070] Based on the instantaneous rate of change of oil temperature and internal operating information, the expected release amount of background gas in the transformer caused by temperature changes is calculated.

[0071] Based on the preset adaptive filter, the instantaneous rate of change of transformer oil temperature, the spectral characteristics of partial discharge background noise, and the expected release amount are adjusted in real time to generate the expected response parameters corresponding to the internal operating information of the transformer. The preset adaptive filter is used to adjust parameters or empirical coefficients.

[0072] Specifically, obtaining the instantaneous rate of change of transformer oil temperature refers to calculating its change over a very short time by continuously monitoring oil temperature data to reflect the rapid response of the transformer's thermal state. The spectral characteristics of partial discharge background noise refer to the frequency distribution characteristics of non-fault partial discharge signals caused by factors such as power grid harmonics and external interference in the transformer operating environment. Its acquisition aims to distinguish real fault signals from environmental noise. Furthermore, calculating the expected release of background gases caused by temperature changes based on the instantaneous rate of change of oil temperature and internal operating information can be understood as utilizing the physical law of gas solubility in oil changing with temperature, combined with information such as the solubility curve and diffusion rate of gases inside the transformer, to predict the expected release of dissolved gases (such as hydrogen, methane, ethane, ethylene, acetylene, etc.) in the transformer oil under the current temperature change trend. Its purpose is to separate the influence of temperature changes on gas concentration from abnormal gas release caused by faults, improving the accuracy of gas analysis. In practical applications, a preset adaptive filter can be understood as a digital filter that can automatically adjust its internal parameters or empirical coefficients according to the characteristics of the input signal. This filter is used to adjust in real time the instantaneous rate of change of oil temperature, the spectral characteristics of partial discharge background noise, and the expected discharge amount. For example, the filter can be a Kalman filter, a least mean square (LMS) algorithm filter, or a recursive least squares (RLS) algorithm filter. By continuously learning and adapting to the dynamic changes in the transformer's operating environment, it optimizes the estimation and prediction of these key parameters, thereby ensuring that the generated expected response parameters can more accurately reflect the normal state of the transformer under the current operating conditions.

[0073] It should be noted that the proposed solution effectively addresses the potential issues of insufficient accuracy and adaptability in the generation of expected response parameters in the basic scheme by incorporating considerations of the instantaneous rate of change of oil temperature, the spectral characteristics of partial discharge background noise, and the expected release of background gas caused by temperature changes, combined with real-time adjustments using a preset adaptive filter. Specifically, the instantaneous rate of change of oil temperature reflects the rapid fluctuations in the transformer's thermal load, while the spectral characteristics of partial discharge background noise help distinguish between environmental interference and internal faults. By calculating the release of background gas caused by temperature changes, normal thermal effects can be effectively distinguished from potential fault gas generation mechanisms. Based on this, the preset adaptive filter can optimize the generation model of expected response parameters in real time according to these dynamic input information, enabling it to dynamically adapt to changes in transformer operating conditions and environmental conditions. It is precisely because of this dynamic and adaptive adjustment mechanism that the generated expected response parameters can more accurately characterize the actual response of the transformer under normal operating conditions, thus providing a more reliable benchmark for subsequent deviation assessments.

[0074] In one embodiment, firstly, oil temperature data is continuously collected at a high sampling rate using a temperature sensor array installed inside the transformer oil tank, and the instantaneous rate of change of oil temperature is calculated using a differential algorithm. Simultaneously, partial discharge signals are collected using a high-frequency current sensor and an ultrasonic sensor, and the collected signals are subjected to Fourier transform to analyze their spectrum in order to identify and extract the spectral characteristics of the partial discharge background noise. Secondly, by combining the solubility curves of dissolved gases (such as hydrogen and methane) in the transformer oil and their diffusion coefficients at different temperatures, as well as the current instantaneous rate of change of oil temperature, the expected release amount of these background gases in the oil under the current temperature change trend is calculated. For example, when the oil temperature rises rapidly, according to Henry's law and the diffusion model, it can be predicted that dissolved gases will accelerate their escape from the oil. Finally, the acquired instantaneous rate of change of oil temperature, the spectral characteristics of the partial discharge background noise, and the calculated expected release amount of background gases are used as inputs and fed into an adaptive model based on a Kalman filter. The Kalman filter continuously updates its internal state estimate and covariance matrix based on the real-time data stream to dynamically adjust the parameters or empirical coefficients used to generate the expected oil temperature, expected gas concentration, and the intensity of the frequency components of the expected partial discharge signal. When an increase in external power grid harmonics is detected, the filter adjusts the weight of the partial discharge background noise accordingly to avoid misclassifying it as an internal fault. Through this real-time adaptive adjustment, the expected response parameters are ultimately generated that highly match the current operating conditions of the transformer.

[0075] In this regard, this application further proposes steps for obtaining the instantaneous rate of change of the transformer oil temperature and the spectral characteristics of the partial discharge background noise, including:

[0076] The current load current and cooling system operating status are obtained based on internal operating information, the ambient temperature is obtained based on external environmental information, and the amplitude of each harmonic current and voltage is obtained based on the power grid operating status.

[0077] To obtain the transformer's own heat dissipation constant and the transformer core's response characteristics to harmonics of different preset frequencies;

[0078] The instantaneous rate of change of transformer oil temperature is obtained by real-time calculation based on the current load current, ambient temperature, cooling system operating status, and heat dissipation constant.

[0079] The spectral characteristics of the partial discharge background noise are obtained by extrapolating the amplitude and response characteristics of each harmonic current and voltage.

[0080] Specifically, the current load current and cooling system operating status can be monitored in real time using current sensors and cooling system status sensors installed inside the transformer. Ambient temperature can be obtained through external environmental sensors. The amplitudes of harmonic currents and voltages can be obtained through a power grid monitoring system or a harmonic analyzer. This information changes in real time, providing dynamic input for subsequent calculations. The transformer's own heat dissipation constant is an inherent parameter characterizing its heat dissipation performance, which can be calibrated using factory test data or historical operating data. The transformer core's response characteristics to harmonics of different preset frequencies reflect the core's magnetization and loss characteristics under the influence of harmonics at different frequencies. This can be obtained through theoretical calculations, simulations, or experimental tests and stored in the system. In practical applications, the instantaneous rate of change of oil temperature is calculated based on a thermodynamic model. This model comprehensively considers the transformer's internal losses, external heat dissipation conditions, and the transformer's own heat dissipation constant. By inputting these parameters in real time, the instantaneous trend of oil temperature change can be accurately calculated. Furthermore, the estimation of the spectral characteristics of partial discharge background noise is based on the influence of harmonic currents and voltages present in the power grid on the transformer core. When harmonic currents and voltages act on the iron core, they induce magnetostriction and eddy current losses, leading to mechanical vibrations and electromagnetic noise. These noises exhibit specific characteristics in the frequency spectrum. By combining the real-time acquired harmonic amplitudes with predetermined iron core response characteristics, the spectral characteristics of the partial discharge background noise caused by power grid harmonics can be calculated, thus distinguishing it from the actual partial discharge signal.

[0081] It is worth noting that the proposed solution refines the acquisition process of the instantaneous rate of change of oil temperature and the spectral characteristics of partial discharge background noise, thereby enabling more accurate generation of expected response parameters corresponding to the transformer's internal operating information. By comprehensively considering load current, ambient temperature, cooling system operating status, and heat dissipation constant, a more accurate transformer thermal model can be established, thus accurately predicting the instantaneous change of oil temperature. Simultaneously, by analyzing the impact of grid harmonics on the core response characteristics, the partial discharge background noise caused by external grid factors can be effectively identified and quantified, avoiding misinterpretation as an internal transformer fault signal. This refined parameter acquisition method provides high-quality input data for the subsequent generation of expected response parameters, thereby improving the accuracy and reliability of the entire monitoring system.

[0082] Specifically, the above calculations, based on the instantaneous rate of change of oil temperature and internal operating information, yield the expected release of background gas from the transformer due to temperature changes, including the following steps:

[0083] The solubility curve and diffusion rate of the background gas in the transformer are obtained based on the internal operating information. The background gas includes at least one of the following: hydrogen, methane, ethane, ethylene, and acetylene.

[0084] Based on the instantaneous rate of change of oil temperature, the solubility curve, and the diffusion rate, the expected release amount caused by the temperature change is obtained.

[0085] The internal operating information refers to real-time data collected by sensors inside the transformer, such as oil temperature, oil pressure, and gas concentration. Background gases refer to various gaseous components dissolved in the transformer insulating oil, which are generated or released during normal operation or when a fault occurs. Specifically, hydrogen, methane, ethane, ethylene, and acetylene are common fault-characteristic gases in transformer oil, and their concentration changes are important indicators for judging internal transformer anomalies. The solubility curve describes the solubility of a specific gas in the insulating oil under different temperature and pressure conditions, i.e., the maximum amount of gas that can dissolve in the oil. The diffusion rate represents the speed at which gas molecules move from high-concentration areas to low-concentration areas in the insulating oil. These parameters are crucial for accurately assessing the amount of background gas released due to temperature changes. Through the above technical solution, the generation process of expected response parameters corresponding to the transformer's internal operating information can be refined and optimized, especially for estimating the amount of background gas released due to temperature changes. This application, by introducing solubility curves and diffusion rates, and combining them with the instantaneous rate of change of oil temperature for calculation, makes the estimation of expected release more accurate, thereby improving the accuracy of transformer operating status assessment. Therefore, in subsequent deviation assessments, it is possible to more effectively identify gas anomalies caused by actual faults rather than normal temperature fluctuations, avoiding false alarms or missed alarms and improving the reliability of intelligent monitoring methods.

[0086] Specifically, the steps described above for evaluating the deviation between internal operating information and expected response parameters to obtain multiple deviation indices include:

[0087] Multiple deviation values ​​were obtained by calculating the internal operating information and the expected response parameters;

[0088] Multiple deviation indices are obtained by calculating percentages based on multiple deviation values ​​and preset standard deviations.

[0089] Internal operating information refers to various parameters collected in real time during the actual operation of the transformer, such as oil temperature, gas concentration, and partial discharge signal strength. Expected response parameters, on the other hand, are the corresponding parameter values ​​that the transformer should have under normal operating conditions, predicted by a model based on the external environment and power grid conditions. Calculating these parameters typically involves comparing each parameter in the internal operating information with its corresponding parameter in the expected response parameters, for example, by subtraction to obtain the difference between each parameter, thus quantifying the difference between the actual operation and the expected state. These differences are called deviations, reflecting the degree of deviation between the transformer's current operating state and the ideal state. After obtaining multiple deviations, percentage calculations are performed based on these deviations and a preset standard deviation to obtain multiple deviation indices. The preset standard deviation can be understood as the allowable fluctuation range or statistical standard deviation of various parameters under normal operating conditions. By calculating the ratio of the deviations to the corresponding preset standard deviations and converting it to a percentage, the deviations of different types and dimensions can be standardized, making them comparable. The resulting deviation indices can intuitively represent the relative degree to which each parameter deviates from the normal range. This allows for the quantification and presentation of the actual deviations of various transformer operating parameters through a standardized deviation index. This percentage-based deviation index not only clearly reflects the relative degree to which each parameter deviates from the normal range, but also, due to its standardized characteristics, enables effective horizontal comparison of the deviations of different physical quantities, greatly improving the accuracy and reliability of anomaly assessment.

[0090] In some embodiments of this application, when evaluating the deviation between the transformer's internal operating information and expected response parameters, it is necessary to calculate multiple deviation differences. Specifically, the steps for calculating multiple deviation differences between the internal operating information and expected response parameters include:

[0091] Obtain the oil temperature from the internal operating information and the expected oil temperature from the expected response parameters;

[0092] The difference between the oil temperature in the internal operating information and the expected oil temperature in the expected response parameters is calculated to obtain the oil temperature deviation difference.

[0093] The difference between the gas concentration in the internal operating information and the expected gas concentration in the expected response parameters is calculated to obtain the gas concentration deviation difference.

[0094] The difference between the intensity of a specific frequency component of the partial discharge signal in the internal operating information and the intensity of the frequency component of the expected partial discharge signal in the expected response parameters is calculated to obtain the deviation difference of the frequency component intensity of the partial discharge signal.

[0095] Multiple deviation values ​​are determined based on the deviation values ​​of oil temperature, gas concentration, and frequency component intensity of the partial discharge signal.

[0096] Specifically, in intelligent monitoring of transformer operating status, to accurately assess its operating condition, it is necessary to quantify the differences between the actual and expected values ​​of several key parameters. Among these, oil temperature, gas concentration, and the intensity of specific frequency components of partial discharge signals in the internal operating information are important indicators reflecting the internal state of the transformer. Expected response parameters provide theoretical or model predictions of these indicators under normal operating conditions. By obtaining the oil temperature from the internal operating information and the expected oil temperature from the expected response parameters, and calculating the difference, the oil temperature deviation difference can be obtained. This difference reflects the deviation between the actual oil temperature and the expected normal oil temperature. Similarly, by obtaining the gas concentration from the internal operating information and the expected gas concentration from the expected response parameters, and calculating the difference, the gas concentration deviation difference can be obtained. This difference reveals abnormalities in the dissolved gas content in the transformer's internal insulating oil. Furthermore, by obtaining the intensity of specific frequency components of the partial discharge signal from the internal operating information and the intensity of the expected frequency components of the partial discharge signal from the expected response parameters, and calculating the difference, the frequency component intensity deviation difference of the partial discharge signal can be obtained. This difference helps identify whether partial discharge phenomena exist inside the transformer and its severity. Finally, these separately calculated oil temperature deviation differences, gas concentration deviation differences, and frequency component intensity deviation differences of partial discharge signals are integrated to determine multiple deviation differences, providing a comprehensive data foundation for subsequent deviation assessment.

[0097] It should be noted that the solution proposed in this application, by calculating the difference between key parameters in the transformer's internal operating information (such as oil temperature, gas concentration, and the intensity of specific frequency components of partial discharge signals) and their corresponding expected response parameters one by one, can precisely quantify the degree of deviation of each indicator. This meticulous calculation method allows anomalies in each key parameter to be identified independently and accurately, avoiding the problem that a single comprehensive indicator may mask local anomalies. It is precisely because of the independent deviation difference calculation for multiple key parameters that subsequent deviation assessments can be based on more comprehensive and specific data, thereby improving the accuracy and reliability of anomaly judgment.

[0098] Specifically, the steps for determining whether a transformer is abnormal include:

[0099] If at least one deviation index continues to exceed the first preset deviation threshold within a preset time, the transformer will be marked as a potential anomaly.

[0100] A pattern recognition algorithm is used to compare the fault problems of transformers marked as potential anomalies with a preset fault feature database to determine whether the transformer has any anomalies.

[0101] The deviation index is a quantitative indicator obtained by evaluating the deviation between the transformer's internal operating information and expected response parameters. It reflects the degree of difference between the transformer's actual operating state and its expected normal state. The first preset deviation threshold is a critical value set based on historical data, expert experience, or industry standards, used to initially screen for potentially abnormal operating states. The preset time refers to the length of time required for the deviation index to continuously exceed the threshold, aiming to avoid misjudgments caused by instantaneous fluctuations. Furthermore, marking a transformer as potentially abnormal means that the system has identified a possible deviation from the normal operating state, requiring deeper analysis. Pattern recognition algorithms are computational methods that can learn and identify specific patterns from data, such as Support Vector Machines (SVM), neural networks, decision trees, or clustering algorithms. This matches the fault characteristics exhibited by potentially abnormal transformers with known fault patterns in a preset fault feature library. The preset fault feature library contains typical deviation index patterns or feature vectors corresponding to various known transformer fault types (such as local overheating, insulation aging, partial discharge, etc.). By comparison, it can be determined whether the current abnormal state of the transformer matches a certain fault pattern in the library, thus ultimately determining whether the transformer is abnormal.

[0102] In some of the embodiments described above in this application, this application further proposes to output early warning information based on multiple deviation indices and a preset fault feature library when an abnormality occurs in the transformer, including:

[0103] The matching degree of the features corresponding to multiple deviation indices is calculated by comparing them with the patterns in the preset fault feature library to obtain multiple target matching degrees. The preset fault feature library includes multiple fault patterns.

[0104] Based on multiple deviation indices and multiple target matching degrees, early warning information is output.

[0105] Specifically, the features corresponding to the deviation index can be understood as the abnormal trend, rate of change, or distribution pattern in a multidimensional space of a specific operating parameter reflected by each deviation index. These patterns are established based on historical data, expert experience, or simulation models and are used to describe the typical deviation of various operating parameters when a specific fault occurs. Matching degree calculation refers to quantifying the similarity or degree of agreement between the features corresponding to the currently observed deviation index and various fault modes in the fault feature library through pattern recognition algorithms, machine learning algorithms, or statistical similarity algorithms. Thus, multiple target matching degrees can be obtained, each representing the degree of agreement between the current transformer operating state and a specific fault mode in the fault feature library. The preset fault feature library can include various fault modes; for example, there are corresponding feature modes for different types of faults such as winding overheating, core overheating, partial discharge, and insulation aging. The solution in this application effectively solves the problem of the lack of specificity in the aforementioned early warning information by introducing a step of calculating the matching degree between the features corresponding to the deviation index and the patterns in the fault feature library. Specifically, when a transformer is judged to have an anomaly, the system no longer simply outputs a general anomaly warning, but further analyzes the features presented by the deviation index that caused the anomaly. These features are input into the matching degree calculation module and compared with a pre-set fault feature library containing various specific fault modes. By calculating the matching degree between each deviation index feature and each fault mode, the system can quantify the degree of correlation between the current abnormal state and each potential fault mode. It is precisely because of this refined matching degree calculation that the system can identify the specific fault mode most likely to cause the current abnormality, thereby providing an accurate basis for subsequent early warning information output.

[0106] The above-mentioned warning information is output based on multiple deviation indices and multiple target matching degrees, including:

[0107] When at least one deviation index continuously exceeds the second preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than the first preset matching degree, an early warning message is output, wherein the early warning message is a reminder to pay attention;

[0108] When multiple deviation indices continuously exceed the third preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than the second preset matching degree, an early warning message is output, wherein the early warning message is a warning reminder;

[0109] When multiple deviation indices continuously exceed the fourth preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than the third preset matching degree, an early warning message is output. The early warning message is a danger reminder. The second preset deviation threshold is less than the third preset deviation threshold, the third preset deviation threshold is less than the fourth preset deviation threshold, the first preset matching degree is less than the second preset matching degree, and the second preset matching degree is less than the third preset matching degree.

[0110] Specifically, this application classifies transformer abnormal states into different risk levels by introducing multi-level preset deviation thresholds (second preset deviation threshold, third preset deviation threshold, and fourth preset deviation threshold) and multi-level preset matching degrees (first preset matching degree, second preset matching degree, and third preset matching degree). The second, third, and fourth preset deviation thresholds are in an increasing relationship, with the second preset deviation threshold being the smallest and the fourth preset deviation threshold being the largest, reflecting a gradual increase in the degree of deviation. Similarly, the first, second, and third preset matching degrees are also in an increasing relationship, reflecting a gradual increase in the fault mode matching degree. When at least one deviation index continuously exceeds the second preset deviation threshold within a preset time, and the target matching degree corresponding to that deviation index is greater than the first preset matching degree, the system will output a "pay attention reminder." This indicates that the transformer may have a minor abnormality or potential risk, requiring initial attention and observation by the operator. When multiple deviation indices continuously exceed the third preset deviation threshold within a preset time, and the target matching degrees corresponding to these deviation indices are greater than the second preset matching degree, the system will output a "warning reminder." This indicates that the transformer anomaly has progressed to a moderate level and may require further inspection or intervention. When multiple deviation indices continuously exceed a fourth preset deviation threshold within a preset time, and the target matching degree corresponding to these deviation indices is greater than a third preset matching degree, the system will output a "danger alert." This indicates that the transformer has a serious anomaly or is about to experience a major fault, requiring immediate emergency measures to prevent equipment damage or accidents. Through the above technical solution, this application provides a more intelligent and refined transformer operating status early warning mechanism, capable of outputting different levels of early warning information based on the degree of deviation between the transformer's internal operating information and expected response parameters, as well as the matching degree with the fault feature database. This allows operators to more accurately judge the severity and urgency of transformer anomalies, thereby taking appropriate countermeasures in a timely manner, effectively avoiding misjudgments or delays caused by ambiguous early warning information, significantly improving the safety and reliability of transformer operation, and optimizing operation and maintenance efficiency.

[0111] See Figure 2 , Figure 2 This is a schematic diagram of an intelligent monitoring system for transformer operating status provided in one embodiment of this application. The intelligent monitoring system 200 for transformer operating status includes:

[0112] The acquisition module 210 is used to acquire the transformer's internal operating information, external environmental information, and power grid operating status.

[0113] The adjustment and generation module 220 is used to generate expected response parameters corresponding to the transformer's internal operating information based on internal operating information, external environmental information, and power grid operating conditions.

[0114] The deviation assessment module 230 is used to assess the deviation between internal operating information and expected response parameters, and obtain multiple deviation indices.

[0115] The judgment module 240 is used to determine whether the transformer is abnormal based on multiple deviation indices and a preset fault feature library.

[0116] The output module 250 is used to output early warning information based on multiple deviation indices and a preset fault feature library when there is an abnormality in the transformer.

[0117] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0118] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0119] The foregoing has provided a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined in this application.

Claims

1. A method for intelligent monitoring of transformer operating status, characterized in that, include: To acquire internal operating information of the transformer, external environmental information, and power grid operating status; Based on the internal operating information, the external environment information, and the power grid operating status, the expected response parameters corresponding to the internal operating information of the transformer are generated. The deviation between the internal operating information and the expected response parameters is evaluated to obtain multiple deviation indices; Based on multiple deviation indices and a preset fault feature library, determine whether the transformer is abnormal; In the event of an abnormality in the transformer, an early warning message is output based on multiple deviation indices and a preset fault feature library.

2. The method according to claim 1, characterized in that, The step of generating expected response parameters corresponding to the internal operating information of the transformer based on the internal operating information, the external environment information, and the power grid operating status includes: Based on the internal operating information, the external environmental information, and the power grid operating status, the instantaneous rate of change of the transformer oil temperature and the spectral characteristics of the partial discharge background noise are obtained. Based on the instantaneous rate of change of the oil temperature and the internal operating information, the expected release amount of background gas from the transformer caused by the temperature change is calculated. The transformer's oil temperature instantaneous change rate, the spectral characteristics of the partial discharge background noise, and the expected release amount are adjusted in real time according to a preset adaptive filter to generate expected response parameters corresponding to the transformer's internal operating information. The preset adaptive filter is used to adjust parameters or empirical coefficients.

3. The method according to claim 2, characterized in that, The process of obtaining the instantaneous rate of change of the transformer oil temperature and the spectral characteristics of the partial discharge background noise based on the internal operating information, the external environmental information, and the power grid operating status includes: The current load current and cooling system operating status are obtained based on the internal operating information, the ambient temperature is obtained based on the external environmental information, and the amplitude of each harmonic current and voltage is obtained based on the power grid operating status. Obtain the heat dissipation constant of the transformer itself and the response characteristics of the transformer core to harmonics of different preset frequencies; The instantaneous rate of change of the transformer oil temperature is obtained by real-time calculation based on the current load current, the ambient temperature, the operating status of the cooling system, and the heat dissipation constant. The spectral characteristics of the partial discharge background noise are calculated based on the amplitude of each harmonic current and voltage and the response characteristics.

4. The method according to claim 2, characterized in that, The calculation based on the instantaneous rate of change of the oil temperature and the internal operating information to obtain the expected release amount of background gas from the transformer due to temperature changes includes: The solubility curve and diffusion rate of the background gas in the transformer are obtained based on the internal operating information, wherein the background gas includes at least one of the following: hydrogen, methane, ethane, ethylene, and acetylene; Based on the instantaneous rate of change of oil temperature, the solubility curve, and the diffusion rate, the expected release amount caused by the temperature change is obtained.

5. The method according to claim 1, characterized in that, The deviation assessment between the internal operating information and the expected response parameters yields multiple deviation indices, including: Multiple deviation values ​​are obtained by calculating the internal operating information and the expected response parameters; Multiple deviation indices are obtained by calculating percentages based on multiple deviation differences and a preset standard deviation.

6. The method according to claim 5, characterized in that, The calculation of the internal operating information and the expected response parameters yields multiple deviation values, including: Obtain the oil temperature from the internal operating information and the expected oil temperature from the expected response parameters; The difference between the oil temperature in the internal operating information and the expected oil temperature in the expected response parameters is calculated to obtain the oil temperature deviation difference. The difference between the gas concentration in the internal operating information and the expected gas concentration in the expected response parameters is calculated to obtain the gas concentration deviation difference. The difference between the intensity of a specific frequency component of the partial discharge signal in the internal operating information and the intensity of the frequency component of the expected partial discharge signal in the expected response parameters is calculated to obtain the deviation difference of the frequency component intensity of the partial discharge signal. Multiple deviation values ​​are determined based on the oil temperature deviation value, the gas concentration deviation value, and the frequency component intensity deviation value of the partial discharge signal.

7. The method according to claim 1, characterized in that, The step of determining whether the transformer is abnormal based on multiple deviation indices and a preset fault feature library includes: If at least one of the deviation indices continues to exceed a first preset deviation threshold within a preset time, the transformer will be marked as a potential anomaly. A pattern recognition algorithm is used to compare the fault problems of the transformer marked as potential anomalies with a preset fault feature database to determine whether the transformer is abnormal.

8. The method according to claim 1, characterized in that, In the event of an abnormality in the transformer, based on multiple deviation indices and a preset fault feature library, an early warning message is output, including: The features corresponding to the multiple deviation indices are respectively matched with the patterns in the preset fault feature library to calculate the matching degree, thereby obtaining multiple target matching degrees. The preset fault feature library includes multiple fault patterns. Based on the multiple deviation indices and multiple target matching degrees, early warning information is output.

9. The method according to claim 8, characterized in that, The step of outputting early warning information based on multiple deviation indices and multiple target matching degrees includes: When at least one of the deviation indices continuously exceeds a second preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than a first preset matching degree, an early warning message is output, wherein the early warning message is a reminder to pay attention; When multiple deviation indices continuously exceed a third preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than a second preset matching degree, an early warning message is output, wherein the early warning message is a warning reminder; When multiple deviation indices continuously exceed a fourth preset deviation threshold within a preset time and the target matching degree corresponding to the deviation index is greater than a third preset matching degree, a warning message is output. The warning message is a danger alert. The second preset deviation threshold is less than the third preset deviation threshold, the third preset deviation threshold is less than the fourth preset deviation threshold, the first preset matching degree is less than the second preset matching degree, and the second preset matching degree is less than the third preset matching degree.

10. An intelligent monitoring system for transformer operating status, characterized in that, include: The acquisition module is used to acquire internal operating information of the transformer, external environmental information, and power grid operating status. An adjustment and generation module is used to generate expected response parameters corresponding to the internal operating information of the transformer based on the internal operating information, the external environment information, and the power grid operating status. The deviation assessment module is used to assess the deviation between the internal operating information and the expected response parameters, and obtain multiple deviation indices. The judgment module is used to determine whether the transformer has any abnormalities based on multiple deviation indices and a preset fault feature library; The output module is used to output early warning information based on multiple deviation indices and a preset fault feature library when the transformer is abnormal.

Images