Main transformer equipment state evaluation and early warning method and system

Abstract

The invention discloses a main transformer equipment state evaluation and early warning method and system, and relates to the technical field of power equipment monitoring and fault diagnosis, and the method comprises the steps: collecting multi-modal data, and carrying out the preprocessing of the multi-modal data; fusing the preprocessed multi-modal data to obtain a fused feature vector; obtaining a health index of the main transformer based on the fusion feature vector; based on the health index of the main transformer, evaluating the health state of the main transformer through quantum correlation analysis; analyzing the health trend of the main transformer through a time sequence based on the health state of the main transformer, and obtaining an early warning signal; and based on the early warning signal, main transformer faults are analyzed through historical working condition data of the main transformer, and a maintenance strategy is formulated. Through multi-modal data fusion and quantum correlation analysis, deeper health state information is provided, potential faults can be found in time, and the operation safety and reliability of equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring and fault diagnosis, and in particular to a method and system for main transformer equipment state assessment and early warning. Background Art

[0002] As a key equipment in the power system, the operating status of the main transformer is directly related to the safety and stability of the entire power grid. With the continuous expansion of the scale of the power system and the continuous improvement of the requirements for power supply reliability, real-time monitoring and status evaluation of the main transformer has become particularly important. In recent years, with the rapid development of sensing technology and data analysis technology, multimodal data acquisition and processing technology has been widely used in main transformer status evaluation. Traditional main transformer status evaluation methods mainly rely on single electrical parameters or mechanical parameters. Although these methods can reflect the operating status of the equipment to a certain extent, due to the lack of comprehensive analysis of multimodal data, they are often unable to comprehensively and accurately evaluate the health status of the equipment.

[0003] The existing main transformer status assessment methods have the following shortcomings: First, the single parameter monitoring method cannot fully reflect the multi-faceted operating status of the main transformer, and it is easy to miss potential fault hazards. For example, relying solely on the monitoring of electrical parameters may not be able to detect mechanical failures or temperature anomalies in a timely manner, and these failures will also have a serious impact on the operating safety of the equipment. Secondly, the existing status assessment methods have deficiencies in data processing and feature extraction, and lack effective multimodal data fusion technology, resulting in low accuracy and reliability of the assessment results. In addition, the existing early warning methods are usually based on simple threshold comparisons, and cannot dynamically adjust the early warning strategy, making it difficult to adapt to complex and changing operating environments. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a main transformer equipment status assessment and early warning method to solve the problems of insufficient multimodal data fusion and low accuracy of assessment results in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a main transformer equipment status assessment and early warning method, which includes collecting multimodal data, preprocessing the multimodal data, fusing the preprocessed multimodal data, and obtaining a fused feature vector; based on the fused feature vector, obtaining a main transformer health index; based on the main transformer health index, evaluating the main transformer health status through quantum correlation analysis; based on the main transformer health status, analyzing the main transformer health trend through time series analysis to obtain an early warning signal; based on the early warning signal, analyzing the main transformer fault through the main transformer historical operating condition data, and formulating a maintenance strategy.

[0008] As a preferred solution of the main transformer equipment status assessment and early warning method of the present invention, wherein: the multimodal data includes transformer temperature data, mechanical vibration data, transformer gas concentration data and electrical fluctuation data;

[0009] The multimodal data preprocessing includes noise removal, outlier processing and data normalization.

[0010] As a preferred solution of the main transformer equipment status assessment and early warning method of the present invention, wherein: the pre-processed multi-modal data is fused to obtain a fused feature vector, and the specific steps are as follows:

[0011] Based on the preprocessed multimodal data, a fully connected layer is used to extract the modal features of each modality and generate a modal feature vector;

[0012] The weight of the modal feature is calculated by a Softmax algorithm, and the weight of the modal feature is normalized to obtain a normalized modal feature weight;

[0013] Generating a gating vector through a gating mechanism based on the normalized modal feature weights to adjust the modal features;

[0014] The adjusted modal features are weighted and fused element by element to obtain a fused feature vector.

[0015] As a preferred solution of the main transformer equipment status assessment and early warning method of the present invention, wherein: the main transformer health index is obtained based on the fusion feature vector, and the specific steps are as follows:

[0016] The fused feature vector is input into the nonlinear weighted Sigmoid function to obtain the health index of the main transformer.

[0017] As a preferred solution of the main transformer equipment status assessment and early warning method of the present invention, wherein: the main transformer health status is assessed by quantum correlation analysis based on the main transformer health index, and the specific steps are as follows:

[0018] Each modal feature is normalized as a quantum state vector, and the modal feature density matrix is ​​constructed by weighting the quantum state vector;

[0019] Calculate quantum correlation through quantum correlation analysis based on modal characteristic density matrix;

[0020] Based on the quantum correlation and the main transformer health index, the main transformer health value Q is calculated;

[0021] Setting a high threshold T based on historical multimodal data high and low threshold T low , evaluate the health status of the main transformer;

[0022] When Q ≥ T high When , it indicates that the main transformer is in a healthy state;

[0023] When Q≤T low When it is on, it means the main transformer is in an unhealthy state and needs to be inspected and repaired immediately;

[0024] When T low <Q<T high When , it indicates that the main transformer is in a sub-healthy state and is under continuous monitoring.

[0025] As a preferred solution of the main transformer equipment status evaluation and early warning method of the present invention, wherein: based on the health status of the main transformer, the health trend of the main transformer is analyzed by time series to obtain an early warning signal, and the specific steps are as follows:

[0026] Based on the health status of the main transformer, the change rate of adjacent time points is calculated through the ratio function to obtain the change rate of the health value of the main transformer;

[0027] Based on the change rate of the health value of the main transformer, the change trend of the health value of the main transformer is obtained through time series analysis;

[0028] Based on the changing trend of the health value of the main transformer, the warning value of the main transformer is calculated by the logistic function;

[0029] The threshold γ is set based on the neutral point of the main transformer health status, and the threshold γ is compared with the main transformer warning value W. t , determine whether to issue a warning signal;

[0030] When W t >γ, it indicates that the health status of the main transformer is deteriorating and an early warning signal is issued;

[0031] When W t When ≤γ, it indicates that the health status of the main transformer is relatively stable.

[0032] As a preferred solution of the main transformer equipment status evaluation and early warning method of the present invention, wherein: based on the early warning signal, the main transformer fault is analyzed through the main transformer historical operating data, and a maintenance strategy is formulated. The specific steps are as follows:

[0033] Establish preset classification rules based on transformer fault type and transformer fault severity;

[0034] Based on the early warning signals, fault classification is performed using preset classification rules;

[0035] Based on the fault classification results, the fault frequency, downtime and maintenance cost are analyzed through the historical operating data of the main transformer;

[0036] Based on the analysis results, the fault types are divided into high priority, medium priority and low priority, and maintenance strategies are formulated for each.

[0037] In the second aspect, the present invention provides a main transformer equipment status assessment and early warning system, including a data acquisition and preprocessing module, a feature fusion module, a health index calculation module, a quantum correlation analysis module, a health trend analysis and early warning module and a fault diagnosis and strategy formulation module; the data acquisition and preprocessing module is used to collect multimodal data and preprocess the multimodal data; the feature fusion module is used to fuse the preprocessed multimodal data to obtain a fused feature vector; the health index calculation module is used to obtain the main transformer health index based on the fused feature vector; the quantum correlation analysis module is used to evaluate the health status of the main transformer through quantum correlation analysis based on the main transformer health index; the health trend analysis and early warning module is used to obtain an early warning signal based on the health status of the main transformer through time series analysis of the main transformer health trend; the fault diagnosis and strategy formulation module is used to analyze the main transformer fault based on the early warning signal and formulate a maintenance strategy through the main transformer historical operating condition data.

[0038] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the main transformer equipment status assessment and early warning method as described in the first aspect of the present invention is implemented.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the main transformer equipment status assessment and early warning method as described in the first aspect of the present invention is implemented.

[0040] The beneficial effects of the present invention are as follows: the present invention realizes the effective fusion of multimodal data through multimodal data fusion, generates a comprehensive feature vector, improves the accuracy and reliability of data fusion, and ensures the accuracy of subsequent health index calculation and status assessment; through quantum correlation analysis, the health status of the main transformer is comprehensively assessed in combination with the health index, the implicit correlation between modal features is revealed, deeper health status information is provided, and the accuracy and reliability of the assessment results are significantly improved, which is helpful to timely discover potential faults and improve the operating safety and reliability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0042] Figure 1 This is a flow chart of the main transformer equipment status assessment and early warning method in Example 1.

[0043] Figure 2 This is a system diagram of the main transformer equipment status assessment and early warning system in Example 1. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0045] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a main transformer equipment status assessment and early warning method, comprising the following steps:

[0046] S1. The multimodal data includes transformer temperature data, mechanical vibration data, transformer gas concentration data and electrical fluctuation data.

[0047] S1.2. The preprocessing of multimodal data includes noise removal, outlier processing and data normalization.

[0048] It should be noted that noise removal: filtering algorithms are used to eliminate random interference and high-frequency noise in multimodal data to ensure the smoothness and consistency of the data, thereby improving the accuracy and reliability of subsequent analysis;

[0049] Outlier processing: Use statistical methods to identify and remove outliers in multimodal data to ensure the rationality and credibility of the data, avoid the interference of outliers on subsequent analysis results, and improve the overall quality of the data;

[0050] Data normalization: Convert multimodal data to the same scale range, eliminate the dimensional differences between different modal data, and ensure the comparability and consistency of each modal data during the fusion and analysis process, thereby improving the accuracy of feature extraction and fusion.

[0051] S2. Fuse the preprocessed multimodal data to obtain a fused feature vector.

[0052] S2.1. Based on the preprocessed multimodal data, use the fully connected layer to extract the modal features of each modality and generate a modal feature vector.

[0053] Specifically, the preprocessed multimodal data is input into the fully connected layer, and the deep features of each modality are extracted through linear transformation and activation function, and finally the modal feature vector is generated.

[0054] S2.2. Calculate the weight of the modal feature by using the Softmax algorithm, and normalize the weight of the modal feature to obtain the normalized modal feature weight.

[0055] It should be noted that the normalized modal feature weight is calculated by the Softmax algorithm, and the expression is:

[0056]

[0057] Among them, α i is the normalized weight of the i-th modal feature, F i is the characteristic norm of the ith mode, F j is the norm of the jth modal feature, n is the total number of modal features, i is the index variable of a modal feature, and j is the index variable of another modal feature.

[0058] S2.3. Generate a gating vector through a gating mechanism based on the normalized modal feature weight to adjust the modal feature.

[0059] It should be noted that the gating vector G is generated by the gating mechanism i , the expression is:

[0060] G i =φ(N·E i + b);

[0061] Where N is the weight matrix of the gating mechanism, and b is the bias vector;

[0062] Based on the gate vector G i Through element-by-element multiplication (Hadamard product), the adjusted modal features are obtained.

[0063] S2.4. Perform element-by-element weighted fusion on the adjusted modal features to obtain a fused feature vector.

[0064] It should be noted that the fused feature vector is obtained by element-by-element weighted fusion, and the expression is:

[0065]

[0066] Among them, Z is the fused feature vector, G i is the gate vector, E i is the ith modal eigenvector, Represents element-wise multiplication.

[0067] S3. Obtain the health index of the main transformer based on the fused feature vector.

[0068] S3.1. Input the fused feature vector into the nonlinear weighted Sigmoid function to obtain the health index of the main transformer.

[0069] It should be noted that the main transformer health index is obtained through the nonlinear weighted Sigmoid function, and the expression is:

[0070]

[0071] Where B is the health index of the main transformer, λ i is the weight coefficient of the i-th modal feature, β i is the scaling factor of the ith modal feature, Z i is the eigenvalue of the i-th mode in the fused eigenvector, μ i is the mean of the i-th modal feature, σ i is the standard deviation of the i-th modal feature, θ i is the offset of the i-th modal feature, i is the index variable of the modal feature, and n is the total number of modal features.

[0072] It should also be noted that the expression calculation process is as follows:

[0073] Each modal feature is standardized, and the standardized feature value is input into the hyperbolic tangent function. The hyperbolic tangent value of each modal feature is multiplied by the corresponding weight coefficient, and the offset is added. All modal features are weighted summed, and the summation result is input into the Sigmoid function to obtain the health index of the main transformer.

[0074] S4. Based on the main transformer health index, the health status of the main transformer is evaluated through quantum correlation analysis.

[0075] S4.1. Each modal feature is normalized and used as a quantum state vector. The modal feature density matrix is ​​weighted by the quantum state vector.

[0076] S4.2. Calculate the quantum correlation degree through quantum correlation analysis based on the modal characteristic density matrix.

[0077] It should be noted that the quantum correlation degree is calculated by quantum correlation analysis, and the expression is:

[0078]

[0079] Among them, S(ρ) is the quantum correlation, ρ is the modal characteristic density matrix, η i is the i-th eigenvalue of the modal feature density matrix ρ, i is the index variable of the modal feature, and n is the total number of modal features.

[0080] It should be noted that the modal characteristic density matrix ρ is expressed as:

[0081]

[0082] Among them, |ψ i > is the quantum state vector corresponding to the i-th modal feature, <ψ i | is the conjugate transpose of the quantum state vector of the i-th modal feature.

[0083] S4.3. Calculate the main transformer health value Q based on the quantum correlation and the main transformer health index.

[0084] It should be noted that the expression for calculating the health value of the main transformer is:

[0085]

[0086] Where Q is the health value of the main transformer, c is the weight coefficient of the health index B of the main transformer, is the weight coefficient of the quantum correlation S(ρ).

[0087] It should be noted that quantum correlation analysis is obtained by combining the modal characteristic density matrix and the quantum state vector;

[0088] Quantum correlation analysis can reveal implicit correlations between modal features and provide deeper health status information, thereby improving the accuracy and reliability of assessment results.

[0089] S4.4. Setting a high threshold T based on historical multimodal data high and low threshold T low , evaluate the health status of the main transformer;

[0090] When Q ≥ T high When , it indicates that the main transformer is in a healthy state;

[0091] When Q≤T lowWhen the main transformer is in an unhealthy state, it should be inspected and repaired immediately;

[0092] When T low <Q<T high When , it indicates that the main transformer is in a sub-healthy state and is under continuous monitoring.

[0093] It should be noted that the high threshold T is set based on historical multimodal data. high and low threshold T low , the specific steps are as follows,

[0094] By analyzing historical multimodal data through cluster analysis, we can find out the health value range of the main transformer with good health status and the health value range of the main transformer with poor health status, and set the high threshold T high and low threshold T low .

[0095] S5. Based on the health status of the main transformer, the health trend of the main transformer is analyzed through time series to obtain early warning signals.

[0096] S5.1. Based on the health status of the main transformer, the change rate of adjacent time points is calculated by a ratio function to obtain the change rate of the health value of the main transformer.

[0097] It should be noted that the rate of change of adjacent time points is calculated by the ratio function, and the expression is:

[0098]

[0099] Among them, R represents the change rate of the health value of the main transformer, Q t represents the health value of the main transformer at time t, Q t-1 Represents the health value of the main transformer at time t-1, where t is the current time point.

[0100] S5.2. Obtain the changing trend of the health value of the main transformer through time series analysis based on the changing rate of the health value of the main transformer.

[0101] It should be noted that the change trend of the health value of the main transformer is obtained through time series analysis, and the expression is:

[0102]

[0103] Among them, H t is the trend of the health value of the main transformer at time t, C t is the cumulative effect of the rate of change of health value from the initial moment to moment t, R k is the rate of change of the health value of the main transformer at time k, where k is the index from the initial time to the current time point.

[0104] S5.3. Based on the changing trend of the health value of the main transformer, the warning value of the main transformer is calculated by the logistic function.

[0105] It should be noted that the main transformer warning value is calculated by the logistic function, and the expression is:

[0106]

[0107] Among them, W t is the main transformer warning value, is the reference value, r is the current time point, and α is the proportional coefficient.

[0108] S5.4, based on the neutral point of the main transformer health status, set the threshold γ, and compare the threshold γ with the main transformer warning value W t , determine whether to issue a warning signal;

[0109] When W t >γ, it indicates that the health status of the main transformer is deteriorating and an early warning signal is issued;

[0110] When W t When ≤γ, it indicates that the health status of the main transformer is relatively stable.

[0111] It should be noted that the neutral point of the health status of the main transformer, that is, the health value range under normal operating conditions, is determined by analyzing the historical multimodal data and health values ​​through statistical methods, and then a reasonable threshold γ is set based on the neutral point.

[0112] S6. Based on the early warning signal, analyze the main transformer fault through the historical operating data of the main transformer and formulate a maintenance strategy.

[0113] S6.1. Establish preset classification rules based on transformer fault type and transformer fault severity.

[0114] S6.2. Based on the early warning signal, fault classification is performed using preset classification rules.

[0115] S6.3. Based on the fault classification results, the fault frequency, downtime and maintenance cost are analyzed through the historical operating data of the main transformer.

[0116] It should be noted that the historical operating data of the main transformer includes maintenance records, fault records, operation data and maintenance data.

[0117] S6.4. Based on the analysis results, the fault types are classified into high priority, medium priority and low priority, and maintenance strategies are formulated for each.

[0118] It should be noted that maintenance strategies are formulated based on high priority, medium priority and low priority, as follows:

[0119] High priority: immediately arrange for professional personnel to conduct detailed inspection and repair, and replace the faulty parts if necessary;

[0120] Medium priority: Perform regular inspections and maintenance, record inspection results, and monitor fault development;

[0121] Low priority: Check as part of routine maintenance, record findings, and keep an eye on it.

[0122] This embodiment also provides a main transformer equipment status assessment and early warning system, including: a data acquisition and preprocessing module, a feature fusion module, a health index calculation module, a quantum correlation analysis module, a health trend analysis and early warning module, and a fault diagnosis and strategy formulation module;

[0123] Data acquisition and preprocessing module, used to acquire multimodal data and preprocess the multimodal data;

[0124] The feature fusion module is used to fuse the preprocessed multimodal data to obtain a fused feature vector;

[0125] A health index calculation module is used to obtain the health index of the main transformer based on the fused feature vector;

[0126] A quantum correlation analysis module is used to evaluate the health status of the main transformer through quantum correlation analysis based on the health index of the main transformer;

[0127] The health trend analysis and early warning module is used to analyze the health trend of the main transformer through time series based on the health status of the main transformer and obtain early warning signals;

[0128] The fault diagnosis and strategy formulation module is used to analyze the main transformer faults and formulate maintenance strategies based on the early warning signals and the historical operating data of the main transformer.

[0129] This embodiment also provides a computer device, which is suitable for the main transformer equipment status assessment and early warning method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the main transformer equipment status assessment and early warning method proposed in the above embodiment.

[0130] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0131] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the main transformer equipment status assessment and early warning method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0132] In summary, the present invention achieves effective fusion of multimodal data through a multimodal data fusion step, generates a comprehensive feature vector, improves the accuracy and reliability of data fusion, and ensures the accuracy of subsequent health index calculation and status assessment; through a quantum correlation analysis step, the health status of the main transformer is comprehensively assessed in combination with the health index, the implicit correlation between modal features is revealed, deeper health status information is provided, and the accuracy and reliability of the assessment results are significantly improved, which is helpful to timely discover potential faults and improve the operating safety and reliability of the equipment.

[0133] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A main transformer equipment status assessment and early warning method, characterized in that: include, Collect multimodal data and preprocess the multimodal data; Fuse the preprocessed multimodal data to obtain a fused feature vector; Based on the fused feature vector, the health index of the main transformer is obtained; Based on the main transformer health index, the health status of the main transformer is evaluated through quantum correlation analysis; Based on the health status of the main transformer, the health trend of the main transformer is analyzed through time series to obtain early warning signals; Based on the early warning signal and the historical operating data of the main transformer, the main transformer fault is analyzed and a maintenance strategy is formulated.

2. The main transformer equipment status assessment and early warning method according to claim 1, characterized in that: The multimodal data includes transformer temperature data, mechanical vibration data, transformer gas concentration data and electrical fluctuation data; The multimodal data preprocessing includes noise removal, outlier processing and data normalization.

3. The main transformer equipment status assessment and early warning method according to claim 2 is characterized in that: The pre-processed multi-modal data is fused to obtain a fused feature vector. The specific steps are as follows: Based on the preprocessed multimodal data, the modal features of each modality are extracted using a fully connected layer to generate a modal feature vector; The weight of the modal feature is calculated by a Softmax algorithm, and the weight of the modal feature is normalized to obtain a normalized modal feature weight; Generating a gating vector through a gating mechanism based on the normalized modal feature weights to adjust the modal features; The adjusted modal features are weighted and fused element by element to obtain a fused feature vector.

4. The main transformer equipment status assessment and early warning method according to claim 3 is characterized in that: The main transformer health index is obtained based on the fused feature vector. The specific steps are as follows: The fused feature vector is input into the nonlinear weighted Sigmoid function to obtain the health index of the main transformer.

5. The main transformer equipment status assessment and early warning method according to claim 4 is characterized in that: The method of evaluating the health status of the main transformer by quantum correlation analysis based on the health index of the main transformer is as follows: Each modal feature is normalized as a quantum state vector, and the modal feature density matrix is ​​constructed by weighting the quantum state vector; Calculate quantum correlation through quantum correlation analysis based on modal characteristic density matrix; Based on the quantum correlation and the main transformer health index, the main transformer health value Q is calculated; Setting a high threshold T based on historical multimodal data high and low threshold T low , evaluate the health status of the main transformer; When Q ≥ T high When , it indicates that the main transformer is in a healthy state; When Q≤T low When it is on, it means the main transformer is in an unhealthy state and needs to be inspected and repaired immediately; When T low <Q<T high When , it indicates that the main transformer is in a sub-healthy state and is under continuous monitoring.

6. The main transformer equipment status assessment and early warning method according to claim 5, characterized in that: Based on the health status of the main transformer, the health trend of the main transformer is analyzed through time series to obtain the early warning signal. The specific steps are as follows: Based on the health status of the main transformer, the change rate of adjacent time points is calculated through the ratio function to obtain the change rate of the health value of the main transformer; Based on the change rate of the health value of the main transformer, the change trend of the health value of the main transformer is obtained through time series analysis; Based on the changing trend of the health value of the main transformer, the warning value of the main transformer is calculated by the logistic function; The threshold γ is set based on the neutral point of the main transformer health status, and the threshold γ is compared with the main transformer warning value W. t , determine whether to issue a warning signal; When W t >γ, it indicates that the health status of the main transformer is deteriorating and an early warning signal is issued; When W t When ≤γ, it indicates that the health status of the main transformer is relatively stable.

7. The main transformer equipment status assessment and early warning method according to claim 6, characterized in that: Based on the early warning signal, the main transformer fault is analyzed through the historical operating data of the main transformer, and a maintenance strategy is formulated. The specific steps are as follows: Establish preset classification rules based on transformer fault type and transformer fault severity; Based on the early warning signals, fault classification is performed using preset classification rules; Based on the fault classification results, the fault frequency, downtime and maintenance cost are analyzed through the historical operating data of the main transformer; Based on the analysis results, the fault types are divided into high priority, medium priority and low priority, and maintenance strategies are formulated for each.

8. A main transformer equipment status assessment and early warning system, based on the main transformer equipment status assessment and early warning method according to any one of claims 1 to 7, characterized in that: Including data collection and preprocessing module, feature fusion module, health index calculation module, quantum correlation analysis module, health trend analysis and early warning module and fault diagnosis and strategy formulation module; Data acquisition and preprocessing module, used to acquire multimodal data and preprocess the multimodal data; The feature fusion module is used to fuse the preprocessed multimodal data to obtain a fused feature vector; A health index calculation module is used to obtain the health index of the main transformer based on the fused feature vector; A quantum correlation analysis module is used to evaluate the health status of the main transformer through quantum correlation analysis based on the health index of the main transformer; The health trend analysis and early warning module is used to analyze the health trend of the main transformer through time series based on the health status of the main transformer and obtain early warning signals; The fault diagnosis and strategy formulation module is used to analyze the main transformer faults and formulate maintenance strategies based on the early warning signals and the historical operating data of the main transformer.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the main transformer equipment status assessment and early warning method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the main transformer equipment status assessment and early warning method described in any one of claims 1 to 7 are implemented.

Images