A substation equipment state multi-parameter online real-time monitoring method and system

Abstract

This invention relates to the field of substation monitoring technology, and discloses a method and system for online real-time monitoring of multiple parameters of substation equipment status. The method includes: time-scale alignment of electrical, mechanical, and thermal parameters of substation equipment to obtain a synchronous multi-parameter data stream; determining the current operating mode and identifying the dominant parameters; mapping the dominant parameters to a pre-set knowledge base to obtain related parameters, and coupling and converging them to obtain a monitoring focus parameter group; evaluating status consistency characteristics based on historical stable operating characteristics; adaptively modifying the judgment rules of substation equipment based on real-time operating information and status consistency characteristics to obtain dynamic monitoring rules; and performing coordination diagnosis on status consistency characteristics based on dynamic monitoring rules to obtain multi-parameter coordination status conclusions. This invention can improve the efficiency of online real-time monitoring of multiple parameters of substation equipment status.

Description

Technical Field

[0001] This invention relates to the field of substation monitoring technology, and in particular to a method and system for online real-time monitoring of multiple parameters of substation equipment status. Background Technology

[0002] In existing substation equipment condition monitoring, the acquisition of multiple parameters often suffers from inconsistent time scales. Time deviations in electrical, mechanical, and thermal parameters lead to fragmented data correlations, failing to accurately reflect the intrinsic relationships of equipment operating status. Furthermore, traditional monitoring methods do not incorporate parameter screening based on the actual operating modes of the equipment, resulting in significant interference from redundant data and inaccurate identification of core parameters. This leads to low effective utilization of monitoring data and makes it difficult to support accurate condition assessments.

[0003] Traditional monitoring judgment rules are mostly fixed and cannot be dynamically adjusted according to real-time changes in equipment operating conditions and parameter fluctuation characteristics. They lack analysis of the coordinated fluctuation patterns of multiple parameters, and the status diagnosis lacks comprehensiveness and adaptability, making it easy to make misjudgments or omissions. They are difficult to meet the real-time and reliability requirements of equipment operation and maintenance. Therefore, how to improve the efficiency of online real-time monitoring of multiple parameters of substation equipment status has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for online real-time monitoring of multiple parameters of substation equipment status to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for online real-time monitoring of multiple parameters of substation equipment status, comprising:

[0006] S1. Time-scale alignment is performed on the electrical, mechanical, and thermal parameters of the substation equipment to obtain the synchronous multi-parameter data stream of the substation equipment;

[0007] S2. Based on the synchronous multi-parameter data stream, determine the current operating mode of the substation equipment, and based on the current operating mode, identify the core parameters of the synchronous multi-parameter data stream to obtain the dominant parameters of the current operating mode.

[0008] S3. Map the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and couple and converge the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment;

[0009] S4. Based on the historical stable operating characteristics of the monitoring focus parameter group, perform a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment to obtain the state consistency characteristics of the substation equipment.

[0010] S5. Based on the real-time operating condition information of the substation equipment and the state consistency characteristics, the judgment rules of the substation equipment are adaptively modified to obtain the dynamic monitoring rules of the substation equipment.

[0011] S6. Based on the dynamic monitoring rules, perform coordination diagnosis on the state consistency characteristics to obtain the multi-parameter coordination state conclusion of the substation equipment.

[0012] In a preferred embodiment, the step of time-scale aligning the electrical, mechanical, and thermal parameters of the substation equipment to obtain a synchronous multi-parameter data stream for the substation equipment includes:

[0013] Receive clock signals from a unified clock source within the substation to generate a time synchronization reference for the substation;

[0014] Based on the time synchronization reference, the electrical, mechanical and thermal parameters of the substation equipment are collected synchronously to obtain the original parameter data of the substation equipment;

[0015] Eliminate the timescale deviation between acquisition times in the original parameter data to obtain unified timescale parameter data for the substation equipment;

[0016] By binding the electrical, mechanical, and thermal parameters corresponding to the same time point in the unified time-scaled parameter data, a synchronous multi-parameter data stream of the substation equipment is obtained.

[0017] In a preferred embodiment, the step of determining the current operating mode of the substation equipment based on the synchronous multi-parameter data stream, and identifying core parameters of the synchronous multi-parameter data stream based on the current operating mode to obtain the dominant parameters of the current operating mode, includes:

[0018] Extract the runtime characteristic information from the synchronous multi-parameter data stream;

[0019] The operating characteristic information is compared with a predefined operating mode characteristic library to obtain the current operating mode of the substation equipment;

[0020] Based on the current operating mode, parameter filtering is performed on the synchronous multi-parameter data stream to obtain the mode-related parameter set of the synchronous multi-parameter data stream;

[0021] An association matrix is ​​constructed from the pattern-related parameter set to obtain the parameter coupling strength matrix of the pattern-related parameter set;

[0022] The principal component contribution rate of the parametric coupling strength matrix is ​​calculated to obtain the parametric contribution degree of the parametric coupling strength matrix.

[0023] The contribution of the parameters is used to select characteristic parameters to obtain the dominant parameters of the current operating mode.

[0024] In a preferred embodiment, the formula for calculating the parameter contribution is as follows:

[0025] ;

[0026] In the formula, For the first The contribution of each parameter The total number of eigenvalues ​​in the parametric coupling strength matrix. The first in the parametric coupling strength matrix 1 eigenvalue, The first in the parametric coupling strength matrix 1 eigenvalue, For the first in the running mode feature library The standard deviation of a parameter across different operating modes In the current operating mode, the first The standard deviation within each parameter These are the preset component variance weighting coefficients. The preset pattern discrimination weight coefficient.

[0027] In a preferred embodiment, mapping the dominant parameter to a pre-set equipment operation mechanism knowledge base to obtain associated parameters of the dominant parameter, and coupling and converging the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment, includes:

[0028] The dominant parameter is matched and queried with a pre-set equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter;

[0029] The correlation relationships of the correlation parameters are parsed to obtain the direct and indirect correlation parameters of the correlation parameters;

[0030] Based on the correlation strength between the directly related parameters, the indirectly related parameters, and the dominant parameters, the influence weights of the dominant parameters, the directly related parameters, and the indirectly related parameters are configured to obtain the weighted parameter set of the substation equipment.

[0031] The weighted parameter set is optimized by feature parameter fusion to obtain the monitoring focus parameter group of the substation equipment.

[0032] In a preferred embodiment, the step of performing a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment, based on the historical stable operating characteristics of the monitoring focus parameter group, to obtain the state consistency characteristics of the substation equipment includes:

[0033] Obtain the historical stable operating characteristics of the monitoring focus parameter group;

[0034] Based on the historical stable operation characteristics, dynamic offset identification is performed on the monitoring focus parameter group at the current moment to obtain the offset feature set of the substation equipment;

[0035] Based on the offset feature set, the offset trend correlation analysis is performed on the monitoring focus parameter group at the current moment to obtain the cooperative fluctuation mode of the substation equipment;

[0036] The time-domain features of the cooperative fluctuation mode are reconstructed to obtain the cooperative feature sequence of the substation equipment.

[0037] The coordination feature sequence is evaluated to obtain the state consistency features of the substation equipment.

[0038] In a preferred embodiment, the step of performing offset trend correlation analysis on the monitoring focus parameter group at the current moment based on the offset feature set to obtain the cooperative fluctuation mode of the substation equipment includes:

[0039] The offset feature set is deconstructed by trend component analysis to obtain the long-term trend component and short-term fluctuation component of the offset feature set.

[0040] The long-term trend components are subjected to eigenvector decomposition to construct the trend correlation matrix of the long-term trend components;

[0041] Based on the trend correlation matrix, principal component features are extracted to assess the consistency and divergence of the long-term trend components, thereby obtaining the trend coordination features of the substation equipment.

[0042] Wave coupling analysis is performed on the phase and amplitude information of the short-term wave components to obtain the coupling characteristics of the short-term wave components;

[0043] The trend coordination feature and the coupling feature are integrated into the coordination fluctuation mode of the substation equipment.

[0044] In a preferred embodiment, the step of adaptively modifying the judgment rules for the substation equipment based on the real-time operating condition information and the state consistency characteristics to obtain the dynamic monitoring rules for the substation equipment includes:

[0045] The real-time operating condition information of the substation equipment is correlated with the state consistency feature in a multi-dimensional way to obtain the operating condition-state correlation mapping table of the substation equipment.

[0046] Based on the operating condition-state association mapping table, the condition thresholds in the judgment rules of the substation equipment are adaptively adjusted to obtain the threshold optimization rules of the substation equipment.

[0047] Based on the temporal change pattern of the state consistency characteristics, the triggering logic of the threshold optimization rule is optimized to obtain the logic optimization rule of the substation equipment.

[0048] The decision logic integration of the aforementioned logic optimization rules yields the dynamic monitoring rules for the substation equipment.

[0049] In a preferred embodiment, the step of performing a coordination diagnosis on the state consistency characteristics based on the dynamic monitoring rules to obtain a multi-parameter coordination state conclusion for the substation equipment includes:

[0050] By performing rule matching and reasoning between the dynamic monitoring rules and the state consistency features, a preliminary diagnostic conclusion set for the substation equipment is obtained.

[0051] The preliminary diagnostic conclusion set is subjected to conflict resolution to obtain the diagnostic conclusion sequence of the substation equipment;

[0052] The evolution trend of the diagnostic conclusion sequence and the state consistency characteristics is used to determine the coordinated state, thereby obtaining the multi-parameter coordinated state conclusion of the substation equipment.

[0053] To address the aforementioned problems, the present invention also provides an online real-time monitoring system for multiple parameters of substation equipment status, the system comprising:

[0054] The time-stamp alignment module is used to time-stamp align the electrical, mechanical, and thermal parameters of the substation equipment to obtain the synchronous multi-parameter data stream of the substation equipment;

[0055] The pattern recognition and parameter extraction module is used to determine the current operating mode of the substation equipment based on the synchronous multi-parameter data stream, and to identify the core parameters of the synchronous multi-parameter data stream based on the current operating mode to obtain the dominant parameters of the current operating mode.

[0056] The focus parameter aggregation module is used to map the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and couple and aggregate the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment.

[0057] The collaborative evaluation module is used to perform a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment based on the historical stable operating characteristics of the monitoring focus parameter group, so as to obtain the state consistency characteristics of the substation equipment.

[0058] The dynamic rule generation module is used to adaptively modify the judgment rules of the substation equipment based on the real-time operating condition information of the substation equipment and the state consistency characteristics, so as to obtain the dynamic monitoring rules of the substation equipment.

[0059] The coordination status diagnosis module is used to perform coordination diagnosis on the status consistency characteristics based on the dynamic monitoring rules, and obtain the multi-parameter coordination status conclusion of the substation equipment.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] 1. This invention aligns electrical, mechanical, and thermal parameters with time scales to construct a synchronous multi-parameter data stream, ensuring the temporal consistency and correlation of multi-dimensional data and laying a solid foundation for subsequent analysis. Based on the current operating mode of the equipment, core parameters are identified, and dominant parameters are accurately selected by combining parameter coupling strength and mode distinguishability. Then, related parameters are mapped and coupled through a knowledge base of the equipment's operating mechanism, forming a monitoring focus parameter group that concentrates key information, significantly improving the relevance and effective utilization of monitoring data.

[0062] 2. This invention uses historical stable operating characteristics as a benchmark for fluctuation coordination assessment, accurately capturing the coordinated fluctuation patterns and state consistency characteristics of parameters. By combining real-time operating information with dynamically revised monitoring rules, a dynamic monitoring rule system adapted to changes in equipment operation is constructed, enabling multi-parameter coordination diagnosis and comprehensive and accurate output of equipment status conclusions. This technology significantly improves the real-time performance, accuracy, and adaptability of substation equipment status monitoring, providing strong support for reliable equipment operation and maintenance. Attached Figure Description

[0063] Figure 1 This is a flowchart illustrating a method for online real-time monitoring of multiple parameters of substation equipment status according to an embodiment of the present invention.

[0064] Figure 2 This is a functional block diagram of a multi-parameter online real-time monitoring system for substation equipment status provided in an embodiment of the present invention;

[0065] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0066] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0067] This application provides a method for online real-time monitoring of multiple parameters of substation equipment status. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for online real-time monitoring of multiple parameters of substation equipment status can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides 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.

[0068] Reference Figure 1 The diagram shown is a flowchart illustrating a method for online real-time monitoring of multiple parameters of substation equipment status according to an embodiment of the present invention. In this embodiment, the method for online real-time monitoring of multiple parameters of substation equipment status includes:

[0069] S1. Time-scale alignment is performed on the electrical, mechanical, and thermal parameters of the substation equipment to obtain the synchronous multi-parameter data stream of the substation equipment;

[0070] In this embodiment of the invention, the step of time-aligning the electrical, mechanical, and thermal parameters of the substation equipment to obtain a synchronous multi-parameter data stream of the substation equipment includes:

[0071] Receive clock signals from a unified clock source within the substation to generate a time synchronization reference for the substation;

[0072] Based on the time synchronization reference, the electrical, mechanical and thermal parameters of the substation equipment are collected synchronously to obtain the original parameter data of the substation equipment;

[0073] Eliminate the timescale deviation between acquisition times in the original parameter data to obtain unified timescale parameter data for the substation equipment;

[0074] By binding the electrical, mechanical, and thermal parameters corresponding to the same time point in the unified time-scaled parameter data, a synchronous multi-parameter data stream of the substation equipment is obtained.

[0075] A stable communication connection is established with the unified clock source in the substation through a dedicated clock receiving module. The module continuously receives the standard time signal sent by the clock source. This signal contains precise time information at the year, month, day, hour, minute, second, and millisecond level. The received time signal is shaped to remove interference noise mixed in during transmission. Then, timing calibration is performed to ensure the stability of the signal. Finally, a time synchronization reference is formed that is followed by all parameter acquisition devices in the entire substation.

[0076] All parameter acquisition devices are bound to the generated time synchronization reference. The electrical, mechanical, and thermal parameter acquisition devices strictly follow the timing requirements specified by the time synchronization reference and synchronously start the acquisition action within the same time interval. The electrical parameter acquisition device collects relevant data such as voltage and current of the equipment, the mechanical parameter acquisition device collects relevant data such as vibration and displacement of the equipment, and the thermal parameter acquisition device collects relevant data such as temperature and humidity of the equipment. During the acquisition process, the acquisition time of each set of data is recorded synchronously. All the acquired parameter data and corresponding acquisition time information are stored together to form the original parameter data of the substation equipment.

[0077] The acquisition time stamps for each set of electrical, mechanical, and thermal parameters in the original parameter data are extracted one by one. These time stamps are then compared with the time synchronization benchmark to determine the specific deviation of the acquisition time of each set of parameter data relative to the benchmark time. Based on the obtained deviation values, the time stamps of each set of parameter data are adjusted accordingly. The acquisition times of all parameter data are uniformly calibrated to the standard time point corresponding to the time synchronization benchmark, thus completely eliminating the time scale differences between different parameters and obtaining uniform time-scaled parameter data.

[0078] Based on the time scale of the time synchronization benchmark, electrical, mechanical, and thermal parameter data with completely consistent time stamps are sequentially selected from the unified time-scale parameter data. Through a data association and binding mechanism, the three types of parameter data at the same time point are logically associated and physically integrated, so that the three types of parameter data form a complete and indivisible data unit. Each data unit clearly corresponds to a unique time point. Then, the parameter data units corresponding to all time points are arranged in chronological order to obtain the synchronous multi-parameter data stream of the substation equipment.

[0079] The beneficial effects are that by establishing a unified time synchronization benchmark and completing the time scale alignment and binding of multiple parameters, the high consistency and correlation of electrical, mechanical and thermal parameter data in the time dimension are ensured, avoiding data fragmentation caused by time scale deviation. This enables the synchronous multi-parameter data stream to truly reflect the comprehensive operating status of the equipment at the same moment, providing a reliable and accurate data foundation for subsequent accurate identification of dominant parameters, operation mode analysis and equipment status assessment.

[0080] S2. Based on the synchronous multi-parameter data stream, determine the current operating mode of the substation equipment, and based on the current operating mode, identify the core parameters of the synchronous multi-parameter data stream to obtain the dominant parameters of the current operating mode.

[0081] In this embodiment of the invention, the step of determining the current operating mode of the substation equipment based on the synchronous multi-parameter data stream, and identifying core parameters of the synchronous multi-parameter data stream based on the current operating mode to obtain the dominant parameters of the current operating mode, includes:

[0082] Extract the runtime characteristic information from the synchronous multi-parameter data stream;

[0083] The operating characteristic information is compared with a predefined operating mode characteristic library to obtain the current operating mode of the substation equipment;

[0084] Based on the current operating mode, parameter filtering is performed on the synchronous multi-parameter data stream to obtain the mode-related parameter set of the synchronous multi-parameter data stream;

[0085] An association matrix is ​​constructed from the pattern-related parameter set to obtain the parameter coupling strength matrix of the pattern-related parameter set;

[0086] The principal component contribution rate of the parametric coupling strength matrix is ​​calculated to obtain the parametric contribution degree of the parametric coupling strength matrix.

[0087] The contribution of the parameters is used to select characteristic parameters to obtain the dominant parameters of the current operating mode.

[0088] The formula for calculating the contribution of the parameter is as follows:

[0089] ;

[0090] In the formula, For the first The contribution of each parameter The total number of eigenvalues ​​in the parametric coupling strength matrix. The first in the parametric coupling strength matrix 1 eigenvalue, The first in the parametric coupling strength matrix 1 eigenvalue, For the first in the running mode feature library The standard deviation of a parameter across different operating modes In the current operating mode, the first The standard deviation within each parameter These are the preset component variance weighting coefficients. The preset pattern discrimination weight coefficient.

[0091] The synchronous multi-parameter data stream contains electrical, mechanical, and thermal parameters bound to the same point in time. It is divided into time periods according to fixed time intervals. Within each time period, the bound data of the three types of parameters are analyzed in groups. The stream records in detail the changing trends of electrical parameters, such as rising, falling, or stabilizing; the stable operating range of data such as vibration amplitude and displacement of mechanical parameters; the frequency of fluctuations of thermal parameters deviating from the stable range per unit time; and the highest peak and lowest valley values ​​of each type of parameter within each time period. It comprehensively sorts out these core information that can directly reflect the operating status of the equipment, summarizes and integrates all key performance indicators, and forms operating characteristic information that can accurately reflect the current operating status of the equipment.

[0092] The predefined operating mode feature library contains a set of typical features corresponding to all common operating modes of the equipment. The features of each mode clearly define the standard change trend, fixed stable range, normal fluctuation frequency, and typical peak and valley range of the electrical, mechanical, and thermal parameters of the equipment under that mode. The extracted operating feature information is compared one by one and comprehensively with the typical features of each operating mode in the library from various dimensions. First, the change trend is compared to see if they are consistent. Then, the stable operating range is checked to see if they overlap. Next, the fluctuation frequency is verified to see if it is within a reasonable range. Finally, the peak and valley values ​​are confirmed to match. The mode feature with the highest comprehensive consistency across all dimensions is identified. The operating mode corresponding to this mode feature is the current operating mode of the substation equipment.

[0093] Based on the equipment operation mechanism and historical operation and maintenance data, the core influencing factors of the equipment operation status under the current operation mode are identified, such as voltage stability and mechanical transmission efficiency under the power generation mode. Using these core influencing factors as the basis for judgment, all parameters in the synchronous multi-parameter data stream are identified one by one. By analyzing the correlation logic between parameters and core influencing factors, redundant parameters that have a very low correlation with the current operation mode and have no direct or indirect effect on reflecting the equipment status under this mode are eliminated. Parameters that can directly reflect the core influencing factors or indirectly reflect the core status of the current operation mode are retained. These retained parameters are integrated to form the mode-related parameter set of the synchronous multi-parameter data stream.

[0094] Each parameter in the pattern-related parameter set is used as a row and column of a matrix, with the parameter name labeled sequentially in both rows and columns. A well-structured blank correlation matrix framework is constructed. For any two parameters in the matrix, the tightness of the coupling relationship between them is comprehensively judged by observing the synchronous change of one parameter when the other changes within the same time period, statistically analyzing the frequency of interaction when both parameters change significantly at the same time, and determining the depth of influence of the change amplitude of one parameter on the change amplitude of the other parameter. The tightness is divided into fixed levels and corresponding to specific values. The values ​​are converted into matrix elements according to a unified standard and filled into the corresponding positions of the correlation matrix. After filling all positions with elements, a complete parameter coupling strength matrix is ​​formed.

[0095] The parameter contribution is obtained through a specific calculation. The core evaluation result of the parameter is named as the first. The contribution of each parameter, the parameter coupling strength matrix is ​​a matrix previously constructed based on the mode-related parameter set. The numerical relationships of each element in this matrix are analyzed, and key values ​​reflecting the overall characteristics of the matrix, i.e., eigenvalues, are extracted. The total number of all extracted eigenvalues ​​is the total number of eigenvalues. The eigenvalue and the eigenvalue Each eigenvalue comes from the eigenvalue analysis of this matrix and is numbered according to the extraction order or numerical value. The eigenvalues ​​are identified solely by their number. and To distinguish different feature values, the operating mode feature library is a predefined collection containing typical features of all common operating modes of a device. The feature library extracts the first feature value from this library. The complete data for each parameter under all preset common operating modes are calculated, and the degree of dispersion of these data from the average value is obtained. The result is the first parameter. The standard deviation of each parameter across different operating modes is used. The current operating mode is the equipment operating mode previously determined by comparing operating feature information with a predefined operating mode feature library. The standard deviation of each parameter collected since the operation of this mode is extracted. For each parameter, calculate the dispersion of all its internal data from its own average value; the result is the i-th parameter. The standard deviation of each parameter within the current operating mode, the component variance weighting coefficient, and the mode discrimination weighting coefficient are fixed values ​​determined by combining the verification results of a large amount of historical monitoring data and the actual needs of on-site operation and maintenance. These values ​​are used to adjust the influence ratio of different evaluation dimensions in the contribution calculation.

[0096] Calculate the first When assessing the contribution of a parameter, first sum all extracted eigenvalues ​​from the parameter coupling strength matrix to obtain the sum of all eigenvalues, and then use the sum of the first eigenvalues... Divide the eigenvalue by the sum, calculate the division result precisely, and retain a fixed number of decimal places to obtain the th eigenvalue. The proportion of each eigenvalue among all eigenvalues ​​is calculated, and this proportion is then multiplied by a preset component variance weighting coefficient to obtain the first part of the calculation result. Simultaneously, the second part of the calculation is performed in parallel, using the... The standard deviation of a parameter across different operating modes is divided by its standard deviation within the current operating mode to obtain a ratio reflecting the mode-discriminating ability of that parameter. This ratio is then multiplied by a preset mode discrimination weighting coefficient to obtain the second part of the calculation result. Finally, the two parts of the calculation result are added together to obtain the final value, which is the first value. The contribution of each parameter.

[0097] The core significance of this calculation process lies in comprehensively evaluating the importance of parameters through two key dimensions. The first dimension reflects the importance of the second dimension through the proportion of eigenvalues. The weight of each parameter in the overall coupling relationship of the pattern-related parameter set indicates its influence. A higher weight indicates a more critical role and a more significant impact on the overall data features. The second dimension reflects the influence of the first dimension through the ratio of the standard deviation between different patterns to that within a pattern. The ability of a parameter to distinguish different operating modes is a key factor. A larger ratio indicates a more significant difference in the parameter's performance across different modes, making it easier to determine the device's operating mode. Combining both factors balances the parameter's importance within the current mode and its ability to differentiate between different modes, resulting in a parameter contribution that comprehensively and accurately reflects the overall performance of the device. The actual contribution of each parameter to the condition monitoring of substation equipment under the current operating mode provides a scientific and reliable evaluation basis for the subsequent selection of dominant parameters.

[0098] The contribution of all parameters is systematically organized, and each parameter and its corresponding contribution value are recorded one by one to establish a complete parameter-contribution correspondence table. All parameters are strictly sorted in descending order of contribution value. If there are parameters with the same contribution value, they are sorted again according to the degree of correlation between the parameter and the core requirements of the current operating mode. Based on the purpose of equipment operation and maintenance focus, the core requirements for equipment status monitoring in the current operating mode are determined. For example, in the power supply mode, the focus is on power supply stability and security. A fixed number or proportion of selections is determined according to the core requirements. Feature parameters with high contribution ranking that can dominate and reflect the operating status of the equipment in this mode are selected. These selected feature parameters are the dominant parameters of the current operating mode.

[0099] The beneficial effects include: extracting operational features by system at fixed time intervals, ensuring the comprehensiveness and accuracy of feature information; comparing the extracted operational features with pattern features in the database in multiple dimensions, making the determination of the current operational mode more reliable; filtering pattern-related parameters based on core influencing factors, effectively eliminating redundant data and reducing interference; constructing a parameter coupling strength matrix with unified standards to clearly present the correlation between parameters; obtaining parameter contribution through rigorous step-by-step calculations; selecting dominant parameters according to scientific standards; comprehensively ensuring that the dominant parameters can accurately match the core monitoring needs of the current equipment operational mode; significantly improving the pertinence and accuracy of parameter identification; providing focused and critical data support for subsequent equipment status assessment; and effectively ensuring the efficient and accurate conduct of monitoring and analysis.

[0100] S3. Map the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and couple and converge the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment;

[0101] In this embodiment of the invention, the step of mapping the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and coupling and converging the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment includes:

[0102] The dominant parameter is matched and queried with a pre-set equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter;

[0103] The correlation relationships of the correlation parameters are parsed to obtain the direct and indirect correlation parameters of the correlation parameters;

[0104] Based on the correlation strength between the directly related parameters, the indirectly related parameters, and the dominant parameters, the influence weights of the dominant parameters, the directly related parameters, and the indirectly related parameters are configured to obtain the weighted parameter set of the substation equipment.

[0105] The weighted parameter set is optimized by feature parameter fusion to obtain the monitoring focus parameter group of the substation equipment.

[0106] The dominant parameter is the core characteristic parameter of the current operating mode identified previously. The pre-set equipment operation mechanism knowledge base stores preset information such as the interaction relationship, influence path, association logic and operation law between various parameters of substation equipment. The core characteristics of the dominant parameter, such as parameter type, functional attributes and operating influence range, are extracted. The knowledge base is searched layer by layer according to the parameter classification directory. The core characteristics of the dominant parameter are compared with the parameter association entries stored in the knowledge base one by one. All parameters that have direct or indirect interaction with the dominant parameter are selected. These selected parameters are the associated parameters of the dominant parameter.

[0107] Each related parameter and the dominant parameter's interaction path is analyzed one by one. It is checked whether the related parameter is related to the dominant parameter through other parameters as intermediate media. If the related parameter can directly receive the influence of the dominant parameter or directly act on the dominant parameter without any intermediate parameters, and there is no transmission link in the interaction process, then the related parameter is determined to be a directly related parameter. If the related parameter must be transmitted through one or more other parameters to form a mutual influence relationship with the dominant parameter, and there is a clear intermediate transmission link in the interaction path, then the related parameter is determined to be an indirectly related parameter. After completing the path analysis and determination of all related parameters, the directly related parameters and indirectly related parameters of the related parameters are obtained.

[0108] Based on the parameter interaction data recorded in the equipment operation mechanism knowledge base, the frequency and magnitude of interaction between directly related parameters and dominant parameters are statistically analyzed. The efficiency and transmission loss of the influence of indirectly related parameters transmitted to the dominant parameters through intermediate parameters are also analyzed. This clarifies the differences in the correlation strength between directly related parameters, indirectly related parameters, and dominant parameters. Three fixed weight levels are set: the dominant parameter corresponds to the highest weight level, the directly related parameter corresponds to the intermediate weight level, and the indirectly related parameter corresponds to the lowest weight level. Within the same weight level, specific weight values ​​are assigned according to the correlation strength, with higher correlation strength resulting in larger weight values. The dominant parameter, directly related parameter, and indirectly related parameter are each bound to their corresponding weight values, forming a weighted parameter set for the substation equipment.

[0109] The weight values ​​of all parameters in the weighted parameter set are systematically organized, and parameters with weight values ​​lower than the set standard and no substantial value in reflecting the operating status of the equipment are removed. The weight values ​​of the remaining parameters are uniformly calibrated to ensure that the weight ratio of different types of parameters meets the core requirements of equipment monitoring. Then, the monitoring dimensions of the remaining parameters are analyzed to avoid excessive superposition of parameters under the same monitoring dimension. Parameters that can comprehensively cover key monitoring dimensions such as electrical, mechanical, and thermal and have high weight values ​​are retained. These parameters that have been screened, calibrated and dimension optimized are logically integrated to obtain the monitoring focus parameter group of substation equipment.

[0110] The beneficial effects are as follows: by accurately matching with the pre-set equipment operation mechanism knowledge base to obtain related parameters, the strong correlation and reliability of related parameters with the dominant parameters are ensured; by analyzing the correlation relationship, the classification of direct and indirect related parameters is clarified, providing a clear basis for weight configuration; the influence weight configuration based on the correlation strength makes the hierarchy of parameter importance clear; and the fusion optimization process of dimension optimization and redundancy elimination ensures that the final monitoring focus parameter group not only comprehensively covers the key dimensions of equipment operation, but also focuses on core monitoring information, effectively improving the data quality and analysis efficiency of subsequent status assessment.

[0111] S4. Based on the historical stable operating characteristics of the monitoring focus parameter group, perform a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment to obtain the state consistency characteristics of the substation equipment.

[0112] In this embodiment of the invention, the step of using the historical stable operating characteristics of the monitoring focus parameter group as a benchmark to perform fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment to obtain the state consistency characteristics of the substation equipment includes:

[0113] Obtain the historical stable operating characteristics of the monitoring focus parameter group;

[0114] Based on the historical stable operation characteristics, dynamic offset identification is performed on the monitoring focus parameter group at the current moment to obtain the offset feature set of the substation equipment;

[0115] Based on the offset feature set, the offset trend correlation analysis is performed on the monitoring focus parameter group at the current moment to obtain the cooperative fluctuation mode of the substation equipment;

[0116] The time-domain features of the cooperative fluctuation mode are reconstructed to obtain the cooperative feature sequence of the substation equipment.

[0117] The coordination feature sequence is evaluated to obtain the state consistency features of the substation equipment.

[0118] The step of performing offset trend correlation analysis on the monitoring focus parameter group at the current moment based on the offset feature set to obtain the cooperative fluctuation mode of the substation equipment includes:

[0119] The offset feature set is deconstructed by trend component analysis to obtain the long-term trend component and short-term fluctuation component of the offset feature set.

[0120] The long-term trend components are subjected to eigenvector decomposition to construct the trend correlation matrix of the long-term trend components;

[0121] Based on the trend correlation matrix, principal component features are extracted to assess the consistency and divergence of the long-term trend components, thereby obtaining the trend coordination features of the substation equipment.

[0122] Wave coupling analysis is performed on the phase and amplitude information of the short-term wave components to obtain the coupling characteristics of the short-term wave components;

[0123] The trend coordination feature and the coupling feature are integrated into the coordination fluctuation mode of the substation equipment.

[0124] The monitoring focus parameter group is a set of core monitoring parameters previously coupled and aggregated. Complete data for this parameter group over the past year with a cumulative normal operating time of 5000 hours or more is retrieved from the equipment's historical operation database. Historical periods of stable equipment operation are selected based on the criteria of no fault alarm records and parameter fluctuations being less than 30% of the historical average. For each parameter within these periods, a 95% confidence interval is determined as the stable value range according to the daily statistical value distribution. The ratio of parameter change to time within a continuous period is calculated, and the maximum value is taken as the change rate threshold. The maximum difference in parameter fluctuations is used as the upper limit of fluctuation amplitude. The synchronous response relationship of different parameter changes is recorded as the coordination relationship between parameters. These key information are classified and organized according to electrical, mechanical, and thermal parameter types to form the historical stable operation characteristics of the monitoring focus parameter group that can reflect the normal operating level of the equipment.

[0125] Based on the stable value range and change rate threshold of each parameter in the historical stable operation characteristics, the actual value of each parameter in the current monitoring focus parameter group is compared with the upper and lower limits of the historical stable value range one by one. If the value exceeds the limit, the numerical deviation is recorded. The average change rate of the parameter in the current 10 minutes is calculated and compared with the historical change rate threshold to analyze the difference. The percentage of each parameter's value deviation from the historical range, the consistency of the change trend with the historical pattern, and the difference in the speed of fluctuation are recorded in detail. The direction of the deviation is clarified as positive (exceeding) or negative (below), the degree is slight, moderate, or severe, and the start time is accurate to the second. All these deviation information of all parameters are systematically integrated according to parameter type to obtain the deviation feature set of substation equipment.

[0126] A deep analysis of the time dimension is performed on all offset data in the offset feature set. Using 30 minutes after calibration based on the equipment's operating cycle as the dividing line, the continuous and instantaneous attributes of data changes are distinguished. Offset data with a duration of more than 30 minutes, consistent change direction, and a gradual increasing or decreasing regular evolution are classified. This type of data constitutes the long-term trend component that can reflect the long-term operating status of the equipment. Offset data with a duration of less than 30 minutes, alternating between increasing and decreasing change direction, and no fixed periodicity are separately classified. This type of data forms the short-term fluctuation component that reflects the instantaneous operating fluctuation of the equipment. Through this clear standard classification and decomposition, the trend component of the offset feature set is deconstructed.

[0127] Each parameter trend data in the long-term trend component is decomposed into direction and intensity according to spatial or functional dimensions. Electrical parameters are decomposed into voltage, current, and power dimensions, while mechanical parameters are decomposed into horizontal, vertical, and radial dimensions. The long-term changes in each dimension are decomposed into multiple eigenvectors. Each eigenvector clearly corresponds to a specific direction of change and the corresponding intensity of change. The intensity level is determined according to the proportion of the parameter change amplitude to the historical stable range, using a scale of 0-10. A matrix framework is constructed based on these eigenvectors, with the rows and columns of the matrix corresponding to the eigenvectors of different parameters. The intensity level of each eigenvector is directly used as a matrix element and filled into the corresponding position in the matrix, ultimately forming the trend correlation matrix of the long-term trend component.

[0128] The correspondence between different parameter feature vectors reflected by each element in the trend correlation matrix is ​​analyzed one by one. Positions with the same element value or a difference of less than 1 indicate that the corresponding feature vector changes are consistent. The number of parameter combinations with the same direction of change is counted and their proportion of all parameter combinations is calculated. If the proportion exceeds 70%, it is judged as strong consistency. At the same time, parameter combinations with opposite directions of change and intensity level differences exceeding 5 are identified, recorded as strong divergence, and the degree of divergence is specified. The direction of change and intensity level with the highest consistency ratio are extracted from the matrix and integrated to form the core features that can dominate the overall trend and reflect the common changes of most parameters. These core features are the trend coordination features of substation equipment.

[0129] By carefully analyzing the time nodes and numerical changes of each fluctuation data point in the short-term fluctuation components, and taking the fluctuation start time of a certain core parameter as the benchmark, the fluctuation start time of other parameters is judged to be in phase if the time difference between the benchmark time and the start time is less than 5 seconds. This clarifies the phase information of the short-term fluctuations. The fluctuation amplitude is determined by calculating the absolute value of the fluctuation peak and trough, and divided into three levels: large, medium, and small, according to the average of historical fluctuation amplitudes. The phase synchronization of short-term fluctuations of different parameters is compared, and the correlation of amplitude changes is analyzed. If the fluctuation amplitude of one parameter reaches the large level and another parameter also reaches the large level within 10 seconds, it is judged as positive correlation coupling. If the amplitude of one parameter increases and the amplitude of another parameter decreases, it is judged as negative correlation coupling. These coordinated changes in phase and amplitude are summarized as the coupling characteristics of the short-term fluctuation components.

[0130] By logically integrating the long-term stable change patterns reflected by the trend coordination characteristics with the short-term fluctuation correlations embodied by the coupling characteristics, the constraint that the peak value of short-term fluctuations must not exceed 15% of the long-term trend fitting line when the long-term trend is continuously rising is clarified. The impact of short-term fluctuation peaks exceeding 30% triggering an acceleration of the long-term trend change rate is evaluated. The core information such as the direction and rate of change of the long-term trend and the phase synchronization rate and amplitude coupling type of short-term fluctuations are integrated into a unified model that can comprehensively cover the long-term operating status and short-term fluctuation status of equipment. This model is the coordinated fluctuation model of substation equipment.

[0131] A time axis is constructed with 1-minute intervals. The long-term trend information and short-term fluctuation information in the cooperative fluctuation mode are reorganized. The long-term trend status and the phase and amplitude data of short-term fluctuations within each time interval are encapsulated into a feature unit. The feature units at different time points are bound one by one in chronological order. It is checked whether each time interval has a corresponding feature unit. If there is a missing one, it is supplemented by interpolation of the features of the preceding and following time periods, forming a continuous and uninterrupted feature sequence with time as the axis. Each time node in the sequence contains the long-term trend status and short-term fluctuation status at that moment. Through this fine integration of the time dimension, the time domain features of the cooperative fluctuation mode are reconstructed, and the cooperative feature sequence of the substation equipment is obtained.

[0132] The trend and fluctuation states at each time point in the coordinated feature sequence are checked for consistency. It is determined whether the short-term fluctuation amplitude is within the reasonable constraint range of ±10% of the long-term trend fitting line. It is checked whether there is a logical contradiction that the long-term trend is stable but the short-term fluctuations are frequent and large in magnitude. The characteristic changes of five consecutive time intervals are evaluated to determine the continuity. The proportion of coordinated time intervals to the total time period, the frequency and specific types of contradictions are statistically analyzed. The results of these checks are combined to form a state consistency feature that can clearly reflect the overall coordination level and contradiction points of the equipment operation status.

[0133] The beneficial effects are as follows: by clarifying the extraction criteria for historical stable operating characteristics, accurately quantifying the degree of deviation, decomposing trend components according to fixed boundaries, refining the construction logic of feature vectors and correlation matrices, clarifying the coupling judgment rules of phase and amplitude, standardizing the integration and sequence reconstruction process of collaborative modes, and refining the coordination verification indicators, every step of the entire process has clear basis and operability. It accurately captures the correlation between the long-term trend and short-term fluctuation of equipment operating status, so that the final state consistency characteristics more comprehensively and accurately reflect the coordination of equipment operating status. This provides solid and reliable feature support for the formulation of subsequent dynamic monitoring rules, and further ensures the accuracy, comprehensiveness and reliability of equipment status assessment.

[0134] S5. Based on the real-time operating condition information of the substation equipment and the state consistency characteristics, the judgment rules of the substation equipment are adaptively modified to obtain the dynamic monitoring rules of the substation equipment.

[0135] In this embodiment of the invention, the step of adaptively modifying the judgment rules of the substation equipment based on the real-time operating condition information of the substation equipment and the state consistency characteristics to obtain the dynamic monitoring rules of the substation equipment includes:

[0136] The real-time operating condition information of the substation equipment is correlated with the state consistency feature in a multi-dimensional way to obtain the operating condition-state correlation mapping table of the substation equipment.

[0137] Based on the operating condition-state association mapping table, the condition thresholds in the judgment rules of the substation equipment are adaptively adjusted to obtain the threshold optimization rules of the substation equipment.

[0138] Based on the temporal change pattern of the state consistency characteristics, the triggering logic of the threshold optimization rule is optimized to obtain the logic optimization rule of the substation equipment.

[0139] The decision logic integration of the aforementioned logic optimization rules yields the dynamic monitoring rules for the substation equipment.

[0140] The real-time operating condition information of substation equipment includes key operating condition data such as current load level, running time, ambient temperature and humidity, and grid voltage stability. The state consistency feature is the core feature reflecting the coordination of equipment operating status, which was previously obtained. Load level, running time range, and ambient temperature and humidity range are selected as operating condition dimensions, and state coordination level, frequency of conflict occurrence, and conflict type are selected as state dimensions. Each operating condition dimension is divided into fixed intervals according to equipment operating standards. The load level is divided into three levels: low, medium, and high. The running time is divided into four time periods with a 24-hour cycle. The temperature and humidity are divided into three categories: suitable, critical, and unsuitable according to the suitable operating range of the equipment. Each combination of operating condition intervals is matched with the specific manifestation of the corresponding state consistency feature. The matching results are organized into a structured table according to the correspondence between operating condition dimension and state dimension. This table is the operating condition-state association mapping table of substation equipment.

[0141] The judgment rules for substation equipment include the condition thresholds for the normal operation of each parameter. Based on the working condition-state correlation mapping table, the performance of state consistency characteristics under different working condition combinations is queried. If the state coordination level under a certain working condition combination is excellent and there are no conflict records, the condition thresholds in the judgment rules corresponding to that working condition are relaxed to the upper limit of the historical reasonable range. If the state coordination level under a certain working condition combination is poor and the frequency of conflicts exceeds the set standard, the corresponding condition thresholds are tightened to the lower limit of the historical reasonable range. For example, when the state coordination level is low under high load conditions, the threshold of electrical parameters is lowered to 80% of the threshold under low load conditions. Through this adjustment based on the specific working condition-state correspondence, the threshold optimization rules for substation equipment are obtained.

[0142] Extract the change data of state consistency characteristics over continuous periods and analyze its temporal change pattern. If the coordination level gradually decreases and the type of conflict changes from mild to severe over five consecutive periods, it is judged as a gradual deterioration pattern. If the frequency of conflicts suddenly surges and the coordination level drops sharply during a certain period, it is judged as a sudden anomaly pattern. If the coordination level remains stable and there are no conflicts for a long period, it is judged as a stable pattern. Optimize the trigger logic of the threshold optimization rules for different temporal change patterns. In the gradual deterioration pattern, the trigger logic is adjusted to trigger an early warning when the threshold is reached for two consecutive periods. In the sudden anomaly pattern, it is adjusted to trigger an emergency early warning immediately when the threshold is reached once. In the stable pattern, it is adjusted to trigger a prompt only when the threshold is reached for three consecutive periods. Through this logic adjustment that adapts to temporal changes, the logic optimization rules for substation equipment are obtained.

[0143] All logical optimization rules are sorted out and prioritized according to operating conditions. Load level has higher priority than runtime, and runtime has higher priority than ambient temperature and humidity. The order in which rules apply for different priority operating conditions is clarified. When multiple logical optimization rules meet the applicable conditions at the same time, the highest priority rule is executed. At the same time, the conflict between rules is checked. If the rule for high load operating conditions conflicts with the rule for stable timing mode, the rule for high load operating conditions shall prevail. All logical optimization rules that have been prioritized and conflict resolved are structurally integrated to form a set of logically consistent rules that cover different operating conditions and timing change modes. This rule system is the dynamic monitoring rule for substation equipment.

[0144] The beneficial effects are that by mapping real-time operating conditions with state consistency features in a multi-dimensional way, it provides a precise basis for threshold adjustment based on operating conditions. The triggering logic is optimized based on the time-series change pattern, making the rules more in line with the evolution of equipment state. The dynamic monitoring rules formed by the integration of decision logic can flexibly adapt to different operating conditions and state changes of equipment, effectively avoiding the problem of insufficient adaptability caused by fixed rules, significantly improving the pertinence and adaptability of monitoring rules, and providing a reliable guarantee for the accurate diagnosis of subsequent equipment state.

[0145] S6. Based on the dynamic monitoring rules, perform coordination diagnosis on the state consistency characteristics to obtain the multi-parameter coordination state conclusion of the substation equipment.

[0146] In this embodiment of the invention, the step of performing a coordination diagnosis on the state consistency characteristics based on the dynamic monitoring rules to obtain a multi-parameter coordination state conclusion for the substation equipment includes:

[0147] By performing rule matching and reasoning between the dynamic monitoring rules and the state consistency features, a preliminary diagnostic conclusion set for the substation equipment is obtained.

[0148] The preliminary diagnostic conclusion set is subjected to conflict resolution to obtain the diagnostic conclusion sequence of the substation equipment;

[0149] The evolution trend of the diagnostic conclusion sequence and the state consistency characteristics is used to determine the coordinated state, thereby obtaining the multi-parameter coordinated state conclusion of the substation equipment.

[0150] The dynamic monitoring rules include judgment conditions and conclusions corresponding to different operating conditions and time-series change modes. The state consistency characteristics cover core information such as the coordination level of equipment operating status, the frequency of conflict occurrence, and the type of conflict. First, the dynamic monitoring rules are decomposed into independent judgment units according to the priority of operating conditions and the type of time-series mode. Each judgment unit clearly defines the triggering conditions and corresponding diagnostic conclusions. Then, the information of each dimension of the state consistency characteristics is compared with the triggering conditions of each judgment unit one by one. If the coordination level, conflict data, etc. of the state consistency characteristics completely meet the triggering conditions of a certain judgment unit, the diagnostic conclusion corresponding to that judgment unit is extracted. This process is repeated until all judgment units have been compared. All extracted diagnostic conclusions are sorted and collected in the order of comparison to obtain the preliminary diagnostic conclusion set of the substation equipment.

[0151] All diagnostic conclusions in the preliminary diagnostic conclusion set are reviewed one by one. The judgment basis and core viewpoints of different conclusions are compared. If two or more conclusions are contradictory in their judgment of the same equipment status, such as one conclusion judging it as a normal coordinated state and another judging it as an abnormal uncoordinated state, the conflict resolution process is initiated. According to the priority of the operating conditions in the dynamic monitoring rules, the diagnostic conclusions corresponding to higher priority operating conditions have higher weights and are retained first. At the same time, the completeness of the feature matching corresponding to the conclusions is checked. The conclusions obtained based on the matching of multiple dimensions of state consistency features take precedence over the conclusions based on the matching of a single dimension. Conflicting low-weight conclusions are eliminated, and the remaining non-conflicting diagnostic conclusions are arranged in the order of the temporal change of state consistency features to obtain the diagnostic conclusion sequence of the substation equipment.

[0152] Information such as changes in coordination level, increase or decrease in conflict frequency, and evolution of conflict type are extracted from the consistency characteristics of the equipment status over a continuous period. The evolution trend of the equipment status is analyzed, such as a gradual deterioration trend of continuously decreasing coordination level and increasing conflict frequency, a sudden abnormal trend of sudden drop in coordination level and sudden serious conflict, and a stable trend of stable coordination level and no conflict. Each conclusion in the diagnostic conclusion sequence is then checked against the evolution trend to determine whether the conclusion is consistent with the trend. If most conclusions in the sequence are abnormal and the trend is gradually deteriorating, the equipment is judged to be in a continuous uncoordinated state. If the conclusions in the sequence are mainly normal and the trend is stable, it is judged to be in a stable coordinated state. By integrating information such as the fit between the trend and the conclusion sequence and the consistency of the core conclusions, a multi-parameter coordination status conclusion of the substation equipment that can comprehensively reflect the multi-parameter collaborative operation of the equipment is finally formed.

[0153] The beneficial effects are that preliminary diagnostic conclusions are obtained through precise matching and reasoning of dynamic monitoring rules and state consistency features, conclusion conflicts are resolved by relying on rule priority and feature matching integrity, and coordinated state determination is carried out in combination with state evolution trends. This ensures the logic and consistency of diagnostic conclusions, effectively avoids the one-sidedness of single rule judgment, and allows the final multi-parameter coordinated state conclusion to comprehensively and accurately reflect the actual operating status of the equipment, providing a reliable basis for equipment operation and maintenance decisions.

[0154] like Figure 2 The diagram shown is a functional block diagram of a multi-parameter online real-time monitoring system for substation equipment status provided in an embodiment of the present invention.

[0155] The online real-time monitoring system 100 for multiple parameters of substation equipment status described in this invention can be installed in an electronic device. Depending on the functions implemented, the online real-time monitoring system 100 may include a time-scale alignment module 101, a pattern recognition and parameter extraction module 102, a focus parameter aggregation module 103, a collaborative evaluation module 104, a dynamic rule generation module 105, and a coordinated status diagnosis module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0156] In this embodiment, the functions of each module / unit are as follows:

[0157] The time-stamp alignment module 101 is used to perform time-stamp alignment on the electrical, mechanical and thermal parameters of the substation equipment to obtain the synchronous multi-parameter data stream of the substation equipment;

[0158] The pattern recognition and parameter extraction module 102 is used to determine the current operating mode of the substation equipment based on the synchronous multi-parameter data stream, and to identify the core parameters of the synchronous multi-parameter data stream based on the current operating mode to obtain the dominant parameters of the current operating mode.

[0159] The focus parameter aggregation module 103 is used to map the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and couple and aggregate the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment.

[0160] The collaborative evaluation module 104 is used to perform a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment based on the historical stable operating characteristics of the monitoring focus parameter group, so as to obtain the state consistency characteristics of the substation equipment.

[0161] The dynamic rule generation module 105 is used to adaptively modify the judgment rules of the substation equipment based on the real-time operating condition information of the substation equipment and the state consistency characteristics, so as to obtain the dynamic monitoring rules of the substation equipment.

[0162] The coordination state diagnosis module 106 is used to perform coordination diagnosis on the state consistency characteristics based on the dynamic monitoring rules, and obtain the multi-parameter coordination state conclusion of the substation equipment.

[0163] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0164] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0165] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0166] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0167] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0168] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for online real-time monitoring of multiple parameters of substation equipment status, characterized in that, The method includes: S1. Time-scale alignment is performed on the electrical, mechanical, and thermal parameters of the substation equipment to obtain the synchronous multi-parameter data stream of the substation equipment; S2. Based on the synchronous multi-parameter data stream, determine the current operating mode of the substation equipment, and based on the current operating mode, identify the core parameters of the synchronous multi-parameter data stream to obtain the dominant parameters of the current operating mode. S3. Map the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and couple and converge the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment; S4. Based on the historical stable operating characteristics of the monitoring focus parameter group, perform a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment to obtain the state consistency characteristics of the substation equipment. S5. Based on the real-time operating condition information of the substation equipment and the state consistency characteristics, the judgment rules of the substation equipment are adaptively modified to obtain the dynamic monitoring rules of the substation equipment. S6. Based on the dynamic monitoring rules, perform coordination diagnosis on the state consistency characteristics to obtain the multi-parameter coordination state conclusion of the substation equipment.

2. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 1, characterized in that, The step of time-aligning the electrical, mechanical, and thermal parameters of the substation equipment to obtain a synchronous multi-parameter data stream for the substation equipment includes: Receive clock signals from a unified clock source within the substation to generate a time synchronization reference for the substation; Based on the time synchronization reference, the electrical, mechanical and thermal parameters of the substation equipment are collected synchronously to obtain the original parameter data of the substation equipment; Eliminate the timescale deviation between acquisition times in the original parameter data to obtain unified timescale parameter data for the substation equipment; By binding the electrical, mechanical, and thermal parameters corresponding to the same time point in the unified time-scaled parameter data, a synchronous multi-parameter data stream of the substation equipment is obtained.

3. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 1, characterized in that, The process involves determining the current operating mode of the substation equipment based on the synchronous multi-parameter data stream, and identifying core parameters of the synchronous multi-parameter data stream based on the current operating mode to obtain the dominant parameters of the current operating mode, including: Extract the runtime characteristic information from the synchronous multi-parameter data stream; The operating characteristic information is compared with a predefined operating mode characteristic library to obtain the current operating mode of the substation equipment; Based on the current operating mode, parameter filtering is performed on the synchronous multi-parameter data stream to obtain the mode-related parameter set of the synchronous multi-parameter data stream; An association matrix is ​​constructed from the pattern-related parameter set to obtain the parameter coupling strength matrix of the pattern-related parameter set; The principal component contribution rate of the parametric coupling strength matrix is ​​calculated to obtain the parametric contribution degree of the parametric coupling strength matrix. The contribution of the parameters is used to select characteristic parameters to obtain the dominant parameters of the current operating mode.

4. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 3, characterized in that, The formula for calculating the contribution of the parameter is as follows: ； In the formula, For the first The contribution of each parameter The total number of eigenvalues ​​in the parametric coupling strength matrix. The first in the parametric coupling strength matrix 1 eigenvalue, The first in the parametric coupling strength matrix 1 eigenvalue, For the first in the running mode feature library The standard deviation of a parameter across different operating modes In the current operating mode, the first The standard deviation within each parameter These are the preset component variance weighting coefficients. The preset pattern discrimination weight coefficient.

5. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 1, characterized in that, The process involves mapping the dominant parameter to a pre-set equipment operation mechanism knowledge base to obtain associated parameters of the dominant parameter, and coupling and converging the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment, including: The dominant parameter is matched and queried with a pre-set equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter; The correlation relationships of the correlation parameters are parsed to obtain the direct and indirect correlation parameters of the correlation parameters; Based on the correlation strength between the directly related parameters, the indirectly related parameters, and the dominant parameters, the influence weights of the dominant parameters, the directly related parameters, and the indirectly related parameters are configured to obtain the weighted parameter set of the substation equipment. The weighted parameter set is optimized by feature parameter fusion to obtain the monitoring focus parameter group of the substation equipment.

6. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 1, characterized in that, The step of using the historical stable operating characteristics of the monitoring focus parameter group as a benchmark to perform fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment, and obtaining the state consistency characteristics of the substation equipment, includes: Obtain the historical stable operating characteristics of the monitoring focus parameter group; Based on the historical stable operation characteristics, dynamic offset identification is performed on the monitoring focus parameter group at the current moment to obtain the offset feature set of the substation equipment; Based on the offset feature set, the offset trend correlation analysis is performed on the monitoring focus parameter group at the current moment to obtain the cooperative fluctuation mode of the substation equipment; The time-domain features of the cooperative fluctuation mode are reconstructed to obtain the cooperative feature sequence of the substation equipment. The coordination feature sequence is evaluated to obtain the state consistency features of the substation equipment.

7. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 6, characterized in that, The step of performing offset trend correlation analysis on the monitoring focus parameter group at the current moment based on the offset feature set to obtain the cooperative fluctuation mode of the substation equipment includes: The offset feature set is deconstructed by trend component analysis to obtain the long-term trend component and short-term fluctuation component of the offset feature set. The long-term trend components are subjected to eigenvector decomposition to construct the trend correlation matrix of the long-term trend components; Based on the trend correlation matrix, principal component features are extracted to assess the consistency and divergence of the long-term trend components, thereby obtaining the trend coordination features of the substation equipment. Wave coupling analysis is performed on the phase and amplitude information of the short-term wave components to obtain the coupling characteristics of the short-term wave components; The trend coordination feature and the coupling feature are integrated into the coordination fluctuation mode of the substation equipment.

8. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 1, characterized in that, The dynamic monitoring rules for the substation equipment are obtained by adaptively modifying the judgment rules based on the real-time operating condition information and the state consistency characteristics of the substation equipment, including: The real-time operating condition information of the substation equipment is correlated with the state consistency feature in a multi-dimensional way to obtain the operating condition-state correlation mapping table of the substation equipment. Based on the operating condition-state association mapping table, the condition thresholds in the judgment rules of the substation equipment are adaptively adjusted to obtain the threshold optimization rules of the substation equipment. Based on the temporal change pattern of the state consistency characteristics, the triggering logic of the threshold optimization rule is optimized to obtain the logic optimization rule of the substation equipment. The decision logic integration of the aforementioned logic optimization rules yields the dynamic monitoring rules for the substation equipment.

9. The method for online real-time monitoring of multiple parameters of substation equipment status as described in claim 1, characterized in that, The process of performing a coordination diagnosis on the state consistency characteristics based on the dynamic monitoring rules to obtain a multi-parameter coordination state conclusion for the substation equipment includes: By performing rule matching and reasoning between the dynamic monitoring rules and the state consistency features, a preliminary diagnostic conclusion set for the substation equipment is obtained. The preliminary diagnostic conclusion set is subjected to conflict resolution to obtain the diagnostic conclusion sequence of the substation equipment; The evolution trend of the diagnostic conclusion sequence and the state consistency characteristics is used to determine the coordinated state, thereby obtaining the multi-parameter coordinated state conclusion of the substation equipment.

10. A multi-parameter online real-time monitoring system for substation equipment status, characterized in that, The system for implementing the online real-time monitoring method for multiple parameters of substation equipment status as described in claim 1 includes: The time-stamp alignment module is used to time-stamp align the electrical, mechanical, and thermal parameters of the substation equipment to obtain the synchronous multi-parameter data stream of the substation equipment; The pattern recognition and parameter extraction module is used to determine the current operating mode of the substation equipment based on the synchronous multi-parameter data stream, and to identify the core parameters of the synchronous multi-parameter data stream based on the current operating mode to obtain the dominant parameters of the current operating mode. The focus parameter aggregation module is used to map the dominant parameter to a preset equipment operation mechanism knowledge base to obtain the associated parameters of the dominant parameter, and couple and aggregate the dominant parameter and the associated parameters to obtain the monitoring focus parameter group of the substation equipment. The collaborative evaluation module is used to perform a fluctuation collaborative evaluation on the monitoring focus parameter group at the current moment based on the historical stable operating characteristics of the monitoring focus parameter group, so as to obtain the state consistency characteristics of the substation equipment. The dynamic rule generation module is used to adaptively modify the judgment rules of the substation equipment based on the real-time operating condition information of the substation equipment and the state consistency characteristics, so as to obtain the dynamic monitoring rules of the substation equipment. The coordination status diagnosis module is used to perform coordination diagnosis on the status consistency characteristics based on the dynamic monitoring rules, and obtain the multi-parameter coordination status conclusion of the substation equipment.

Images