Multi-parameter fusion GIL anti-vibration support safety monitoring method and system

Abstract

The invention provides a multi-parameter fusion GIL anti-vibration support safety monitoring method and system, and relates to the technical field of power transmission line monitoring, and the method comprises the steps: obtaining an SF6 gas pressure time sequence; if the target gas pressure is at a preset pressure threshold value, performing predictive analysis on the SF6 gas pressure time sequence to obtain predicted gas pressure; if the predicted gas pressure is not in the preset pressure threshold value, performing multi-parameter dynamic monitoring on the anti-vibration bracket to obtain multi-parameter detection information; performing predictive analysis on the parameter detection information to obtain a predicted parameter value; introducing a predetermined security map structure network to perform fusion analysis on the prediction parameter values to obtain a security state index; if the safety state index does not reach the preset state threshold value, safety early warning is carried out. The technical problem that the safety state of the GIL anti-vibration support cannot be comprehensively evaluated due to single monitoring parameter and lack of state prediction capability in the prior art is solved, and the accuracy, comprehensiveness and detection efficiency of safety monitoring are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission line monitoring, and in particular to a multi-parameter fusion GIL anti-vibration support safety monitoring method and system. Background Art

[0002] Gas insulated transmission lines (GIL) are widely used in large-scale power transmission systems due to their high transmission capacity, high reliability and small footprint. GIL anti-vibration brackets are important components to ensure the stable operation of transmission lines. They are mainly used to reduce the damage caused by vibration to equipment and improve the reliability of transmission system operation. Due to the complex operating environment and long-term exposure to mechanical vibration and electrical loads, the safety status of the anti-vibration bracket directly affects the operating safety of the entire GIL system.

[0003] At present, the safety monitoring methods for GIL anti-vibration brackets are mainly based on real-time monitoring of a single parameter (such as SF6 gas pressure or vibration acceleration), and a simple threshold is used to determine whether the equipment is in a safe state. However, this type of method has obvious shortcomings. On the one hand, since the stability of GIL is affected by many factors, including temperature, vibration, etc., the monitoring of a single parameter cannot fully reflect the complex working state of the anti-vibration bracket; on the other hand, the existing technology mainly relies on post-analysis and lacks the ability to predict and analyze monitoring data. It is difficult to perceive possible safety risks in a timely manner, which limits the identification and response to potential risks and easily leads to underreporting or false reporting of potential hidden dangers. Summary of the invention

[0004] The present application provides a multi-parameter fusion GIL anti-vibration support safety monitoring method and system, which solves the technical problems in the prior art that the safety status of the GIL anti-vibration support cannot be comprehensively evaluated and the potential risks of the GIL anti-vibration support cannot be identified in a timely manner due to the single monitoring parameters and lack of status prediction capabilities. This achieves the technical effect of improving the accuracy, comprehensiveness and detection efficiency of the safety monitoring of the GIL anti-vibration support, thereby enhancing the safe operation of the GIL line.

[0005] In view of the above problems, on the one hand, the present application provides a multi-parameter fusion GIL anti-vibration support safety monitoring method, the method comprising: activating an SF6 gas pressure detector, and dynamically monitoring the target GIL anti-vibration support through the SF6 gas pressure detector to obtain an SF6 gas pressure time series; judging whether the target gas pressure at the first target time in the SF6 gas pressure time series is within a predetermined pressure threshold; if so, calling the safety analysis center to perform a predictive analysis on the SF6 gas pressure time series to obtain a target predicted gas pressure at a second target time; judging whether the target predicted gas pressure is within the predetermined pressure threshold; if not, activating a multi-parameter detection device group to dynamically monitor the target GIL anti-vibration support state monitoring to obtain target multi-parameter detection information; calling the first analysis channel in the safety analysis center to perform predictive analysis on the first parameter detection information to obtain the first predicted parameter value at the second target time, wherein the first parameter detection information refers to the parameter detection information corresponding to the first characteristic indicator in the target multi-parameter detection information; introducing a predetermined safety graph structure network to perform fusion analysis on the first predicted parameter value of the first characteristic indicator to obtain the target safety state index of the target GIL anti-vibration bracket at the second target time; if the target safety state index does not reach the predetermined state threshold, issuing a first safety warning instruction, and performing safety warning processing on the target GIL anti-vibration bracket based on the first safety warning instruction.

[0006] On the other hand, the present application also provides a multi-parameter fusion GIL anti-vibration support safety monitoring system, the system comprising: a gas pressure detection module, used to activate the SF6 gas pressure detector, and dynamically monitor the target GIL anti-vibration support through the SF6 gas pressure detector to obtain the SF6 gas pressure time series; a first judgment module, used to judge whether the target gas pressure at the first target time in the SF6 gas pressure time series is within a predetermined pressure threshold; a gas pressure prediction module, used to call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series if it is within, and obtain the target predicted gas pressure at the second target time; a second judgment module, used to judge whether the target predicted gas pressure is within the predetermined pressure threshold; a multi-parameter detection module, used to activate the multi-parameter detection equipment group to detect the target GIL if it is not within. L anti-vibration bracket is dynamically monitored to obtain target multi-parameter detection information; a parameter prediction module is used to call the first analysis channel in the safety analysis center to perform predictive analysis on the first parameter detection information to obtain the first predicted parameter value at the second target time, wherein the first parameter detection information refers to the parameter detection information corresponding to the first characteristic indicator in the target multi-parameter detection information; a safety status analysis module is used to introduce a predetermined safety graph structure network to perform fusion analysis on the first predicted parameter value of the first characteristic indicator to obtain the target safety status index of the target GIL anti-vibration bracket at the second target time; a safety warning module is used to issue a first safety warning instruction if the target safety status index does not reach a predetermined status threshold, and perform safety warning processing on the target GIL anti-vibration bracket based on the first safety warning instruction.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Activate the SF6 gas pressure detector, and dynamically monitor the target GIL anti-vibration bracket through the SF6 gas pressure detector to obtain the SF6 gas pressure time series, providing basic information for subsequent safety status analysis. Determine whether the target gas pressure at the first target time in the SF6 gas pressure time series is within the predetermined pressure threshold; if it is, call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series to obtain the target predicted gas pressure at the second target time. When the SF6 gas pressure is initially judged to be normal, predictive analysis can be performed to understand the future gas pressure situation in advance, providing a reference for subsequent more comprehensive monitoring. Determine whether the target predicted gas pressure is within the predetermined pressure threshold; when the predicted gas pressure is abnormal, activate the multi-parameter detection equipment group to dynamically monitor the target GIL anti-vibration bracket, obtain more information about the operation of the GIL anti-vibration bracket, and evaluate its safety status from multiple dimensions. Perform predictive analysis on the indicators in the multi-parameter detection information, deeply mine the data information, and provide multi-dimensional data support for the final fusion analysis. A predetermined safety graph structure network is introduced to perform fusion analysis on the predicted parameter values ​​to obtain a target safety status index that can overall reflect the safety status of the GIL anti-vibration support. A judgment is made based on the calculated safety status index. If the target safety status index does not reach the predetermined status threshold, an early warning is issued in time to ensure the safe operation of the GIL anti-vibration support.

[0009] In summary, this application introduces a method that combines dynamic monitoring, multi-parameter fusion and predictive analysis, based on preliminary monitoring of SF6 gas pressure and comprehensive analysis of multi-parameter equipment, combined with a safety graph structure network to accurately evaluate the safety status of the GIL anti-vibration support. By establishing a hierarchical early warning mechanism and real-time response, early warning instructions can be issued in a timely manner when safety risks are discovered, enhancing the ability to identify and respond to potential risks, significantly improving the comprehensiveness, accuracy and foresight of GIL anti-vibration support safety monitoring, and improving the safety and reliability of GIL lines.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of a multi-parameter fusion GIL anti-vibration support safety monitoring method provided in an embodiment of the present application.

[0012] Figure 2 A schematic diagram of a process for obtaining a SF6 gas pressure feature set in a multi-parameter fusion GIL anti-vibration support safety monitoring method provided in an embodiment of the present application.

[0013] Figure 3 A schematic diagram of a flow chart of obtaining a target safety status index at a second target time in the multi-parameter fusion GIL anti-vibration support safety monitoring method provided in an embodiment of the present application.

[0014] Figure 4 A schematic diagram of the structure of a multi-parameter fusion GIL anti-vibration support safety monitoring system provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: gas pressure detection module 10, first judgment module 20, gas pressure prediction module 30, second judgment module 40, multi-parameter detection module 50, parameter prediction module 60, safety status analysis module 70, safety warning module 80. DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a multi-parameter fusion GIL anti-vibration support safety monitoring method and system, which solves the technical problems in the prior art that the safety status of the GIL anti-vibration support cannot be comprehensively evaluated and the potential risks of the GIL anti-vibration support cannot be identified in a timely manner due to the single monitoring parameters and lack of status prediction capability. This achieves the technical effect of improving the accuracy, comprehensiveness and detection efficiency of the safety monitoring of the GIL anti-vibration support, thereby enhancing the safe operation of the GIL line.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a multi-parameter fusion GIL anti-vibration support safety monitoring method, the method comprising:

[0018] Step S1: activating the SF6 gas pressure detector, and dynamically monitoring the target GIL anti-vibration support through the SF6 gas pressure detector to obtain the SF6 gas pressure time series.

[0019] Specifically, SF6 (sulfur hexafluoride) is the insulating medium in GIL. SF6 gas pressure detector is an instrument specially used to detect SF6 gas pressure. GIL (gas-insulated metal-enclosed transmission line) is a form of transmission line, and the anti-vibration bracket is a structural component used to support and fix GIL, which can reduce the impact of external vibration and other factors on GIL and ensure the stability and safety of GIL during operation. The target GIL anti-vibration bracket can be any GIL anti-vibration bracket in the GIL system that needs to be monitored for safety.

[0020] The flange joint of GIL is equipped with an SF6 leakage detection module, which is a hardware device for measuring SF6 gas pressure. The SF6 gas pressure detector is built into the SF6 leakage detection module. For example, select the SF6 sensor model BA-2200-004 and insert it into the SF6 closed cavity to measure the SF6 signal. After the safety monitoring starts, send a control command to activate the SF6 gas pressure detector, which continuously collects the SF6 gas pressure data inside the target GIL anti-vibration bracket. The collected SF6 gas pressure data is read through the data interface and sorted in the order of collection time to obtain the SF6 gas pressure time series. For example, if the pressure data is collected every 5 minutes and continuously collected for 1 hour, a SF6 gas pressure time series consisting of 12 pressure data points arranged in chronological order will be obtained. By acquiring SF6 gas pressure data in real time, preliminary monitoring data is provided for subsequent safety assessments.

[0021] Step S2: Determine whether the target gas pressure at the first target time in the SF6 gas pressure time sequence is within a predetermined pressure threshold.

[0022] Specifically, the predetermined pressure threshold is a pressure range pre-set according to the safe operation requirements of the GIL. The first target time refers to a specific time point in the monitoring time series data, which is usually a specific monitoring time set according to the safety monitoring frequency. For example, a specific monitoring time point is determined according to the frequency of a safety monitoring assessment every half an hour.

[0023] From the SF6 gas pressure time series data obtained in step S1, the target gas pressure value corresponding to the specific first target time is selected, and then compared with the preset predetermined pressure threshold. For example, the predetermined pressure threshold is set to 0.4 to 0.6MPa. If the pressure value at the first target time (such as 15 minutes after the start of collection) is 0.5MPa, it is within the threshold range. Preliminary screening of the initially collected SF6 gas pressure data can determine whether the current gas pressure is normal and determine further processing measures.

[0024] Step S3: If it is, call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series to obtain the target predicted gas pressure at the second target time.

[0025] Specifically, the safety analysis center is a platform for centralized safety-related data analysis and processing, integrating a variety of analysis algorithms and data processing modules, etc., for analyzing the collected SF6 gas pressure time series data. The second target time is the next specific monitoring time determined according to the set safety monitoring frequency, such as half an hour later.

[0026] If the target gas pressure is within the predetermined pressure threshold, it means that the gas pressure of the GIL anti-vibration bracket at that point in time is normal. At this time, it is also necessary to perform a predictive analysis on the SF6 gas pressure time series to determine whether there is a potential risk. The SF6 gas pressure time series data is transmitted to the safety analysis center. Inside the safety analysis center, these data are processed by the built-in predictive analysis algorithm to obtain the target predicted gas pressure at the second target time. By performing a predictive analysis on the SF6 gas pressure time series, the future state of the target GIL anti-vibration bracket can be predicted in advance, providing a basis for early warning before a fault occurs.

[0027] Step S4: Determine whether the target predicted gas pressure is within the predetermined pressure threshold.

[0028] Specifically, the target predicted gas pressure obtained in step S3 is compared with the predetermined pressure threshold again to determine whether it is within the normal range, so as to further determine whether there is a potential risk in the target GIL anti-vibration support, and if there is a risk, more in-depth monitoring is triggered.

[0029] Step S5: If not, activate the multi-parameter detection equipment group to dynamically monitor the target GIL anti-vibration support to obtain target multi-parameter detection information.

[0030] Specifically, the multi-parameter detection equipment group is a set of equipment used to perform multi-dimensional detection on the GIL anti-vibration bracket. It is radially installed on the GIL anti-vibration bracket through bolts on both sides. It has multiple sensor modules such as temperature sensor module, acceleration sensor module, stress sensor module, etc. built-in, which are used to obtain the temperature, vibration acceleration, stress and other parameters related to the operating status of the target GIL anti-vibration bracket. Among them, the temperature sensor module is used to measure the temperature signal of the measured point, such as the temperature sensor of model sht35; the acceleration sensor module is used to measure the vibration acceleration signal of the measured point, such as the single-axis acceleration sensor of model ADXL103. There are two strain sensor modules, which are radially and axially installed inside the multi-parameter detection equipment group, respectively, to measure stress-related signals, including tensile stress and torsional stress signals. The target multi-parameter detection information refers to various types of monitoring data obtained through the multi-parameter detection equipment group, which will be used to comprehensively evaluate the status of the equipment.

[0031] When step S4 determines that the target predicted gas pressure is not at the predetermined pressure threshold, the multi-parameter detection equipment group is started. Each sensor in this equipment group will detect the target GIL anti-vibration bracket at the same time. The detection data of each sensor is read through the data interface, and then these different detection parameters are summarized to obtain the target multi-parameter detection information. When the SF6 gas pressure prediction is abnormal, the operation information of the GIL anti-vibration bracket is obtained from multiple dimensions through multi-parameter detection, in preparation for a more comprehensive and accurate assessment of its safety status.

[0032] Step S6: Call the first analysis channel in the security analysis center to perform predictive analysis on the first parameter detection information to obtain the first predicted parameter value at the second target time, wherein the first parameter detection information refers to the parameter detection information corresponding to the first characteristic indicator in the target multi-parameter detection information.

[0033] Specifically, the safety analysis center is a platform for centralized processing and analysis of detection data, which can perform predictive analysis on the collected multi-parameter detection information. The safety analysis center includes multiple analysis channels, each of which corresponds to a characteristic indicator in the multi-parameter detection information, and is used to analyze and predict the parameter detection information corresponding to the characteristic indicator. Among them, the first analysis channel is a functional module for analyzing and predicting the first parameter detection information. This first parameter detection information can be the parameter detection information corresponding to any characteristic indicator (temperature, vibration acceleration, tensile stress, torsional stress, etc.) in the target multi-parameter detection information.

[0034] From the target multi-parameter detection information obtained in step S5, the first parameter detection information corresponding to the first characteristic indicator is extracted (for example, if the first characteristic indicator is temperature, then the temperature-related detection information is extracted), and then transmitted to the first analysis channel in the security analysis center. In this analysis channel, the parameter detection information is analyzed using its built-in predictive analysis algorithm (such as a temperature trend prediction algorithm based on machine learning) to obtain the first predicted parameter value at the second target time. Through the predictive analysis of multiple monitoring parameters, the changing trends of various parameters can be understood in advance, thereby performing a more accurate risk assessment.

[0035] Step S7: introducing a predetermined safety graph structure network to perform a fusion analysis on the first prediction parameter value of the first characteristic index to obtain a target safety state index of the target GIL anti-vibration support at the second target time.

[0036] Specifically, the safety graph structure network is a safety assessment model based on graph theory. It uses various monitoring parameters (such as gas pressure, vibration, temperature, etc.) as nodes for comprehensive analysis to obtain the overall safety status of the equipment. The target safety status index is a comprehensive index that reflects the safety status of the GIL anti-vibration bracket calculated based on various monitoring and prediction data.

[0037] The first prediction parameter value obtained in step S6 is input into a predetermined safety graph structure network. The network performs a fusion analysis on the first prediction parameter value according to a preset structure and algorithm (for example, according to the weight relationship and connection mode between the parameters), and finally obtains the target safety state index of the target GIL anti-vibration support at the second target time. Through fusion analysis, multiple prediction parameter values ​​are comprehensively processed to obtain an index that can comprehensively reflect the safety state of the GIL anti-vibration support, thereby improving the accuracy and comprehensiveness of safety monitoring and evaluation.

[0038] Step S8: If the target safety status index does not reach a predetermined status threshold, a first safety warning instruction is issued, and a safety warning process is performed on the target GIL anti-vibration support based on the first safety warning instruction.

[0039] Specifically, the first safety warning instruction is a safety warning instruction issued when the safety status index shows an abnormality. The predetermined state threshold is a predefined safety status index value, which indicates the minimum value of the safety status index required for the safe operation of the target GIL anti-vibration bracket. The target safety status index obtained in step S7 is compared with the predetermined state threshold. If the target safety status index does not reach the predetermined state threshold, it is considered that there is a safety risk in the target GIL anti-vibration bracket. At this time, the first safety warning instruction is issued, which will trigger the relevant safety warning equipment (such as flashing alarm lights, sending alarm information to the monitoring center, etc.) to perform safety warning processing on the target GIL anti-vibration bracket. Through the threshold-based safety warning, it is ensured that when potential safety problems occur in the GIL anti-vibration bracket, timely measures can be taken to avoid accidents, thereby improving the safety and reliability of the GIL system.

[0040] Further, if the target gas pressure is not within the predetermined pressure threshold, a second safety warning instruction is issued, and safety warning processing is performed on the target GIL anti-vibration support based on the second safety warning instruction.

[0041] Specifically, the second safety warning instruction is an instruction issued when the target gas pressure is not at the predetermined pressure threshold, which is used to trigger the safety warning processing of the target GIL anti-vibration bracket, and notify the relevant personnel or equipment system that the GIL anti-vibration bracket may have safety risks and measures need to be taken. When it is determined that the target gas pressure is not at the predetermined pressure threshold, the second safety warning instruction is issued. The second safety warning instruction instructs the relevant safety warning equipment to start working and perform safety warning processing on the target GIL anti-vibration bracket. For example, if the warning equipment includes an audible and visual alarm, the audible and visual alarm will be triggered to emit sound and light signals; if the monitoring system is connected to a remote monitoring center, an alarm message containing information such as the bracket number and abnormal pressure value will also be sent to the monitoring center. Through the above steps, it is possible to respond quickly to abnormal pressure conditions when the gas pressure is abnormal, avoid further deterioration of the state of the target GIL anti-vibration bracket or serious failure, thereby reducing equipment damage or safety accidents caused by delayed processing.

[0042] Further, step S3 includes:

[0043] Step S31: extracting the gas pressure prediction model embedded in the safety analysis center.

[0044] Step S32: Collect multi-domain features of the SF6 gas pressure time series to obtain a SF6 gas pressure feature set.

[0045] Step S33: inputting the SF6 gas pressure feature set into the gas pressure prediction model, and obtaining the target predicted gas pressure at the second target time through the gas pressure prediction model.

[0046] Among them, the gas pressure prediction model is an intelligent model obtained by supervised learning of a sample gas pressure data set constructed based on an SF6 gas pressure database, and the sample gas pressure data set includes a sample SF6 gas pressure feature set and a sample gas pressure at the second target time.

[0047] Specifically, the security analysis platform has a gas pressure prediction model pre-embedded in it. This gas pressure prediction model is pre-built through supervised learning of sample gas pressure data sets and is loaded into memory when the security analysis platform is started so that it can be called at any time.

[0048] The gas pressure prediction model is built based on the supervised learning algorithm. First, sample data is extracted from the SF6 gas pressure database to form a sample gas pressure data set. This SF6 gas pressure database is a database that stores data related to SF6 gas pressure, including sample SF6 gas pressure characteristics under different states and corresponding sample SF6 gas pressure time series data. From the SF6 gas pressure database, multiple different sample SF6 gas pressure characteristics (time characteristics, spectrum characteristics, etc.) are selected to form a sample SF6 gas pressure feature set, and the sample gas pressure corresponding to each sample SF6 gas pressure feature at the second target time (after a specific time interval) is extracted. These sample SF6 gas pressure characteristics and sample gas pressures are integrated to generate a sample gas pressure data set.

[0049] By using supervised learning algorithms such as neural networks and decision trees, the sample SF6 gas pressure feature set is used as input data, and the sample gas pressure at the second target time is used as the corresponding output result. The model is iteratively trained using this corresponding relationship between input and output, and the parameters of the model are continuously adjusted to minimize the error between the predicted result and the actual sample gas pressure, so that the model can learn the intrinsic relationship between the sample SF6 gas pressure feature set and the sample gas pressure at the second target time.

[0050] For the SF6 gas pressure time series data obtained in step S1, feature collection is performed from multiple different fields such as the time domain and the frequency domain. For example, features such as the pressure change rate and fluctuation period can be collected in the time domain, and the spectral features of the pressure signal can be collected in the frequency domain. These features collected from different domains are combined to obtain the SF6 gas pressure feature set. By comprehensively extracting the features of the SF6 gas pressure time series data from multiple angles, the data subsequently input into the gas pressure prediction model is more representative, which can improve the accuracy of the prediction.

[0051] Extract the gas pressure prediction model embedded in the safety analysis platform, and input the SF6 gas pressure feature set as input data into the gas pressure prediction model. The gas pressure prediction model processes the input SF6 gas pressure feature set according to its internal algorithm structure, and outputs the target predicted gas pressure at the second target time. For example, if the second target time is half an hour later, the model will predict the pressure value of the SF6 gas half an hour later based on the input feature set. Using the constructed gas pressure prediction model, the future gas pressure (at the second target time) is predicted based on the current SF6 gas pressure characteristics, which provides an important basis for evaluating the operating status of the GIL anti-vibration support in advance, so that potential safety risks can be discovered in advance.

[0052] Further, such as Figure 2 As shown, step S32 includes:

[0053] Step S321: collecting time domain characteristics of the SF6 gas pressure time series to obtain the SF6 gas pressure time domain characteristics.

[0054] Step S322: performing frequency domain conversion on the SF6 gas pressure time series to obtain a SF6 gas pressure spectrum.

[0055] Step S323: collecting frequency domain characteristics of the SF6 gas pressure spectrum to obtain frequency domain characteristics of the SF6 gas pressure.

[0056] Step S324: fusing the SF6 gas pressure time series and the SF6 gas pressure spectrum in the time-frequency domain to obtain the SF6 gas pressure time-frequency mode.

[0057] Step S325: performing modal decomposition on the SF6 gas pressure time-frequency mode and screening to obtain the optimal SF6 gas pressure modal component.

[0058] Step S326: collecting time-frequency domain features of the optimal SF6 gas pressure modal component to obtain the time-frequency domain features of the SF6 gas pressure.

[0059] Step S327: constructing the SF6 gas pressure feature set based on the SF6 gas pressure time domain feature, the SF6 gas pressure frequency domain feature and the SF6 gas pressure time-frequency domain feature.

[0060] Specifically, the time domain features of the SF6 gas pressure time series are collected, and features that can reflect the changes in gas pressure are extracted from the time series data, including the average value, standard deviation, maximum value, minimum value, and change rate of the gas pressure. The time domain features reflect the changing trend and dynamic characteristics of SF6 gas pressure over time.

[0061] The SF6 gas pressure time series is converted to the frequency domain through Fourier transform (such as discrete Fourier transform, fast Fourier transform, etc.), that is, the time series data is converted to the frequency domain to obtain the SF6 gas pressure spectrum. In the frequency domain, the frequency components of the gas pressure signal can be analyzed, such as whether there are fluctuations or periodic changes at a specific frequency.

[0062] The frequency domain characteristics of SF6 gas pressure describe the distribution of SF6 gas pressure at different frequencies. The collection of frequency domain characteristics helps to identify the periodicity and vibration mode of SF6 gas pressure changes. The frequency domain characteristics of SF6 gas pressure spectrum are collected, similar to the time domain characteristics collection. Features that can reflect the frequency characteristics of gas pressure are extracted from the spectrum data, including the main frequency, bandwidth, spectrum peak, etc. For example, the main frequency is determined by traversing the spectrum data to find the point with the largest amplitude; the bandwidth is calculated by finding the frequency range corresponding to a certain energy threshold or by counting the energy distribution in different frequency bands.

[0063] The SF6 gas pressure time series and the SF6 gas pressure spectrum are fused in the time and frequency domains, that is, the information in the time domain and frequency domains are combined by wavelet transform to obtain the time-frequency mode of SF6 gas pressure. For example, weights can be assigned according to the importance of time and frequency, and then the weighted time domain and frequency domain data are summed to obtain time-frequency modal data that can reflect both time changes and frequency characteristics. Time-frequency domain fusion can provide more comprehensive information on gas pressure changes, including both the trend of changes in time and the distribution of frequency.

[0064] The modal decomposition methods such as empirical mode decomposition or ensemble empirical mode decomposition are used to decompose the time-frequency mode of SF6 gas pressure, and the complex time-frequency signal is decomposed into multiple simple modal components. Then the optimal SF6 gas pressure modal component that best represents the gas pressure change characteristics is selected as the optimal modal component, such as the modal component with the highest energy. This step can help remove noise or irrelevant signal components and improve the accuracy of subsequent analysis.

[0065] The same method as the above-mentioned collection of time domain features and frequency domain features of SF6 gas pressure time series is adopted to collect time and frequency domain features of the optimal SF6 gas pressure modal component again, extract features from the perspective of time domain and frequency domain, and obtain the time and frequency domain features of SF6 gas pressure. These features will focus more on the key information of gas pressure changes and help improve the accuracy of the prediction model.

[0066] Based on the previously collected SF6 gas pressure time domain features, SF6 gas pressure frequency domain features and SF6 gas pressure time-frequency domain features, an SF6 gas pressure feature set is constructed. This feature set will be used as input data to train the gas pressure prediction model to achieve accurate prediction of future gas pressure.

[0067] Through the above steps, the changing characteristics of SF6 gas pressure can be comprehensively and deeply analyzed, providing comprehensive data support for subsequent predictive analysis, so that the gas pressure prediction model can understand and predict the changes in SF6 gas pressure from multiple angles, thereby improving the accuracy of the prediction.

[0068] Further, step S6 includes:

[0069] Step S61: generating a first detection scatter plot of the first characteristic indicator based on a first corresponding relationship between a first detection time and a first detection parameter in the first parameter detection information.

[0070] Step S62: performing a polynomial fitting analysis on the first detection scatter plot through the first analysis channel to obtain a first fitting spline curve.

[0071] Step S63: obtaining the first prediction parameter value at the second target time according to the first fitting spline curve.

[0072] Specifically, the first detection time can be any sensor detection time point in the first parameter detection information, and each first detection time corresponds to a first detection parameter at the detection time. For each first characteristic indicator, a data pair of the first detection time and the first detection parameter is extracted from its first parameter detection information. Then, with the first detection time as the horizontal coordinate and the first detection parameter as the vertical coordinate, these data pairs are plotted in a plane rectangular coordinate system, thereby generating a first detection scatter plot of the first characteristic indicator.

[0073] The first detection scatter plot is input into the first analysis channel. The first analysis channel uses a polynomial fitting analysis method to find an optimal polynomial function based on the data points in the scatter plot, so that the polynomial function is as close as possible to all the data points, thereby obtaining a first fitting spline curve. For example, if a quadratic polynomial fitting is used, a curve of the form y=ax will be obtained. 2 +bx+c, where x is the first detection time, y is the first detection parameter after fitting, and a, b, and c are coefficients obtained through fitting calculation. This first fitting spline curve is a curve that can reflect the trend of the first detection parameter changing with the first detection time, and provides a mathematical model for predicting the parameter value in the future (second target time).

[0074] According to the obtained first fitting spline curve, the second target time is substituted into the function expression of the curve to calculate the corresponding function value, which is the first prediction parameter value under the second target time. For example, if the first fitting spline curve is y=2x 2 +3x+1, the second target time x=5, then substitute x=5 into the function to calculate y=2×5 2 +3×5+1=66, this 66 is the first prediction parameter value under the second target time.

[0075] The above steps realize the predictive analysis of the first characteristic index through scatter plot and polynomial fitting analysis, and provide data basis for the safety monitoring and early warning of GIL anti-vibration support.

[0076] Further, step S7 includes:

[0077] Step S71: Analyze the predetermined safety graph structure network to obtain the first characteristic index and the first influencing factor of the safety state of the target GIL anti-vibration support.

[0078] Step S72: performing a weighted fusion analysis on the first prediction parameter value using the first influencing factor as a weight coefficient to obtain the target safety status index.

[0079] Specifically, the predetermined safety graph structure network includes multiple nodes and edges, where the nodes represent different characteristic indicators, and the edges represent the influence relationship and weight of these characteristic indicators on the safety status of the target GIL anti-vibration bracket. Use graph analysis algorithms, such as depth-first search, breadth-first search, etc. to traverse the predetermined safety graph structure network and identify the safety status influencing factor associated with the first characteristic indicator, namely the first influencing factor. This first influencing factor is a numerical value that indicates the degree of influence of the first characteristic indicator on the safety status of the target GIL anti-vibration bracket.

[0080] Each first prediction parameter value corresponds to a first influencing factor. These first influencing factors are used as weight coefficients to perform weighted summation on the first prediction parameter values. The influence of multiple characteristic indicators on the safety state and the prediction parameter values ​​are comprehensively considered to obtain the target safety state index. For example, the first prediction parameter values ​​corresponding to temperature, vibration acceleration, tensile stress, and torsional stress are a, b, c, and d, respectively, and the values ​​of their first influencing factors are α, β, γ, and δ, respectively. Through weighted summation, the target safety state index = αa+βb+γc+δd is obtained. This target safety state index provides a quantitative indicator for evaluating and monitoring the safety state of the GIL anti-vibration bracket.

[0081] Further, such as Figure 3 As shown, establishing the predetermined security graph structure network includes:

[0082] Step S711: constructing a set of influencing factors of the safety status of the target GIL anti-vibration support based on subjective and objective decision strategies.

[0083] Step S712: extract any impact factor from the impact factor set, and record the arbitrary impact factor as a graph structure vertex.

[0084] Step S713: acquiring any detection record containing the arbitrary influencing factor in the multi-parameter database, and obtaining any correlation degree of the arbitrary influencing factor based on the arbitrary detection record.

[0085] Step S714: Match any length level according to the arbitrary association degree, and record the arbitrary length level as the graph structure length.

[0086] Step S715: Establishing the predetermined secure graph structure network based on the mapping relationship between the graph structure vertices and the graph structure lengths.

[0087] Specifically, a set of influencing factors of the safety status of the target GIL anti-vibration bracket is formed based on subjective and objective decision-making strategies. Subjectively, the opinions of experts on the influencing factors of the safety status of the target GIL anti-vibration bracket and the general understanding of the safety of such brackets in the industry are collected. For example, experts may point out based on experience that certain specific structural parameters or environmental factors have an important impact on the safety status of the bracket. Objectively, the actual operation data and experimental test data of the target GIL anti-vibration bracket are analyzed to find out the variables related to the safety status. For example, it is found from a large amount of operation monitoring data that the changes in certain physical parameters (such as vibration frequency, amplitude, etc.) are closely related to the safety status of the bracket. The subjective and objective factors related to the safety status are combined to form a set of influencing factors of the safety status of the target GIL anti-vibration bracket. By forming a set of influencing factors through this comprehensive strategy, the obtained set of influencing factors can more comprehensively and accurately reflect the factors related to the safety status of the target GIL anti-vibration bracket, and provide basic data for constructing a predetermined safety graph structure network.

[0088] Select any one of the influencing factors from the obtained influencing factor set. For example, if the influencing factor set includes influencing factors such as vibration frequency, amplitude, and ambient temperature, select the influencing factor of vibration frequency. Define the selected influencing factor as a graph structure vertex. The graph structure vertex is the basic component of the graph, representing a node in the network. In the predetermined safety graph structure, each vertex corresponds to an influencing factor.

[0089] The multi-parameter database is a database containing information related to multiple parameters, covering data on various characteristics, operating status, etc. of the target GIL anti-vibration support. Perform query operations in the multi-parameter database to find any detection record containing the selected arbitrary influencing factor (such as vibration frequency). For example, in a database that stores a large amount of support operating status detection data, find all records containing vibration frequency data. Based on these detection records, the correlation between this arbitrary influencing factor and other factors, that is, the arbitrary correlation degree, is calculated through correlation analysis (such as the Pearson correlation coefficient). The arbitrary correlation degree reflects the closeness of the correlation of the corresponding arbitrary influencing factor in the entire GIL system, and is an important basis for determining the length of the graph structure.

[0090] The graph structure length is a value representing the length level of the edge in the graph structure obtained by matching any correlation of any influencing factor. It reflects the closeness of the relationship between different influencing factors to a certain extent and is used to construct the attributes of the edges in the predetermined secure graph structure network. According to the obtained arbitrary correlation value, the corresponding arbitrary length level is matched according to the pre-set correlation-length level matching rule. For example, if the correlation value is within a certain interval, it is matched to a specific length level, which can be represented by a number or a symbol.

[0091] According to the mapping relationship between the determined graph structure vertices and the graph structure lengths, a predetermined safety graph structure network is constructed. For example, if there are multiple influencing factors (graph structure vertices) and their corresponding graph structure lengths, these vertices can be connected through edges with corresponding lengths to form a network structure. This network provides a powerful analytical framework for the evaluation and prediction of safety status. Through this network, the degree of influence of each characteristic indicator on the safety status of the GIL anti-vibration support can be more accurately identified and evaluated.

[0092] Further, step S713 includes:

[0093] Step S713 - 1 : taking any influencing factor value corresponding to any influencing factor in any detection record as an independent variable.

[0094] Step S713-2: taking any safety status index of the GIL anti-vibration support in the any detection record as a dependent variable.

[0095] Step S713-3: Perform correlation analysis on the independent variable and the dependent variable to obtain the arbitrary correlation.

[0096] Specifically, when determining the arbitrary correlation of any influencing factor, first, from any test record obtained from the multi-parameter database, the numerical value corresponding to the selected arbitrary influencing factor is clarified and set as the independent variable. For example, in a test record containing multiple parameters, the specific numerical value (such as 50Hz) corresponding to the influencing factor of vibration frequency is determined, and it is used as the independent variable for subsequent correlation analysis. In the same test record, find out the arbitrary safety status index of the GIL anti-vibration bracket and use it as the dependent variable. This safety status index may be calculated in advance by other algorithms or evaluation methods, and represents the safety status of the bracket at that time in this test record. The independent variable (arbitrary influencing factor value) and the dependent variable (arbitrary safety status index) are analyzed using the correlation analysis method. For example, the Pearson correlation coefficient analysis method is used to calculate the correlation coefficient between the two variables based on a series of values ​​of the two variables. This correlation coefficient is the arbitrary correlation.

[0097] Determining the arbitrary correlation degree of any influencing factor is the key link in constructing a predetermined safety graph structure network, which provides the weight of the edge in the network, that is, the correlation strength between the influencing factors. Through the arbitrary correlation degree, the factors that have the greatest impact on the safety status of the GIL anti-vibration support can be identified, providing a scientific basis for safety monitoring and risk assessment.

[0098] In summary, the multi-parameter fusion GIL anti-vibration support safety monitoring method provided in the embodiment of the present application has the following technical effects:

[0099] By activating the SF6 gas pressure detector to dynamically monitor the target GIL anti-vibration bracket, the SF6 gas pressure time series is obtained to provide basic information for subsequent safety status analysis. Determine whether the target gas pressure at the first target time in the SF6 gas pressure time series is within the predetermined pressure threshold; if so, call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series to obtain the target predicted gas pressure at the second target time. When the SF6 gas pressure is initially judged to be normal, predictive analysis can be performed to understand the future gas pressure situation in advance, providing a reference for subsequent more comprehensive monitoring. Determine whether the target predicted gas pressure is within the predetermined pressure threshold; when the predicted gas pressure is abnormal, activate the multi-parameter detection equipment group to dynamically monitor the target GIL anti-vibration bracket, obtain more information about the operation of the GIL anti-vibration bracket, and evaluate its safety status from multiple dimensions. Perform predictive analysis on the indicators in the multi-parameter detection information, deeply mine the data information, and provide multi-dimensional data support for the final fusion analysis. A predetermined safety graph structure network is introduced to perform fusion analysis on the predicted parameter values ​​to obtain a target safety status index that can overall reflect the safety status of the GIL anti-vibration support. A judgment is made based on the calculated safety status index. If the target safety status index does not reach the predetermined status threshold, an early warning is issued in time to ensure the safe operation of the GIL anti-vibration support.

[0100] In general, the embodiment of the present application introduces a method combining dynamic monitoring, multi-parameter fusion and predictive analysis, based on preliminary monitoring of SF6 gas pressure and comprehensive analysis of multi-parameter equipment, combined with a safety graph structure network to accurately evaluate the safety status of the GIL anti-vibration support. By establishing a hierarchical early warning mechanism and real-time response, early warning instructions can be issued in a timely manner when safety risks are discovered, enhancing the ability to identify and respond to potential risks, significantly improving the comprehensiveness, accuracy and foresight of the safety monitoring of the GIL anti-vibration support, and improving the safety and reliability of the GIL line.

[0101] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a multi-parameter fusion GIL anti-vibration support safety monitoring system, the system comprising:

[0102] The gas pressure detection module 10 is used to activate the SF6 gas pressure detector and dynamically monitor the target GIL anti-vibration support through the SF6 gas pressure detector to obtain the SF6 gas pressure time series.

[0103] The first judgment module 20 is used to judge whether the target gas pressure at the first target time in the SF6 gas pressure time sequence is within a predetermined pressure threshold.

[0104] The gas pressure prediction module 30 is used to call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series if it is in the state, and obtain the target predicted gas pressure under the second target time.

[0105] The second judgment module 40 is used to judge whether the target predicted gas pressure is within the predetermined pressure threshold.

[0106] The multi-parameter detection module 50 is used to activate the multi-parameter detection equipment group to dynamically monitor the target GIL anti-vibration support if it is not in the state, so as to obtain target multi-parameter detection information.

[0107] The parameter prediction module 60 is used to call the first analysis channel in the security analysis center to perform predictive analysis on the first parameter detection information to obtain the first predicted parameter value at the second target time, wherein the first parameter detection information refers to the parameter detection information corresponding to the first characteristic indicator in the target multi-parameter detection information.

[0108] The safety status analysis module 70 is used to introduce a predetermined safety graph structure network to perform a fusion analysis on the first prediction parameter value of the first characteristic indicator to obtain a target safety status index of the target GIL anti-vibration support at the second target time.

[0109] The safety warning module 80 is used to issue a first safety warning instruction if the target safety status index does not reach a predetermined status threshold, and perform safety warning processing on the target GIL anti-vibration support based on the first safety warning instruction.

[0110] Furthermore, the system described in the embodiment of the present application further includes a second early warning module, and the second early warning module is further configured to perform the following steps:

[0111] If the target gas pressure is not within the predetermined pressure threshold, a second safety warning instruction is issued, and safety warning processing is performed on the target GIL anti-vibration support based on the second safety warning instruction.

[0112] Furthermore, the gas pressure prediction module 30 is further configured to perform the following steps:

[0113] Extract the gas pressure prediction model embedded in the safety analysis center; collect multi-domain features of the SF6 gas pressure time series to obtain an SF6 gas pressure feature set; input the SF6 gas pressure feature set into the gas pressure prediction model, and obtain the target predicted gas pressure at the second target time through the gas pressure prediction model; wherein, the gas pressure prediction model is an intelligent model obtained by supervised learning of a sample gas pressure data set constructed based on an SF6 gas pressure database, and the sample gas pressure data set includes a sample SF6 gas pressure feature set and a sample gas pressure at the second target time.

[0114] Furthermore, the gas pressure prediction module 30 is further configured to perform the following steps:

[0115] Perform time domain feature collection on the SF6 gas pressure time series to obtain time domain features of SF6 gas pressure; perform frequency domain conversion on the SF6 gas pressure time series to obtain a SF6 gas pressure spectrum; perform frequency domain feature collection on the SF6 gas pressure spectrum to obtain frequency domain features of SF6 gas pressure; perform time-frequency domain fusion on the SF6 gas pressure time series and the SF6 gas pressure spectrum to obtain time-frequency modes of SF6 gas pressure; perform modal decomposition on the SF6 gas pressure time-frequency modes and screen them to obtain optimal SF6 gas pressure modal components; perform time-frequency domain feature collection on the optimal SF6 gas pressure modal components to obtain time-frequency domain features of SF6 gas pressure; and construct the SF6 gas pressure feature set based on the SF6 gas pressure time domain features, the SF6 gas pressure frequency domain features, and the SF6 gas pressure time-frequency domain features.

[0116] Furthermore, the parameter prediction module 60 is further configured to perform the following steps:

[0117] Based on the first corresponding relationship between the first detection time and the first detection parameter in the first parameter detection information, a first detection scatter plot of the first characteristic indicator is generated; a polynomial fitting analysis is performed on the first detection scatter plot through the first analysis channel to obtain a first fitting spline curve; and according to the first fitting spline curve, the first predicted parameter value at the second target time is obtained.

[0118] Furthermore, the security status analysis module 70 is further configured to perform the following steps:

[0119] The predetermined safety graph structure network is analyzed to obtain the first characteristic index and the first influencing factor of the safety status of the target GIL anti-vibration support; and the first prediction parameter value is weightedly fused and analyzed with the first influencing factor as a weight coefficient to obtain the target safety status index.

[0120] Furthermore, the security status analysis module 70 is further configured to perform the following steps:

[0121] Based on subjective and objective decision-making strategies, a set of influencing factors of the safety status of the target GIL anti-vibration support is established; arbitrary influencing factors in the influencing factor set are extracted, and the arbitrary influencing factors are recorded as graph structure vertices; arbitrary detection records containing the arbitrary influencing factors are obtained in a multi-parameter database, and arbitrary correlation degrees of the arbitrary influencing factors are obtained based on the arbitrary detection records; arbitrary length levels are matched according to the arbitrary correlation degrees, and the arbitrary length levels are recorded as graph structure lengths; the predetermined safety graph structure network is established based on the mapping relationship between the graph structure vertices and the graph structure lengths.

[0122] Furthermore, the security status analysis module 70 is further configured to perform the following steps:

[0123] Taking any influencing factor value corresponding to any influencing factor in any detection record as an independent variable; taking any safety status index of the GIL anti-vibration support in any detection record as a dependent variable; and performing correlation analysis on the independent variable and the dependent variable to obtain the arbitrary correlation.

[0124] Through the above-mentioned detailed description of the multi-parameter fusion GIL anti-vibration support safety monitoring method in this specification, those skilled in the art can clearly understand the multi-parameter fusion GIL anti-vibration support safety monitoring system in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1, it has corresponding functional modules and beneficial effects. For relevant matters, please refer to the method part description.

[0125] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-parameter fusion GIL anti-vibration support safety monitoring method, characterized in that: include: activating an SF6 gas pressure detector, and dynamically monitoring the target GIL anti-vibration support through the SF6 gas pressure detector to obtain an SF6 gas pressure time series; Determining whether the target gas pressure at the first target time in the SF6 gas pressure time sequence is at a predetermined pressure threshold; If it is, call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series to obtain the target predicted gas pressure at the second target time; determining whether the target predicted gas pressure is within the predetermined pressure threshold; If not, activate the multi-parameter detection equipment group to dynamically monitor the target GIL anti-vibration bracket to obtain target multi-parameter detection information; Retrieving a first analysis channel in a security analysis center to perform predictive analysis on first parameter detection information to obtain a first predicted parameter value at the second target time, wherein the first parameter detection information refers to parameter detection information corresponding to a first characteristic indicator in the target multi-parameter detection information; Introducing a predetermined safety graph structure network to perform fusion analysis on the first prediction parameter value of the first characteristic index to obtain a target safety state index of the target GIL anti-vibration support at the second target time; If the target safety status index does not reach a predetermined status threshold, a first safety warning instruction is issued, and safety warning processing is performed on the target GIL anti-vibration support based on the first safety warning instruction.

2. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 1 is characterized in that: If the target gas pressure is not within the predetermined pressure threshold, a second safety warning instruction is issued, and safety warning processing is performed on the target GIL anti-vibration support based on the second safety warning instruction.

3. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 1 is characterized in that: The safety analysis center is called to perform predictive analysis on the SF6 gas pressure time series to obtain the target predicted gas pressure at the second target time, including: Extracting the gas pressure prediction model embedded in the safety analysis platform; Collecting multi-domain features of the SF6 gas pressure time series to obtain a SF6 gas pressure feature set; Inputting the SF6 gas pressure feature set into the gas pressure prediction model, and obtaining the target predicted gas pressure at the second target time through the gas pressure prediction model; Among them, the gas pressure prediction model is an intelligent model obtained by supervised learning of a sample gas pressure data set constructed based on an SF6 gas pressure database, and the sample gas pressure data set includes a sample SF6 gas pressure feature set and a sample gas pressure at the second target time.

4. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 3 is characterized in that: Multi-domain feature collection is performed on the SF6 gas pressure time series to obtain a SF6 gas pressure feature set, including: Collecting time domain characteristics of the SF6 gas pressure time series to obtain the SF6 gas pressure time domain characteristics; Performing frequency domain conversion on the SF6 gas pressure time series to obtain a SF6 gas pressure spectrum; Collecting frequency domain characteristics of the SF6 gas pressure spectrum to obtain frequency domain characteristics of the SF6 gas pressure; Performing time-frequency fusion on the SF6 gas pressure time series and the SF6 gas pressure spectrum to obtain the SF6 gas pressure time-frequency mode; Performing modal decomposition on the SF6 gas pressure time-frequency mode and screening to obtain the optimal SF6 gas pressure modal component; Collecting the time-frequency domain characteristics of the optimal SF6 gas pressure modal component to obtain the time-frequency domain characteristics of the SF6 gas pressure; The SF6 gas pressure feature set is established based on the SF6 gas pressure time domain features, the SF6 gas pressure frequency domain features and the SF6 gas pressure time-frequency domain features.

5. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 1 is characterized in that: Retrieving the first analysis channel in the security analysis center to perform predictive analysis on the first parameter detection information to obtain the first predicted parameter value at the second target time, including: generating a first detection scatter plot of the first characteristic indicator based on a first corresponding relationship between a first detection time and a first detection parameter in the first parameter detection information; Performing a polynomial fitting analysis on the first detection scatter plot through the first analysis channel to obtain a first fitting spline curve; The first prediction parameter value at the second target time is obtained according to the first fitting spline curve.

6. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 1 is characterized in that: Introducing a predetermined safety graph structure network to perform fusion analysis on the first prediction parameter value of the first characteristic indicator to obtain a target safety state index of the target GIL anti-vibration support at the second target time, including: Analyzing the predetermined safety graph structure network to obtain the first characteristic index and a first influencing factor of the safety state of the target GIL anti-vibration support; A weighted fusion analysis is performed on the first prediction parameter value using the first influencing factor as a weight coefficient to obtain the target safety status index.

7. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 1 is characterized in that: Introducing a predetermined safety graph structure network to perform fusion analysis on the first prediction parameter value of the first characteristic indicator to obtain a target safety state index of the target GIL anti-vibration support at the second target time, including: Establishing a set of influencing factors of the safety status of the target GIL anti-vibration support based on subjective and objective decision-making strategies; Extracting any impact factor from the impact factor set, and recording the arbitrary impact factor as a vertex of a graph structure; Acquire any detection record containing the arbitrary influencing factor in the multi-parameter database, and obtain any correlation degree of the arbitrary influencing factor based on the arbitrary detection record; Matching any length level according to the arbitrary association degree, and recording the arbitrary length level as the graph structure length; The predetermined secure graph structure network is established based on a mapping relationship between the graph structure vertices and the graph structure lengths.

8. The multi-parameter fusion GIL anti-vibration support safety monitoring method according to claim 7 is characterized in that: Obtaining any detection record containing the arbitrary influencing factor in the multi-parameter database, and obtaining any correlation degree of the arbitrary influencing factor based on the arbitrary detection record, including: Taking any influencing factor value corresponding to any influencing factor in any detection record as an independent variable; Taking any safety status index of the GIL anti-vibration support in any detection record as a dependent variable; A correlation analysis is performed on the independent variable and the dependent variable to obtain the arbitrary correlation.

9. The multi-parameter fusion GIL anti-vibration support safety monitoring system is characterized by: The system is used to execute the multi-parameter fusion GIL anti-vibration support safety monitoring method according to any one of claims 1 to 8, comprising: A gas pressure detection module is used to activate the SF6 gas pressure detector and dynamically monitor the target GIL anti-vibration support through the SF6 gas pressure detector to obtain the SF6 gas pressure time series; A first judgment module, used to judge whether the target gas pressure at the first target time in the SF6 gas pressure time sequence is within a predetermined pressure threshold; A gas pressure prediction module is used to call the safety analysis center to perform predictive analysis on the SF6 gas pressure time series if it is in, and obtain the target predicted gas pressure at the second target time; A second judgment module, used to judge whether the target predicted gas pressure is within the predetermined pressure threshold; A multi-parameter detection module, for activating a multi-parameter detection equipment group to dynamically monitor the target GIL anti-vibration support if it is not in the state, and obtaining target multi-parameter detection information; a parameter prediction module, configured to call a first analysis channel in a security analysis center to perform predictive analysis on first parameter detection information to obtain a first predicted parameter value at the second target time, wherein the first parameter detection information refers to parameter detection information corresponding to a first characteristic indicator in the target multi-parameter detection information; A safety state analysis module, used for introducing a predetermined safety graph structure network to perform a fusion analysis on the first prediction parameter value of the first characteristic index to obtain a target safety state index of the target GIL anti-vibration support at the second target time; The safety warning module is used to issue a first safety warning instruction if the target safety status index does not reach a predetermined status threshold, and perform safety warning processing on the target GIL anti-vibration support based on the first safety warning instruction.

Images