Fault Monitoring Method and System for Sulfur Hexafluoride Gas Purification and Filtration Devices

Abstract

This invention provides a fault monitoring method and system for a sulfur hexafluoride (SF6) gas purification and filtration device, relating to the field of gas purification technology. The method includes: obtaining a first monitoring block and a second monitoring block for the device; disassembling the SF6 gas purification and filtration device into components to obtain a purification component, a filtration component, and a valve and piping component; performing fault analysis on the purification component to obtain a first component fault analysis result; performing fault analysis on the filtration component to obtain a second component fault analysis result; performing fault analysis on the valve and piping component to obtain a third component fault analysis result; and performing global fault analysis to generate a filtration device fault analysis report. This invention solves the technical problem that existing technologies typically focus on fault monitoring of a single purification or filtration component, lacking coordinated monitoring and analysis of multiple components, thus failing to comprehensively reflect the overall health status of the device, leading to inaccurate and untimely fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of gas purification technology, and specifically to a fault monitoring method and system for a sulfur hexafluoride gas purification and filtration device. Background Technology

[0002] Sulfur hexafluoride (SF6) gas is a highly efficient insulating medium widely used in the insulation systems of power equipment (such as gas-insulated switchgear and transformers). In these devices, the purity of SF6 gas directly affects the insulation performance and safety of the equipment. Therefore, real-time monitoring and fault diagnosis of the operating status of SF6 gas purification and filtration devices are crucial.

[0003] However, existing technologies typically focus on monitoring a single component, such as a purification or filtration component, but lack the coordinated monitoring and analysis of multiple components. Since sulfur hexafluoride gas purification and filtration devices consist of multiple components that are interdependent, a failure in one component may affect other components and even lead to a decline in the performance of the entire sulfur hexafluoride gas purification and filtration device. Monitoring the failure of a single component cannot fully reflect the overall health status of the device, resulting in inaccurate and untimely fault diagnosis, which may ultimately lead to more serious failures. Summary of the Invention

[0004] This application provides a fault monitoring method and system for a sulfur hexafluoride gas purification and filtration device, aiming to solve the technical problem that the prior art usually focuses on fault monitoring of a single component of purification or filtration, lacks collaborative monitoring and analysis of multiple components, and cannot fully reflect the overall health status of the device, thus leading to inaccurate and untimely fault diagnosis.

[0005] The first aspect disclosed in this application provides a fault monitoring method for a sulfur hexafluoride (SF6) gas purification and filtration device. The method includes: when the SF6 gas purification and filtration device executes a purification and filtration scheme, obtaining a first monitoring block and a second monitoring block of the device; disassembling the SF6 gas purification and filtration device into components to obtain a purification component, a filter component, and a valve and piping component; performing fault analysis on the purification component based on the first monitoring block and the second monitoring block to obtain a first component fault analysis result; performing fault analysis on the filter component based on the first monitoring block and the second monitoring block to obtain a second component fault analysis result; performing fault analysis on the valve and piping component based on the first monitoring block and the second monitoring block to obtain a third component fault analysis result; and performing a global fault analysis on the SF6 gas purification and filtration device based on the first component fault analysis result, the second component fault analysis result, and the third component fault analysis result to generate a filter device fault analysis report.

[0006] The second aspect of this application discloses a fault monitoring system for a sulfur hexafluoride gas purification and filtration device. The system is used in the aforementioned fault monitoring method for a sulfur hexafluoride gas purification and filtration device. The system includes: a monitoring block acquisition unit, used to acquire a first monitoring block and a second monitoring block of the device when the sulfur hexafluoride gas purification and filtration device executes a purification and filtration scheme; a component disassembly unit, used to disassemble the sulfur hexafluoride gas purification and filtration device into components, obtaining purification components, filtration components, and valve and pipeline components; and a first fault analysis unit, used to analyze the faults of the purification components based on the first monitoring block and the second monitoring block. The system performs fault analysis on the filter assembly based on the first and second monitoring blocks of the device, obtaining a fault analysis result for the first component. A second fault analysis unit performs fault analysis on the valve and pipeline assembly based on the first and second monitoring blocks of the device, obtaining a fault analysis result for the third component. A global fault analysis unit performs global fault analysis on the sulfur hexafluoride gas purification filter based on the fault analysis results of the first, second, and third components, generating a filter assembly fault analysis report.

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

[0008] By breaking down the sulfur hexafluoride gas purification and filtration device into purification components, filtration components, and valve and piping components, and performing fault analysis on each component separately, it is ensured that each component can be analyzed individually based on its specific operating characteristics and fault modes, making fault location more accurate and efficient. Data from the first and second monitoring blocks are used to analyze the faults of each component. The first monitoring block is used to capture sudden faults, and the second monitoring block is used to capture slowly changing faults, ensuring that different fault types can be diagnosed in a timely and accurate manner. By comprehensively analyzing the fault analysis results of the first, second, and third components, the interaction between the components and the propagation effect of faults can be comprehensively evaluated, achieving global fault analysis. The effect of global fault analysis is that it can link the faults of each component, revealing the mutual influence and transmission paths between different faults. The global fault analysis report provides a systematic perspective for understanding the overall operating status of the equipment. This report not only provides maintenance personnel with detailed fault information but also serves as a decision support tool to help determine the optimal repair and maintenance strategies.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] Figure 1 This is a schematic flowchart of a fault monitoring method for a sulfur hexafluoride gas purification and filtration device provided in an embodiment of this application.

[0011] Figure 2 This is a schematic diagram of the fault monitoring system for a sulfur hexafluoride gas purification and filtration device provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached figures: Monitoring block acquisition unit 10, component-based splitting unit 20, first fault analysis unit 30, second fault analysis unit 40, third fault analysis unit 50, global fault analysis unit 60. Detailed Implementation

[0013] This application provides a fault monitoring method and system for a sulfur hexafluoride gas purification and filtration device, which solves the technical problem that the prior art usually focuses on fault monitoring of a single component of purification or filtration, lacks collaborative monitoring and analysis of multiple components, and cannot fully reflect the overall health status of the device, thus leading to inaccurate and untimely fault diagnosis.

[0014] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0015] Example 1, as Figure 1 As shown in the embodiments of this application, a fault monitoring method for a sulfur hexafluoride gas purification and filtration device is provided, the method comprising:

[0016] When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the first monitoring block and the second monitoring block of the device are obtained.

[0017] The execution of the purification and filtration scheme by the sulfur hexafluoride (SF6) gas purification and filtration unit is the initial state of the unit. This scheme guides the unit in purifying and filtering SF6 gas, including filtering impurities and cleaning or removing harmful components. This step indicates that the equipment is performing gas purification and filtration operations to ensure the gas meets predetermined quality standards. At this time, the unit's first and second monitoring blocks are obtained. A monitoring block refers to a data area within the entire unit acquired according to a monitoring time period. Each monitoring block collects specific data. The first monitoring block collects data over a shorter time period, including real-time monitoring of gas flow, pressure, and temperature. The second monitoring block collects data over a longer time period, including information on the unit's long-term stability and filtration efficiency. These monitoring blocks capture the unit's operating status at different time scales, facilitating subsequent fault diagnosis and performance evaluation.

[0018] The sulfur hexafluoride gas purification and filtration device is disassembled into components to obtain purification components, filtration components, and valve and pipeline components.

[0019] The modular disassembly of a sulfur hexafluoride (SF6) gas purification and filtration device involves breaking down the device using design drawings and other methods, and then modularizing it according to function to obtain different independent working units. Each component is a key functional module within the device, and can be individually used for fault diagnosis and performance testing. Specifically, the purification component is responsible for purifying the SF6 gas. This component includes gas treatment filter elements, adsorbents, or other chemical reaction devices to ensure the removal of impurities, contaminants, or other harmful substances from the gas. The filtration component is used to filter solid particles or droplets from the gas, including mechanical filters, liquid separators, or fine particle filtration systems. This component removes visible or minute impurities from the gas through physical methods. The valve and piping component controls the gas flow direction, flow rate, and pressure, including various valves (such as shut-off valves and regulating valves), pipes, and joints. This component ensures that the gas flows along a predetermined route and allows for flow rate or pressure control by adjusting the valves.

[0020] The purification component is analyzed for faults based on the first monitoring block and the second monitoring block of the device to obtain the fault analysis result of the first component.

[0021] Based on data from the first and second monitoring blocks of the device, fault analysis is performed on the purification components. Specifically, data processing algorithms identify data sets related to the purification components from the first and second monitoring blocks. Real-time data from the first monitoring block identifies sudden faults in the purification components, such as sudden equipment failures or abnormal fluctuations, and the causes of these faults are analyzed. Common sudden faults include equipment damage, sensor failures, and a sharp drop in filtration efficiency. Data from the second monitoring block identifies slowly changing faults in the purification components, such as prolonged performance degradation or gradually increasing wear, and the root causes of these problems are analyzed. After completing the above analysis, the analysis results of sudden and slowly changing faults are fused to obtain a comprehensive fault analysis result for the first component. This result indicates the fault type of the purification component and its possible causes.

[0022] The filter component is analyzed for faults based on the first monitoring block and the second monitoring block of the device to obtain the fault analysis result of the second component.

[0023] Similar to the fault analysis of the purification components, fault analysis of the filter components is performed based on data from the first and second monitoring blocks of the device. Specifically, the data in the first and second monitoring blocks is first filtered to identify characteristic data related to the filter components, such as pressure and flow rate changes. Real-time data from the first monitoring block is used to identify potential sudden faults in the filter components, typically manifesting as abnormal pressure increases, sudden flow drops, or filter clogging. Long-term data from the second monitoring block is used to analyze slowly changing faults, typically characterized by a gradual decrease in filtration efficiency or a gradual deterioration in system performance. The combined analysis results of both types of faults generate a fault analysis report for the second component, which not only identifies the fault type but also indicates the stage of the fault (e.g., sudden or gradual), assisting engineers in maintenance and optimization.

[0024] Based on the first monitoring block and the second monitoring block of the device, the valve and pipeline assembly is analyzed for faults, and the fault analysis results of the third component are obtained.

[0025] Similar to the fault analysis of purification and filtration components, fault analysis of valve and pipeline components is performed based on data from the first and second monitoring blocks of the device. Specifically, firstly, data in the first and second monitoring blocks is identified to obtain monitoring data for valves and pipelines. Using real-time data from the first monitoring block, sudden faults related to valve and pipeline components are detected, such as abnormal valve opening and closing, pipeline leaks, and abnormal flow fluctuations. These sudden faults often directly impact equipment operation and require rapid response. Using data from the second monitoring block, slowly changing faults in valve and pipeline components are identified, such as gradual valve wear, pipeline corrosion, and long-term flow rate declines. These problems typically affect the overall performance of the equipment gradually over time. The analysis results of both types of faults are combined to generate a third component fault analysis result. This result includes the specific fault type, possible causes, and their impact on equipment performance, helping to pinpoint the problem within the valve and pipeline components.

[0026] Based on the fault analysis results of the first component, the second component, and the third component, a global fault analysis is performed on the sulfur hexafluoride gas purification and filtration device, and a filtration device fault analysis report is generated.

[0027] After completing the fault analysis of the purification component, filtration component, and valve and piping component individually, a global fault analysis is performed. This global fault analysis combines the results of the individual component fault analyses to determine the failure modes and potential problems of the entire system. Specifically, it integrates the failure types, causes, and impacts on equipment performance of the purification, filtration, and valve and piping components. Based on the results of each fault analysis, fault propagation prediction is performed to analyze whether a failure in one component will lead to the failure of other components. For example, a failure in the valve and piping may lead to a decrease in the performance of the purification and filtration components, and vice versa. Based on the analysis results, repair or optimization suggestions are provided to help engineers determine maintenance priorities and quickly locate the problem. The entire global fault analysis is then used to generate a filtration unit fault analysis report. This report integrates the component-level fault analysis results, fault propagation characteristics, and possible repair measures to form a comprehensive fault diagnosis report.

[0028] Furthermore, based on the first monitoring block and the second monitoring block of the device, fault analysis is performed on the purification component to obtain the fault analysis result of the first component, including:

[0029] Data identification is performed on the first monitoring block and the second monitoring block of the device based on the purification component to obtain a first set of purification monitoring data and a second set of purification monitoring data. Based on the purification filtration scheme, a sudden fault analysis is performed on the purification component based on the first set of purification monitoring data to obtain a first fault analysis result. Based on the purification filtration scheme, a gradual fault analysis is performed on the purification component based on the second set of purification monitoring data to obtain a second fault analysis result. The first fault analysis result and the second fault analysis result are fused to generate a fault analysis result for the first component.

[0030] Based on the key performance indicators of the purification components, such as filtration efficiency, gas purification rate, and pressure and flow rate changes, the data in the first and second monitoring blocks of the device are classified into two data sets: Purification Monitoring Set 1 and Purification Monitoring Set 2. The Purification Monitoring Set 1 is a set of real-time data related to the purification components identified from the first monitoring block, which typically includes data on sudden changes, such as drastic fluctuations in pressure, flow rate, and temperature. The Purification Monitoring Set 2 is a set of long-term change data related to the purification components identified from the second monitoring block, which typically includes data related to slow-changing faults, such as gradual performance degradation and long-term stability issues.

[0031] Based on the purification and filtration scheme, the first set of purification monitoring data is analyzed to specifically analyze whether any sudden failures have occurred in the purification components during operation. These sudden failures may be caused by mechanical failures of the equipment, sensor failures, or changes in the external environment. For example, by using time series analysis, short-term anomaly detection, and other methods, combined with the expected performance of the purification and filtration scheme, drastic fluctuations or abnormal behaviors in equipment performance can be identified. Finally, by analyzing this data, the first failure analysis result is obtained, clarifying which sudden failure caused the abnormal performance of the purification components.

[0032] Using standard operating parameters from the purification and filtration solution, the second set of purification monitoring data is analyzed to specifically examine whether the purification components exhibit slow-changing, long-term faults. Typical slow-changing faults may be due to long-term efficiency decline caused by equipment wear, filter material aging, or pipe blockage. For example, for the second set of purification monitoring data, long-term anomaly identification techniques, such as trend analysis, regression analysis, or long-term pattern recognition, are used to identify slow fault modes. Based on the equipment's normal operating mode and the identified performance degradation, the analysis determines whether the purification components exhibit slow-changing faults caused by long-term operation or environmental changes. Ultimately, the second fault analysis results are obtained, indicating the type of slow-changing fault in the purification components and its possible causes.

[0033] The purpose of integrating the first and second fault analysis results is to combine short-term and long-term fault analyses to generate a comprehensive fault report for the purification component. This fusion analysis allows for better identification of the impact of multiple factors on equipment performance, especially when sudden and gradually changing faults occur simultaneously, potentially causing more complex effects on the equipment. The resulting first component fault analysis result is a comprehensive report that clearly identifies the fault type, severity, and impact of the purification component, providing guidance for subsequent repairs or optimizations.

[0034] Furthermore, based on the purification and filtration scheme, and according to the first set of purification monitoring data, a sudden fault analysis is performed on the purification component to obtain a first fault analysis result, including:

[0035] Based on a first time window, the state of the purification component is fitted according to the purification and filtration scheme to obtain first window state fitting data; short-term anomaly identification is performed on the first set of purification monitoring based on the first window state fitting data to obtain purification short-term anomaly identification results; integrated learning is performed on the purification short-term anomaly identification sample set and the purification sudden failure sample set of the purification component to generate a purification sudden failure analysis model; the purification short-term anomaly identification results are input into the purification sudden failure analysis model to obtain the first failure analysis result.

[0036] State fitting involves simulating the standard operating conditions of the purification component within a first time window, according to the purification and filtration scheme. This yields standard data for the equipment under normal operating conditions, which serves as a reference state for detecting subsequent anomalies. Specifically, the purification and filtration scheme specifies the operating conditions of the purification component, including standard parameters such as gas flow rate, temperature, pressure, and purification efficiency. Based on these parameters, the performance of the purification component under ideal operating conditions is simulated within the first time window. Data modeling techniques are used to simulate the ideal state of the purification component within the first time window, resulting in first-window state fitting data. This first-window state fitting data serves as standard data storage, representing the expected output of the purification component under optimal operating conditions.

[0037] Using the first window state fitting data as a standard, short-term anomaly identification is performed. The purpose is to detect whether there are significant deviations between the short-term operating data of the purification component within the first time window and the standard data. Short-term anomalies refer to sudden problems that occur in the equipment within a short period of time, such as sudden flow fluctuations or pressure anomalies. Specifically, for the first set of purification monitoring data (real-time data collected during equipment operation), abnormal fluctuations are detected by comparing it with the first window state fitting data. The comparison methods include threshold detection (e.g., fluctuations exceeding a predetermined range) and statistical analysis (e.g., standard deviation exceeding a certain range). Short-term anomaly identification algorithms, such as the sliding window method and mutation detection, are used to identify monitoring data that deviate significantly from the first window state fitting data, thereby determining short-term anomalies. The identified anomaly results are recorded as purification short-term anomaly identification results, which form the basis for subsequent fault analysis.

[0038] The purification short-term anomaly identification sample set consists of data samples obtained through short-term anomaly detection, representing anomalies that occur in the equipment within a short period of time, such as abnormal fluctuations in parameters like flow rate and pressure. The purification sudden failure sample set consists of manually labeled failure types corresponding to these anomalies, such as valve failure, filter blockage, and sensor failure, used for classifying and labeling identified anomalies. By combining these two sets, a model can be trained to learn the relationship between short-term anomalies and sudden failures, thereby enabling failure type prediction based on short-term anomaly data.

[0039] Specifically, using the short-term anomaly identification sample set and the sudden failure sample set of the purification component as training data, an ensemble learning method, such as random forest and gradient boosting tree, is used to train a classification model. The ensemble learning method combines multiple learning algorithms, and the prediction accuracy is optimized through the integration of the model, enabling the model to accurately identify the type of sudden failure when faced with new data. During the training process, the abnormal data is matched with manually labeled failure types, and the model is trained to identify the correlation between anomalies and failures. Finally, the trained purification sudden failure analysis model can automatically predict the specific failure type corresponding to short-term anomalies.

[0040] The results of short-term anomaly identification in the purification system are input into the pre-trained purification sudden fault analysis model. Based on the input results, the model matches the relationship between the short-term anomaly identification results and known fault types, makes predictions, analyzes which specific fault types are associated with the known short-term anomaly characteristics, and finally outputs the first fault analysis result. This is a prediction of the type of sudden fault, including the types of faults, such as filter blockage, valve damage, sensor failure, etc.

[0041] Furthermore, based on the purification and filtration scheme, and according to the second set of purification monitoring data, a slow-varying fault analysis is performed on the purification component to obtain a second fault analysis result, including:

[0042] Based on the second time window, the state of the purification component is fitted according to the purification and filtration scheme to obtain the second window state fitting data; long-term anomaly identification is performed on the second set of purification monitoring based on the second window state fitting data to obtain the long-term anomaly identification result; the long-term anomaly identification sample set of the purification component and the slowly changing fault sample set of the purification component are integrated and fused for training to generate a slowly changing fault analysis model; the long-term anomaly identification result is input into the slowly changing fault analysis model to obtain the second fault analysis result.

[0043] The second time window is used to analyze the performance changes of the purification components over a longer period, focusing on slow-changing faults such as gradual wear and tear and performance degradation. Referring to the purification and filtration scheme, within the second time window, the state of the purification components is fitted according to the standard operating parameters of the equipment, such as gas flow rate, pressure, and temperature, to simulate the ideal performance of the purification components over a long period. Through fitting, the standard operating state of the purification components within this time period is obtained, and the state fitting data of the second window is obtained. It represents the expected output of the purification components under normal conditions and according to the scheme, and serves as the benchmark data for subsequent long-term anomaly identification.

[0044] Based on the second window state fitting data, the second set of purification monitoring data is detected over a long time scale to identify the presence of slowly varying faults. Slowly varying faults refer to faults in which the performance of purification components gradually degrades or changes. These faults usually do not manifest as sudden anomalies, but rather as a gradual decline in equipment performance over time. Specifically, similar to short-term anomaly identification, for the second set of purification monitoring data (real-time data collected during equipment operation), long-term abnormal fluctuations are detected by comparing it with the second window state fitting data. Comparison methods include threshold detection (e.g., fluctuations exceeding a predetermined range) and statistical analysis (e.g., standard deviation exceeding a certain range). Short-term anomaly identification algorithms, such as the sliding window method and abrupt change detection, are used to identify monitoring data that deviate significantly from the second window state fitting data, thereby determining short-term anomalies. The identified anomaly results are recorded as long-term purification anomaly identification results, which form the basis for subsequent fault analysis.

[0045] The long-term anomaly identification sample set for purification components contains long-term anomaly data samples, reflecting potential anomaly patterns that may occur during long-term operation. The slowly varying fault sample set for purification consists of manually labeled fault types corresponding to these long-term anomalies, such as filter wear and component aging. An ensemble learning method is used to combine these two datasets, generating a slowly varying fault analysis model for purification through fusion training. During training, the model learns the correlation between anomaly data and slowly varying faults, thereby identifying potential slowly varying faults when new data arrives.

[0046] The long-term anomaly identification results of the purification system are input into the pre-trained purification slow-change fault analysis model. The model predicts the type of slow-change fault by comparing these long-term anomaly data with known slow-change fault modes. The output of the second fault analysis results includes slow-change fault types, such as filter aging, filter element wear, and pipeline corrosion.

[0047] Furthermore, based on the first monitoring block and the second monitoring block of the device, fault analysis is performed on the filter component to obtain the fault analysis result of the second component, including:

[0048] Data identification is performed on the first monitoring block and the second monitoring block of the device based on the filter component to obtain a first set of filter monitoring and a second set of filter monitoring. Based on the purification and filtration scheme, a sudden fault analysis is performed on the filter component based on the first set of filter monitoring to obtain a third fault analysis result. Based on the purification and filtration scheme, a gradual fault analysis is performed on the filter component based on the second set of filter monitoring to obtain a fourth fault analysis result. The third fault analysis result and the fourth fault analysis result are fused to generate the second component fault analysis result.

[0049] Data identification is performed on the first and second monitoring blocks of the device based on the key indicators of the filter components. Data characteristics related to the filter components are identified, including indicators such as filter pressure, flow rate, and particle concentration. These data are then cleaned and classified to obtain the first and second sets of filter monitoring data, which represent the filter component data under short-term and long-term operating conditions, respectively.

[0050] Similar to analyzing sudden failures of purification components, based on a first time window, the state of the filter component is fitted according to the purification filtration scheme. The fitted data is used as standard data to identify short-term anomalies in the first set of filter monitoring data. Through methods such as sliding window analysis, data points with large deviations from the standard state are identified to obtain the short-term anomaly identification results. The short-term anomaly identification results refer to the anomalies exhibited by the filter component in a short period of time, such as a sharp increase in pressure or a sudden drop in flow. Based on the filter component's short-term anomaly identification sample set and the filter sudden failure sample set, an integrated learning is performed to generate a filter sudden failure analysis model. The filter short-term anomaly identification results are input into the filter sudden failure analysis model to output the third failure analysis results. The third failure analysis results include sudden failures of the filter component, which are usually manifested as abnormal pressure increases, sudden drops in flow, or filter blockage.

[0051] Similar to analyzing the gradual changes in the purification components, based on a second time window, the state of the filter components is fitted according to the purification filtration scheme. The fitted data is used as standard data to perform long-term anomaly identification on the second set of filter monitoring data, obtaining the long-term anomaly identification results. The long-term anomaly identification results refer to the anomalies exhibited by the filter components over a long period of time, such as gradual clogging of the filter and decreased efficiency. The filter components' long-term anomaly identification sample set and the filter gradual change fault sample set are integrated and fused for training to generate a filter gradual change fault analysis model. The filter long-term anomaly identification results are input into the filter gradual change fault analysis model, and the fourth fault analysis result is output. The fourth fault analysis result includes the gradual change faults of the filter components. Gradual change faults refer to the faults that gradually occur in the filter components during long-term operation, such as gradual clogging of the filter and decreased efficiency.

[0052] The third and fourth fault analysis results are merged to form the second component fault analysis result, which provides a complete fault analysis of the filtering component, covering both short-term and long-term fault modes.

[0053] Furthermore, based on the first monitoring block and the second monitoring block of the device, fault analysis is performed on the valve and pipeline assembly to obtain the fault analysis result of the third component, including:

[0054] Data identification is performed on the first monitoring block and the second monitoring block of the device based on the valve and pipeline assembly to obtain a first set of valve and pipeline monitoring data and a second set of valve and pipeline monitoring data. Based on the purification and filtration scheme, a sudden fault analysis is performed on the valve and pipeline assembly based on the first set of valve and pipeline monitoring data to obtain a fifth fault analysis result. Based on the purification and filtration scheme, a gradual fault analysis is performed on the valve and pipeline assembly based on the second set of valve and pipeline monitoring data to obtain a sixth fault analysis result. The fifth fault analysis result and the sixth fault analysis result are then fused to generate the third component fault analysis result.

[0055] Based on the key indicators of the valve and pipeline components, data identification is performed on the first and second monitoring blocks of the device to identify data characteristics related to the valve and pipeline components, including valve on / off status, pressure changes, pipeline flow, leakage, and other indicators. These data are then cleaned and classified to obtain the first and second sets of valve and pipeline monitoring data, which represent the valve and pipeline component data under short-term and long-term operating conditions, respectively.

[0056] Similar to analyzing sudden failures of purification components, based on a first time window, the valve and pipeline components are fitted to a state according to the purification and filtration scheme. The fitted data is used as standard data to identify short-term anomalies in the first set of valve and pipeline monitoring data. Through methods such as sliding window analysis, data points with large deviations from the standard state are identified to obtain the valve and pipeline short-term anomaly identification results. The valve and pipeline short-term anomaly identification results refer to the anomalies exhibited by the valve and pipeline components in a short period of time, such as sudden changes in flow rate or drastic pressure fluctuations. Based on the valve and pipeline short-term anomaly identification sample set and the valve and pipeline sudden failure sample set, an integrated learning is performed to generate a valve and pipeline sudden failure analysis model. The valve and pipeline short-term anomaly identification results are input into the valve and pipeline sudden failure analysis model to output the fifth failure analysis results. The fifth failure analysis results include sudden failures of the valve and pipeline components. Sudden failures usually manifest as drastic changes in pressure or flow rate of the valve and pipeline components in a short period of time, which need to be identified and handled in a timely manner.

[0057] Similar to analyzing the gradual changes in the purification components, based on the second time window, the valve and pipeline components are fitted with their states according to the purification and filtration scheme. The fitted data is used as standard data to identify long-term anomalies in the second set of valve and pipeline monitoring data, obtaining the long-term anomaly identification results. The long-term anomaly identification results refer to the anomalies exhibited by the valve and pipeline components over a long period of time, such as valve wear and pipeline aging. The valve and pipeline components are integrated and fused with the long-term anomaly identification sample set and the gradual change in the valve and pipeline sample set to generate a gradual change in the valve and pipeline fault analysis model. The long-term anomaly identification results are input into the gradual change in the valve and pipeline fault analysis model, and the sixth fault analysis result is output. The sixth fault analysis result includes the gradual change in the valve and pipeline components. Gradual change in the fault refers to the faults that gradually occur in the valve and pipeline components during long-term operation, such as the valve gradually becoming unable to open completely or pipeline aging. Gradual change in the fault is difficult to detect directly through short-term anomalies, so long-term data analysis and trend identification are required.

[0058] The fifth and sixth fault analysis results are merged to form the third component fault analysis result, which provides a complete fault analysis of the valve and pipeline components, covering both short-term and long-term fault modes.

[0059] Furthermore, based on the fault analysis results of the first component, the second component, and the third component, a global fault analysis is performed on the sulfur hexafluoride gas purification and filtration device to generate a filtration device fault analysis report, including:

[0060] A 3D reconstruction of the sulfur hexafluoride gas purification and filtration device is performed to obtain a filtration device model. Fault propagation prediction is then performed on the filtration device model based on the fault analysis results of the first component to obtain a first fault propagation feature. Similarly, fault propagation prediction is performed on the filtration device model based on the fault analysis results of the second component to obtain a second fault propagation feature. Finally, fault propagation prediction is performed on the filtration device model based on the fault analysis results of the third component to obtain a third fault propagation feature. The fault analysis results of the first, second, and third components, along with the first, second, and third fault propagation features, are then combined to obtain a fault analysis report for the filtration device.

[0061] A 3D reconstruction of the sulfur hexafluoride (SF6) gas purification and filtration device is performed. This 3D reconstruction helps visualize the structure, component locations, and operating mechanisms of the entire SF6 gas purification and filtration device, thereby aiding in accurate analysis and location during fault propagation. Specifically, based on the design drawings, CAD files, or measured data of the SF6 gas purification and filtration device, a 3D modeling tool is used to reconstruct the entire device. During the 3D reconstruction process, each major component (including purification components, filtration components, and valve and piping components) is modeled in detail to ensure that their positions, connections, and structures in the model match the actual device. Ultimately, an accurate filtration device model is obtained, which can be used for fault propagation analysis, simulation, and optimization.

[0062] Based on the failure analysis results of the first component, i.e. the failure type of the purification component, the failure propagation prediction of the filtration device model is performed. The goal is to analyze how the failure of the purification component affects the entire device, especially the impact of the failure on other parts of the system. Specifically, based on the failure analysis results of the first component, the filtration device model is simulated using simulation tools to simulate the propagation path of the failure in the system. Based on the simulation results, the first characteristic of failure propagation is obtained, i.e. the potential impact of the failure of the purification component on other parts, and how the failure propagates in the entire device.

[0063] Similarly, based on the failure analysis results of the second component, i.e. the failure type of the filter component, the failure propagation prediction of the filter device model is performed. The goal is to analyze how the failure of the filter component affects the entire device, especially the impact of the failure on other parts of the system. Specifically, based on the failure analysis results of the second component, the filter device model is simulated using simulation tools to simulate the propagation path of the failure in the system. Based on the simulation results, the second characteristic of failure propagation is obtained, i.e. the potential impact of the failure of the filter component on other parts, and how the failure propagates in the entire device.

[0064] Similarly, based on the failure analysis results of the third component, namely the failure type of the valve and piping assembly, the failure propagation prediction of the filtration device model is performed. The goal is to analyze how the failure of the valve and piping assembly affects the entire device, especially the impact of the failure on other parts of the system. Specifically, based on the failure analysis results of the third component, the filtration device model is simulated using simulation tools to simulate the propagation path of the failure in the system. The third characteristic of failure propagation is obtained based on the simulation results, namely the potential impact of the failure of the valve and piping assembly on other parts, and how the failure propagates throughout the device. For example, the failure of the valve may cause flow problems, which in turn affect the efficiency of the purification and filtration components.

[0065] By integrating the fault analysis results of the first component, the second component, and the third component, as well as the first, second, and third characteristics of fault propagation, a comprehensive fault analysis report for the filtration device is generated. This report will provide decision support for the maintenance and repair of the sulfur hexafluoride gas purification filtration device, helping engineers to fully understand the source, impact, and propagation path of the fault.

[0066] Furthermore, when the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the device's first monitoring block and second monitoring block are obtained, including:

[0067] A first time window and a second time window are set, wherein the first time window is smaller than the second time window; when the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, a first monitoring block of the device is constructed according to the first time window, and a second monitoring block of the device is constructed according to the second time window.

[0068] Based on the operating characteristics of the sulfur hexafluoride gas purification and filtration device, time windows of different lengths are set for data acquisition and fault monitoring. The size of the first and second time windows directly affects the accuracy and real-time performance of the data. The first time window is set to a relatively short period, such as a few seconds to a few minutes, mainly used to monitor instantaneous changes in the equipment, such as pressure fluctuations, sudden increases in flow, and rapid temperature changes. The second time window is set to a relatively long period, such as several hours to several days or even months, used to capture long-term trends and gradually changing faults, such as equipment wear, efficiency decline, and component aging. Setting different time window lengths helps to balance the sensitivity of real-time monitoring and the long-term monitoring of equipment operation, ensuring accurate identification of different types of faults.

[0069] During equipment operation, real-time data is collected according to a set first and second time window, and corresponding first and second monitoring blocks are constructed. These monitoring blocks are used for subsequent fault diagnosis and performance analysis. Specifically, when the sulfur hexafluoride gas purification and filtration device starts executing the purification and filtration scheme, monitoring is first performed according to the first time window. The data during this period is mainly used to capture short-term changes and sudden faults in the equipment. For example, parameters such as gas flow rate, pressure, and temperature are recorded every second. Based on this real-time data, the first monitoring block is generated, providing the device's performance performance in a short period of time and providing basic data for the detection of sudden faults. At the same time, long-term operating data of the equipment is collected according to the second time window. Within this second time window, slowly changing performance indicators are monitored, such as equipment wear, gradual decrease in filtration efficiency, and gradual increase in pressure, generating a second monitoring block for the analysis and prediction of slowly changing faults.

[0070] Furthermore, constructing the first monitoring block of the device based on the first time window includes:

[0071] When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the sulfur hexafluoride gas purification and filtration device is monitored in real time according to the first time window to obtain a first window monitoring dataset; the first window monitoring dataset is cleaned to obtain a first cleaned dataset; the first cleaned dataset is encapsulated according to the blockchain to generate the first monitoring block of the device.

[0072] When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, sensors and monitoring equipment are used to collect various operating data of the device in real time within the first time window. For example, parameters such as gas flow rate, pressure, and temperature are recorded every second. These operating data are then organized according to the time period of the first time window (e.g., every second, every minute, etc.) to form the first window monitoring dataset.

[0073] Data cleaning is performed on the first window monitoring dataset, including: identifying and removing extreme values ​​that significantly deviate from the normal range, such as data fluctuations caused by sensor malfunctions or errors; supplementing missing values ​​in the dataset using interpolation, mean imputation, or other statistical methods; and removing noise from the data using smoothing algorithms such as moving averages and Gaussian filtering. After cleaning, a first cleaned dataset is generated to ensure the accuracy and reliability of the data.

[0074] Blockchain technology is used to encapsulate the cleaned data, ensuring its immutability and security. Specifically, the first cleaned dataset is converted into a block, which includes metadata such as the dataset content, timestamp, hash value, and signature. In the blockchain, each data block is encrypted using a hash function to ensure that the data cannot be tampered with at any time. The first monitoring block of the device is generated through blockchain technology. The first monitoring block of the device contains the cleaned monitoring data, information on the device's operating time period, and encrypted hash value. The use of blockchain ensures the security, traceability, and integrity of the data.

[0075] In summary, the fault monitoring method for a sulfur hexafluoride gas purification and filtration device provided in this application has the following technical effects:

[0076] By breaking down the sulfur hexafluoride gas purification and filtration device into purification components, filtration components, and valve and piping components, and performing fault analysis on each component separately, it is ensured that each component can be analyzed individually based on its specific operating characteristics and fault modes, making fault location more accurate and efficient. Data from the first and second monitoring blocks are used to analyze the faults of each component. The first monitoring block is used to capture sudden faults, and the second monitoring block is used to capture slowly changing faults, ensuring that different fault types can be diagnosed in a timely and accurate manner. By comprehensively analyzing the fault analysis results of the first, second, and third components, the interaction between the components and the propagation effect of faults can be comprehensively evaluated, achieving global fault analysis. The effect of global fault analysis is that it can link the faults of each component, revealing the mutual influence and transmission paths between different faults. The global fault analysis report provides a systematic perspective for understanding the overall operating status of the equipment. This report not only provides maintenance personnel with detailed fault information but also serves as a decision support tool to help determine the optimal repair and maintenance strategies.

[0077] Example 2, based on the same inventive concept as the fault monitoring method for the sulfur hexafluoride gas purification and filtration device in the foregoing examples, such as... Figure 2 As shown in the embodiment of this application, a fault monitoring system for a sulfur hexafluoride gas purification and filtration device is provided, the system comprising:

[0078] The monitoring block acquisition unit 10 is used to acquire the first monitoring block and the second monitoring block of the device when the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme.

[0079] The component disassembly unit 20 is used to disassemble the sulfur hexafluoride gas purification and filtration device into components to obtain purification components, filtration components, and valve and pipeline components.

[0080] The first fault analysis unit 30 is used to perform fault analysis on the purification component based on the first monitoring block and the second monitoring block of the device, and obtain the fault analysis result of the first component.

[0081] The second fault analysis unit 40 is used to perform fault analysis on the filter component based on the first monitoring block and the second monitoring block of the device, and obtain the fault analysis result of the second component.

[0082] The third fault analysis unit 50 is used to perform fault analysis on the valve and pipeline assembly based on the first monitoring block and the second monitoring block of the device, and obtain the fault analysis result of the third assembly.

[0083] The global fault analysis unit 60 is used to perform global fault analysis on the sulfur hexafluoride gas purification and filtration device based on the fault analysis results of the first component, the second component, and the third component, and generate a filtration device fault analysis report.

[0084] Furthermore, the first fault analysis unit 30 is used to perform the following operation steps:

[0085] Data identification is performed on the first monitoring block and the second monitoring block of the device based on the purification component to obtain a first set of purification monitoring data and a second set of purification monitoring data. Based on the purification filtration scheme, a sudden fault analysis is performed on the purification component based on the first set of purification monitoring data to obtain a first fault analysis result. Based on the purification filtration scheme, a gradual fault analysis is performed on the purification component based on the second set of purification monitoring data to obtain a second fault analysis result. The first fault analysis result and the second fault analysis result are fused to generate a fault analysis result for the first component.

[0086] Furthermore, the first fault analysis unit 30 is used to perform the following operation steps:

[0087] Based on a first time window, the state of the purification component is fitted according to the purification and filtration scheme to obtain first window state fitting data; short-term anomaly identification is performed on the first set of purification monitoring based on the first window state fitting data to obtain purification short-term anomaly identification results; integrated learning is performed on the purification short-term anomaly identification sample set and the purification sudden failure sample set of the purification component to generate a purification sudden failure analysis model; the purification short-term anomaly identification results are input into the purification sudden failure analysis model to obtain the first failure analysis result.

[0088] Furthermore, the first fault analysis unit 30 is used to perform the following operation steps:

[0089] Based on the second time window, the state of the purification component is fitted according to the purification and filtration scheme to obtain the second window state fitting data; long-term anomaly identification is performed on the second set of purification monitoring based on the second window state fitting data to obtain the long-term anomaly identification result; the long-term anomaly identification sample set of the purification component and the slowly changing fault sample set of the purification component are integrated and fused for training to generate a slowly changing fault analysis model; the long-term anomaly identification result is input into the slowly changing fault analysis model to obtain the second fault analysis result.

[0090] Furthermore, the second fault analysis unit 40 is used to perform the following operation steps:

[0091] Data identification is performed on the first monitoring block and the second monitoring block of the device based on the filter component to obtain a first set of filter monitoring and a second set of filter monitoring. Based on the purification and filtration scheme, a sudden fault analysis is performed on the filter component based on the first set of filter monitoring to obtain a third fault analysis result. Based on the purification and filtration scheme, a gradual fault analysis is performed on the filter component based on the second set of filter monitoring to obtain a fourth fault analysis result. The third fault analysis result and the fourth fault analysis result are fused to generate the second component fault analysis result.

[0092] Furthermore, the third fault analysis unit 50 is used to perform the following operation steps:

[0093] Data identification is performed on the first monitoring block and the second monitoring block of the device based on the valve and pipeline assembly to obtain a first set of valve and pipeline monitoring data and a second set of valve and pipeline monitoring data. Based on the purification and filtration scheme, a sudden fault analysis is performed on the valve and pipeline assembly based on the first set of valve and pipeline monitoring data to obtain a fifth fault analysis result. Based on the purification and filtration scheme, a gradual fault analysis is performed on the valve and pipeline assembly based on the second set of valve and pipeline monitoring data to obtain a sixth fault analysis result. The fifth fault analysis result and the sixth fault analysis result are then fused to generate the third component fault analysis result.

[0094] Furthermore, the global fault analysis unit 60 is used to perform the following operation steps:

[0095] A 3D reconstruction of the sulfur hexafluoride gas purification and filtration device is performed to obtain a filtration device model. Fault propagation prediction is then performed on the filtration device model based on the fault analysis results of the first component to obtain a first fault propagation feature. Similarly, fault propagation prediction is performed on the filtration device model based on the fault analysis results of the second component to obtain a second fault propagation feature. Finally, fault propagation prediction is performed on the filtration device model based on the fault analysis results of the third component to obtain a third fault propagation feature. The fault analysis results of the first, second, and third components, along with the first, second, and third fault propagation features, are then combined to obtain a fault analysis report for the filtration device.

[0096] Furthermore, the monitoring block acquisition unit 10 is used to perform the following operation steps:

[0097] A first time window and a second time window are set, wherein the first time window is smaller than the second time window; when the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, a first monitoring block of the device is constructed according to the first time window, and a second monitoring block of the device is constructed according to the second time window.

[0098] Furthermore, the monitoring block acquisition unit 10 is used to perform the following operation steps:

[0099] When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the sulfur hexafluoride gas purification and filtration device is monitored in real time according to the first time window to obtain a first window monitoring dataset; the first window monitoring dataset is cleaned to obtain a first cleaned dataset; the first cleaned dataset is encapsulated according to the blockchain to generate the first monitoring block of the device.

[0100] Through the foregoing detailed description of the fault monitoring method for a sulfur hexafluoride gas purification and filtration device, those skilled in the art can clearly understand the fault monitoring system for the sulfur hexafluoride gas purification and filtration device in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant parts can be referred to the method section.

[0101] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fault monitoring method for a sulfur hexafluoride gas purification and filtration device, characterized in that, The method includes: When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the first monitoring block and the second monitoring block of the device are obtained; The sulfur hexafluoride gas purification and filtration device is disassembled into components to obtain purification components, filtration components, and valve and pipeline components. Based on the first monitoring block and the second monitoring block of the device, the purification component is analyzed for faults to obtain the fault analysis result of the first component; Based on the first monitoring block and the second monitoring block of the device, the filter component is analyzed for faults to obtain the fault analysis result of the second component; Based on the first monitoring block and the second monitoring block of the device, the valve and pipeline assembly is analyzed for faults to obtain the fault analysis results of the third component; Based on the fault analysis results of the first component, the second component, and the third component, a global fault analysis is performed on the sulfur hexafluoride gas purification and filtration device to generate a filtration device fault analysis report. Specifically, the process of analyzing the purification component based on the first monitoring block and the second monitoring block of the device to obtain the first component fault analysis result includes: Based on the purification components, data identification is performed on the first monitoring block and the second monitoring block of the device to obtain a first set of purification monitoring and a second set of purification monitoring. Based on the purification and filtration scheme, the purification component is analyzed for sudden failure according to the first set of purification monitoring data to obtain the first failure analysis result; Based on the purification and filtration scheme, the purification component is subjected to slow-varying fault analysis according to the second set of purification monitoring, and a second fault analysis result is obtained. By combining the first fault analysis result and the second fault analysis result, the first component fault analysis result is generated; Specifically, based on the purification and filtration scheme, the purification components are analyzed for sudden faults according to the first set of purification monitoring data to obtain a first fault analysis result, including: Based on the first time window, the state of the purification component is fitted according to the purification and filtration scheme to obtain the state fitting data of the first window. Based on the fitted data of the first window state, short-term anomaly identification is performed on the first set of purification monitoring to obtain purification short-term anomaly identification results; The purification component's short-term anomaly identification sample set and purification sudden failure sample set are integrated and fused for learning to generate a purification sudden failure analysis model. The purification short-term anomaly identification result is input into the purification sudden fault analysis model to obtain the first fault analysis result; Specifically, based on the purification and filtration scheme, the purification components are subjected to slow-varying fault analysis according to the second set of purification monitoring data to obtain a second fault analysis result, including: Based on the second time window, the state fitting of the purification component is performed according to the purification and filtration scheme to obtain the second window state fitting data. Based on the fitted data of the second window state, long-term anomaly identification is performed on the second set of purification monitoring data to obtain the purification long-term anomaly identification result. Based on the purification component's long-term anomaly identification sample set and purification slow-change fault sample set, an integrated and fused training is performed to generate a purification slow-change fault analysis model. The long-term anomaly identification result of the purification system is input into the purification slow-change fault analysis model to obtain the second fault analysis result.

2. The fault monitoring method for a sulfur hexafluoride gas purification and filtration device as described in claim 1, characterized in that, Based on the first monitoring block and the second monitoring block of the device, fault analysis is performed on the filter component to obtain the fault analysis result of the second component, including: Based on the filtering component, data identification is performed on the first monitoring block and the second monitoring block of the device to obtain a first set of filtering monitoring and a second set of filtering monitoring; Based on the purification and filtration scheme, the filter component is analyzed for sudden failure according to the first set of filtration monitoring data to obtain a third failure analysis result. Based on the purification and filtration scheme, the filter component is subjected to slow-varying fault analysis according to the second set of filtration monitoring to obtain a fourth fault analysis result. The third fault analysis result and the fourth fault analysis result are combined to generate the second component fault analysis result.

3. The fault monitoring method for a sulfur hexafluoride gas purification and filtration device as described in claim 1, characterized in that, Based on the first monitoring block and the second monitoring block of the device, fault analysis is performed on the valve and pipeline assembly to obtain the fault analysis results of the third component, including: Data identification is performed on the first monitoring block and the second monitoring block of the device based on the valve and pipeline assembly to obtain a first set of valve and pipeline monitoring and a second set of valve and pipeline monitoring; Based on the purification and filtration scheme, the valve and pipeline components are analyzed for sudden faults according to the first set of valve and pipeline monitoring data to obtain the fifth fault analysis result; Based on the purification and filtration scheme, the valve and pipeline assembly is subjected to slow-change fault analysis according to the second set of valve and pipeline monitoring, and a sixth fault analysis result is obtained. The fifth fault analysis result and the sixth fault analysis result are combined to generate the third component fault analysis result.

4. The fault monitoring method for a sulfur hexafluoride gas purification and filtration device as described in claim 1, characterized in that, Based on the fault analysis results of the first component, the second component, and the third component, a global fault analysis is performed on the sulfur hexafluoride gas purification and filtration device, generating a filtration device fault analysis report, including: A three-dimensional reconstruction was performed on the sulfur hexafluoride gas purification and filtration device to obtain a model of the filtration device. Based on the fault analysis results of the first component, the filter device model is used to predict fault propagation and obtain the first feature of fault propagation. Based on the fault analysis results of the second component, the filter device model is used to predict fault propagation and obtain the second feature of fault propagation. Based on the fault analysis results of the third component, the filter device model is used to predict fault propagation and obtain the third feature of fault propagation. The failure analysis results of the first component, the second component, the third component, the first fault propagation feature, the second fault propagation feature, and the third fault propagation feature are compiled to obtain the failure analysis report of the filtering device.

5. The fault monitoring method for a sulfur hexafluoride gas purification and filtration device as described in claim 1, characterized in that, When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the device's first monitoring block and second monitoring block are obtained, including: Set a first time window and a second time window, where the first time window is smaller than the second time window; When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, a first monitoring block of the device is constructed according to the first time window, and a second monitoring block of the device is constructed according to the second time window.

6. The fault monitoring method for a sulfur hexafluoride gas purification and filtration device as described in claim 5, characterized in that, The first monitoring block of the device is constructed according to the first time window, including: When the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme, the sulfur hexafluoride gas purification and filtration device is monitored in real time according to the first time window to obtain the first window monitoring dataset. The first window monitoring dataset is cleaned to obtain a first cleaned dataset; Based on the blockchain, the first cleaning dataset is encapsulated to generate the first monitoring block of the device.

7. A fault monitoring system for a sulfur hexafluoride gas purification and filtration device, characterized in that, A fault monitoring method for a sulfur hexafluoride gas purification and filtration device according to any one of claims 1-6, the system comprising: The monitoring block acquisition unit is used to acquire the first monitoring block and the second monitoring block of the device when the sulfur hexafluoride gas purification and filtration device executes the purification and filtration scheme. A modular disassembly unit is used to disassemble the sulfur hexafluoride gas purification and filtration device into components to obtain purification components, filtration components, and valve and pipeline components. The first fault analysis unit is used to perform fault analysis on the purification component based on the first monitoring block and the second monitoring block of the device, and obtain the fault analysis result of the first component; The second fault analysis unit is used to perform fault analysis on the filter component based on the first monitoring block and the second monitoring block of the device, and obtain the fault analysis result of the second component; The third fault analysis unit is used to perform fault analysis on the valve and pipeline assembly based on the first monitoring block and the second monitoring block of the device, and obtain the fault analysis result of the third assembly. The global fault analysis unit is used to perform global fault analysis on the sulfur hexafluoride gas purification and filtration device based on the fault analysis results of the first component, the second component, and the third component, and generate a filtration device fault analysis report.

Images