Power equipment defect visual analysis method and system based on fault tree

Abstract

The invention discloses a power equipment defect visual analysis method and system based on a fault tree, and relates to the technical field of equipment defect analysis, and the method comprises the steps: obtaining equipment data and historical fault data in a power system, and analyzing the data of a newly added power system and an existing power system when the power system is newly added; the method comprises the following steps: analyzing equipment operation similarity between a newly-added power system and existing power systems according to equipment types, comprehensively considering the equipment types and equipment replenishment difficulty of the power systems, and selecting the most similar existing power system as a similar system to establish an operation feature comparison library; according to the method, the demand quantity of equipment caused by equipment faults is predicted by comprehensively considering the operation state of the equipment, the demand quantity is adjusted when the equipment is abnormal, the predicted demand quantity is improved, and a demand quantity and inventory comparison image coordinate system is established on a visual platform. And the accuracy of defect judgment of the power equipment is improved.

Description

Technical Field

[0001] This invention relates to the field of equipment defect analysis technology, specifically to a method and system for visual analysis of power equipment defects based on fault trees. Background Technology

[0002] In the field of power equipment defect analysis, existing technologies have significant limitations in the data acquisition stage. Most analytical methods only collect data from a portion of equipment within a single power system, failing to achieve systematic integration of data from multiple systems and all types of equipment. Furthermore, they often overlook key operational characteristics recorded when equipment malfunctions, resulting in a lack of comprehensive and coherent data support for subsequent analysis. This one-sidedness in data acquisition makes the analysis process susceptible to local data biases, making it difficult to accurately reflect the overall defect status of power equipment and creating hidden dangers for subsequent defect diagnosis and risk prediction. Existing technologies lack scientific and precise computational logic in similar system matching and equipment demand forecasting. Some methods rely solely on a single dimension such as the number of equipment when selecting similar power systems, failing to consider the differences in the impact of different types of equipment on the overall system operation, nor establishing a correlation between equipment failure frequency and system operating status. This leads to similar system matching results deviating from reality. When forecasting equipment demand based on these matching results, the lack of reliable references often results in significant errors between the forecasted results and actual demand, easily leading to excessive equipment reserves resulting in resource waste, or insufficient reserves affecting the normal operation and maintenance of the power system. In terms of visualization and decision support for power equipment defect management, existing technologies lack practicality. Most visualization solutions can only display isolated data such as equipment inventory or demand, failing to construct dynamic relationship charts between the two, and lacking differentiated visualization dimensions for different types of equipment. This presentation method makes it difficult for managers to intuitively grasp the dynamic balance of equipment supply and demand, and to quickly identify the risk of supply and demand imbalance. As a result, the decision-making process requires a significant amount of time to organize and analyze data, leading to low decision-making efficiency and potentially delaying the handling of power equipment defects, which can adversely affect the stable operation of the power system. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for visual analysis of power equipment defects based on fault trees, so as to solve the problems mentioned in the background art.

[0004] To address the aforementioned technical problems, this invention provides the following technical solution: a power equipment defect visualization analysis method based on fault tree, comprising the following steps: S1. Collect data from the power system to obtain equipment data and historical fault data. S2. When adding a new power system, analyze the data of the new power system and the existing power system, and analyze the similarity of equipment operation between the new power system and the existing power system according to the equipment type; S3. Taking into account the equipment types and equipment replenishment difficulties of the power system, analyze the similarity between the new power system and the existing power system, and then select the most similar existing power system as the similar system to establish an operational feature comparison library. S4. If the similarity between the newly added power system and similar systems is normal, the demand for equipment caused by equipment failure should be predicted by comprehensively considering the equipment operating status. S5. If the similarity between the newly added power system and similar systems is abnormal, adjust the demand to increase the predicted demand. S6. After completing the forecast of demand, establish a graph coordinate system for comparing demand and inventory on the visualization platform.

[0005] Furthermore, in step S1, after authorization, data is collected from M power systems to obtain equipment data and historical fault data from the M power systems. The number of N types of power equipment in the m-th power system is {A}. m_1 A m_2 ,…,A m_n ,…,A m_N Substituting each value into the database, we obtain the number of N types of electrical equipment in M ​​power systems. This number is then stored in a database. Historical fault data for the nth type of electrical equipment is collected from the mth power system. This data includes the historical fault types and the characteristics of the equipment at the time of the fault. Authorization is required before data collection to ensure the legality and compliance of the data source, mitigating risks associated with unauthorized data acquisition and laying a legal foundation for subsequent analysis. Furthermore, the data collection scope covers multiple power systems, breaking the limitations of single-system data. It not only integrates basic quantity information for various types of electrical equipment but also collects historical fault data for each type. The fault data includes both fault types and the characteristics of the equipment at the time of the fault, making the data more comprehensive. Finally, unified storage in a database ensures more organized data, facilitating rapid retrieval during subsequent analysis and improving the reliability of the entire analysis process from the source.

[0006] Furthermore, in step S2, when adding the kth power system, the matching degree between the kth power system and the mth power system is analyzed, and the number of N types of power equipment in the kth power system is {A}. k_1 A k_2 ,…,A k_n ,…,A k_N}, the number of N types of power devices in the m-th power system called {A m_1 A m_2 ,…,Am_n ,…,A m_N In the k-th power system, for the n-th type of power equipment, the historical fault data of the n-th type of power equipment includes X types of faults, where the number of occurrences of the x-th type of fault is B. k_x This leads to the occurrence frequency C of the x-th type of fault in the n-th type of power equipment in the k-th power system. k_x , T k Let x be the number of monitoring cycles in the k-th power system. Substitute each of these into x = 1, 2, ..., X to obtain the frequency of X types of faults in the n-th type of power equipment in the k-th power system {C}. k_1 C k_2 ,…,C k_x ,…,C k_X In the m-th power system, for the n-th type of power equipment, the number of occurrences of the x-th type of fault in the n-th type of power equipment is B. m_x This leads to the occurrence frequency C of the x-th type of fault in the n-th type of power equipment in the m-th power system. m_x , Substituting x = 1, 2, ..., X into each value, we obtain the frequency of fault type X of the nth type of power equipment in the mth power system {C}. m_1 C m_2 ,…,C m_x ,…,C m_X} Calculate the operational similarity D between the m-th power system and the n-th type of power equipment in the k-th power system. m_k_n : ; Substituting each value into n=1,2,…,N, we obtain the operational similarity {D} of the N types of power equipment between the m-th power system and the k-th power system. m_k_1 D m_k_2 ,…,D m_k_n ,…,D m_k_N This approach provides precise analytical basis for matching new power systems with existing systems. By comparing the number of various types of equipment in the new and existing systems, and combining this with the frequency of different faults in each type of equipment, similarity calculations are performed. This breaks through the limitations of single-dimensional judgment and can more meticulously reflect the correlation of operational characteristics between systems. Calculating operational similarity separately for each type of equipment fully considers the differences in characteristics between different devices, avoiding biases caused by general comparisons. This makes the similarity analysis more closely reflect actual operating conditions, laying a solid foundation for subsequently determining the overall system similarity and improving the scientific rigor and reliability of matching similar systems.

[0007] Furthermore, in step S3, after obtaining the operational similarity of N types of power equipment between the m-th power system and the k-th power system, the system similarity E between the m-th power system and the k-th power system is calculated. m_k : ; Among them, Z n Z represents the weight of the system similarity analysis for the nth type of power equipment. n It is the ratio of the previous freight cycle of the nth type of power equipment to the sum of the previous freight cycles of the Nth type of power equipment, with the current time as the endpoint. The freight cycle represents the length of time from the submission of equipment demand to the receipt of power equipment. Substituting each value into m = 1, 2, ..., M, we obtain the system similarity {E} between the M power systems and the k-th power system. 1_k E 2_k ,…,E m_k ,…,E M_k}, and then obtain the system similarity {E} 1_k E 2_k ,…,E m_k ,…,E M_k The system with the highest similarity is selected as the similar system to the k-th power system. An operational feature comparison library is established, comprising: operational features of equipment in a set of similar systems obtained at intervals of one data collection period, and the number of equipment failures within one freight cycle after collecting the operational features of each set of similar systems. This improves the rationality and reliability of the system similarity analysis. By introducing equipment weights based on freight cycles, it distinguishes the differences in the influence of different equipment in the system, avoiding similarity calculation biases caused by treating all types of equipment equally. This makes the overall system similarity more closely reflect the differences in the importance of equipment in actual operation, improving the rationality of the calculation results. Simultaneously, by selecting the system with the highest similarity as a reference, the accuracy of the matching of similar systems is ensured, providing a reliable reference object for subsequent analysis. Furthermore, the established operational feature comparison library links the operational features of similar systems with subsequent failure data, providing direct and effective data support for subsequent demand judgments based on operational features, further solidifying the foundation of the analysis work.

[0008] Furthermore, in step S4, when the system similarity between the similar system and the k-th system is higher than the preset system similarity threshold, the similarity level is judged to be normal, and the operating characteristics of any power device α in the n-th type of equipment in the k-th power system are collected in real time. The current operating characteristics of power device α are {G1, G2, ..., G...} y ,…,G Y}, call the runtime characteristic comparison library to obtain the Q group of runtime characteristics for the nth type of device, and the qth group of runtime characteristics is {G 1_q G 2_q ,…,G y_q ,…,G Y_q}, and then obtain the similarity between the current running feature and the y-th feature of the q-th group of running features. The similarity between the current running feature and the y-th feature of the q-th group of running features is |(G y -G y_q ) / G y |, and then obtain the comprehensive similarity H between the current running features and the q-th group of running features. q The comprehensive similarity between the current operating characteristics and the q-th group of operating characteristics is represented by the average similarity of the Y features between the current operating characteristics and the q-th group of operating characteristics. Substituting each feature into q = 1, 2, ..., Q, we obtain the comprehensive similarity between the current operating characteristics and the Q groups of operating characteristics. The group of operating characteristics with the highest comprehensive similarity is selected as the reference operating characteristics. The number of equipment failures β within a freight cycle of the n-th type of equipment after collecting the reference operating characteristics is then used as the demand for power equipment α at the current moment. This improves the accuracy and reliability of equipment demand assessment. When similar systems match normally, by collecting the current operating characteristics of the equipment in real time and comparing them with historical data in the operating characteristic comparison database, the current state and historical operating patterns can be effectively correlated. By calculating the comprehensive similarity and selecting the most suitable reference characteristics, a high degree of fit between the reference basis and the current equipment operating state is ensured, avoiding bias from subjective judgment or single feature comparison. Using the historical failure count corresponding to the reference characteristics as the current demand directly establishes a correlation between operating characteristics and actual demand, making demand assessment based on real operating data, improving the practicality of the results, and providing an accurate and reliable basis for equipment reserve planning.

[0009] Furthermore, in step S5, when the system similarity between the similar system and the k-th system is less than or equal to a preset system similarity threshold, an abnormal similarity is determined, and the demand for power equipment α at the current moment is adjusted to [a value]. R is a demand adjustment coefficient, and R is a real number greater than 1, which is used to obtain the demand of all power equipment in the k-th power system. This provides a risk mitigation and accurate correction mechanism for judging equipment demand in scenarios with abnormal similarity. When the similarity between similar systems and newly added systems does not reach the threshold, the reliability of the original reference data will have gaps, and directly using the previous demand results is prone to underestimation due to reference bias. By introducing a demand adjustment coefficient greater than 1, the demand results corresponding to the original reference fault number are adjusted upwards, which can effectively make up for the judgment error caused by insufficient similarity, and avoid the situation where equipment shortages are caused by underestimation of demand, thus affecting the normal operation and maintenance of the power system. This targeted adjustment not only retains the basic value of the reference data, but also fully considers the risks of abnormal scenarios, so that equipment demand forecasts can still adapt to actual needs in complex situations, improve the fault tolerance and reliability of demand judgment, and ensure the rationality of equipment reserve planning for newly added systems.

[0010] Furthermore, in step S6, a demand and inventory comparison image coordinate system is established on the visualization platform. The horizontal axis represents the time point, and the vertical axis represents the demand and inventory. The number of demand and inventory comparison image coordinate systems is the same as the total number of power equipment in the k-th power system. When the demand exceeds the inventory, an inventory shortage alarm is issued, prompting managers to replenish the inventory. This makes the supply and demand management of power equipment more intuitive and efficient, while also establishing a timely early warning mechanism for inventory risks. By building a demand and inventory comparison image on the visualization platform, the originally scattered supply and demand data is transformed into an intuitive and correlated presentation in the time dimension. Managers no longer need to manually organize and analyze complex data, and can quickly and clearly grasp the dynamic changes in the supply and demand of various types of equipment. When the demand exceeds the inventory, an automatic alarm is issued, which can remind managers to replenish the inventory in time, avoiding equipment shortages due to failure to detect inventory shortages in time, which could affect the operation and maintenance progress or stable operation of the power system. This significantly improves the response efficiency of equipment inventory management and provides a strong guarantee for the continuous and stable operation of the power system.

[0011] The power equipment defect visualization analysis system based on fault tree includes: power data acquisition module, equipment similarity analysis module, system similarity selection module, normal demand prediction module, abnormal demand adjustment module, and supply and demand visualization planning module. The power data acquisition module is used to acquire data from the power system, including equipment data and historical fault data. The equipment similarity analysis module is used to analyze the data of the new power system and the existing power system when adding a new power system, and to analyze the equipment operation similarity between the new power system and the existing power system according to the equipment type. The system similarity selection module is used to comprehensively consider the equipment type and equipment replenishment difficulty of the power system, analyze the similarity between the new power system and the existing power system, and then select the most similar existing power system as the similar system to establish an operational feature comparison library. The normal demand forecasting module is used to predict the demand for equipment caused by equipment failure if the similarity between the newly added power system and similar systems is normal, taking into account the equipment operating status. The abnormal demand adjustment module is used to adjust the demand if the similarity between the newly added power system and similar systems is abnormal, thereby increasing the predicted demand. The supply and demand visualization planning module is used to predict the demand and then establish a coordinate system for comparing the demand and inventory on the visualization platform.

[0012] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: On the one hand, by authorizing the collection of basic equipment data and historical fault data from multiple systems and establishing a standardized database, the completeness of the data required for analysis is ensured. This not only covers the quantity of equipment but also incorporates fault types and corresponding equipment characteristics, providing a comprehensive and accurate data foundation for subsequent defect analysis. This avoids analytical biases caused by missing or isolated data, thus ensuring the reliability of power equipment defect analysis from the source.

[0013] On the one hand, by calculating the similarity of equipment operation and the overall system similarity in a hierarchical manner, and combining equipment weights, scientific screening of similar systems is achieved, effectively improving the accuracy of system matching. On the other hand, relying on the comparison library of similar system operation characteristics, the operation characteristics are correlated with the number of subsequent failures to accurately determine the equipment demand. For cases of abnormal similarity, the demand forecast results are further optimized by adjusting the coefficients, providing a precise basis for equipment reserve planning and reducing resource waste or supply shortages caused by misjudgment of demand.

[0014] On the other hand, by leveraging a visualization platform to create a comparative image of demand and inventory, abstract data is transformed into intuitive time-quantity relationship charts. Furthermore, a separate coordinate system is constructed for each type of equipment, making the dynamics of equipment supply and demand readily apparent. This visualization approach allows managers to quickly grasp equipment status, promptly identify supply-demand imbalance risks, shorten decision-making cycles, improve the efficiency of power equipment defect management and resource allocation, and ensure the stable operation of the power system. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a structural diagram of the power equipment defect visualization analysis system based on fault tree according to the present invention; Figure 2 This is a flowchart of the power equipment defect visualization analysis method based on fault tree according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 and Figure 2 This invention provides a technical solution: a power equipment defect visualization analysis method based on fault tree, comprising the following steps: S1. Collect data from the power system to obtain equipment data and historical fault data. S2. When adding a new power system, analyze the data of the new power system and the existing power system, and analyze the similarity of equipment operation between the new power system and the existing power system according to the equipment type; S3. Taking into account the equipment types and equipment replenishment difficulties of the power system, analyze the similarity between the new power system and the existing power system, and then select the most similar existing power system as the similar system to establish an operational feature comparison library. S4. If the similarity between the newly added power system and similar systems is normal, the demand for equipment caused by equipment failure should be predicted by comprehensively considering the equipment operating status. S5. If the similarity between the newly added power system and similar systems is abnormal, adjust the demand to increase the predicted demand. S6. After completing the forecast of demand, establish a graph coordinate system for comparing demand and inventory on the visualization platform.

[0018] In step S1, after authorization, data is collected from M power systems to obtain equipment data and historical fault data from the M power systems. The number of N types of power equipment in the m-th power system is {A}. m_1 A m_2 ,…,A m_n ,…,A m_NSubstituting each value into the database, we obtain the number of N types of electrical equipment in M ​​power systems. This number is then stored in a database. Historical fault data for the nth type of electrical equipment is collected from the mth power system. This data includes the historical fault types and the characteristics of the equipment at the time of the fault. Authorization is required before data collection to ensure the legality and compliance of the data source, mitigating risks associated with unauthorized data acquisition and laying a legal foundation for subsequent analysis. Furthermore, the data collection scope covers multiple power systems, breaking the limitations of single-system data. It not only integrates basic quantity information for various types of electrical equipment but also collects historical fault data for each type. The fault data includes both fault types and the characteristics of the equipment at the time of the fault, making the data more comprehensive. Finally, unified storage in a database ensures more organized data, facilitating rapid retrieval during subsequent analysis and improving the reliability of the entire analysis process from the source.

[0019] In step S2, when adding the kth power system, the matching degree between the kth power system and the mth power system is analyzed, and the number of N types of power equipment in the kth power system is {A}. k_1 A k_2 ,…,A k_n ,…,A k_N}, the number of N types of power devices in the m-th power system called {A m_1 A m_2 ,…,A m_n ,…,A m_N In the k-th power system, for the n-th type of power equipment, the historical fault data of the n-th type of power equipment includes X types of faults, where the number of occurrences of the x-th type of fault is B. k_x This leads to the occurrence frequency C of the x-th type of fault in the n-th type of power equipment in the k-th power system. k_x , T k Let x be the number of monitoring cycles in the k-th power system. Substitute each of these into x = 1, 2, ..., X to obtain the frequency of X types of faults in the n-th type of power equipment in the k-th power system {C}. k_1 C k_2 ,…,C k_x ,…,C k_X In the m-th power system, for the n-th type of power equipment, the number of occurrences of the x-th type of fault in the n-th type of power equipment is B. m_x This leads to the occurrence frequency C of the x-th type of fault in the n-th type of power equipment in the m-th power system. m_x , Substituting x = 1, 2, ..., X into each value, we obtain the frequency of fault type X of the nth type of power equipment in the mth power system {C}. m_1 C m_2 ,…,C m_x ,…,C m_X} Calculate the operational similarity D between the m-th power system and the n-th type of power equipment in the k-th power system. m_k_n : ; Substituting each value into n=1,2,…,N, we obtain the operational similarity {D} of the N types of power equipment between the m-th power system and the k-th power system. m_k_1 D m_k_2 ,…,D m_k_n ,…,D m_k_N This approach provides precise analytical basis for matching new power systems with existing systems. By comparing the number of various types of equipment in the new and existing systems, and combining this with the frequency of different faults in each type of equipment, similarity calculations are performed. This breaks through the limitations of single-dimensional judgment and can more meticulously reflect the correlation of operational characteristics between systems. Calculating operational similarity separately for each type of equipment fully considers the differences in characteristics between different devices, avoiding biases caused by general comparisons. This makes the similarity analysis more closely reflect actual operating conditions, laying a solid foundation for subsequently determining the overall system similarity and improving the scientific rigor and reliability of matching similar systems.

[0020] In step S3, after obtaining the operational similarity of N types of power equipment between the m-th power system and the k-th power system, the system similarity E between the m-th power system and the k-th power system is calculated. m_k : ; Among them, Z n Z represents the weight of the system similarity analysis for the nth type of power equipment. n It is the ratio of the previous freight cycle of the nth type of power equipment to the sum of the previous freight cycles of the Nth type of power equipment, with the current time as the endpoint. The freight cycle represents the length of time from the submission of equipment demand to the receipt of power equipment. Substituting each value into m = 1, 2, ..., M, we obtain the system similarity {E} between the M power systems and the k-th power system. 1_k E 2_k ,…,E m_k ,…,E M_k}, and then obtain the system similarity {E} 1_k E 2_k ,…,E m_k ,…,E M_kThe system with the highest similarity is selected as the similar system to the k-th power system. An operational feature comparison library is established, comprising: operational features of equipment in a set of similar systems obtained at intervals of one data collection period, and the number of equipment failures within one freight cycle after collecting the operational features of each set of similar systems. This improves the rationality and reliability of the system similarity analysis. By introducing equipment weights based on freight cycles, it distinguishes the differences in the influence of different equipment in the system, avoiding similarity calculation biases caused by treating all types of equipment equally. This makes the overall system similarity more closely reflect the differences in the importance of equipment in actual operation, improving the rationality of the calculation results. Simultaneously, by selecting the system with the highest similarity as a reference, the accuracy of the matching of similar systems is ensured, providing a reliable reference object for subsequent analysis. Furthermore, the established operational feature comparison library links the operational features of similar systems with subsequent failure data, providing direct and effective data support for subsequent demand judgments based on operational features, further solidifying the foundation of the analysis work.

[0021] In step S4, when the system similarity between the similar system and the k-th system is higher than the preset system similarity threshold, the similarity level is judged to be normal. The operating characteristics of any power device α in the n-th type of equipment in the k-th power system are collected in real time. The current operating characteristics of power device α are {G1, G2, ..., G...} y ,…,G Y}, call the runtime characteristic comparison library to obtain the Q group of runtime characteristics for the nth type of device, and the qth group of runtime characteristics is {G 1_q G 2_q ,…,G y_q ,…,G Y_q}, and then obtain the similarity between the current running feature and the y-th feature of the q-th group of running features. The similarity between the current running feature and the y-th feature of the q-th group of running features is |(G y -G y_q ) / G y |, and then obtain the comprehensive similarity H between the current running features and the q-th group of running features. qThe comprehensive similarity between the current operating characteristics and the q-th group of operating characteristics is represented by the average similarity of the Y features between the current operating characteristics and the q-th group of operating characteristics. Substituting each feature into q = 1, 2, ..., Q, we obtain the comprehensive similarity between the current operating characteristics and the Q groups of operating characteristics. The group of operating characteristics with the highest comprehensive similarity is selected as the reference operating characteristics. The number of equipment failures β within a freight cycle of the n-th type of equipment after collecting the reference operating characteristics is then used as the demand for power equipment α at the current moment. This improves the accuracy and reliability of equipment demand assessment. When similar systems match normally, by collecting the current operating characteristics of the equipment in real time and comparing them with historical data in the operating characteristic comparison database, the current state and historical operating patterns can be effectively correlated. By calculating the comprehensive similarity and selecting the most suitable reference characteristics, a high degree of fit between the reference basis and the current equipment operating state is ensured, avoiding bias from subjective judgment or single feature comparison. Using the historical failure count corresponding to the reference characteristics as the current demand directly establishes a correlation between operating characteristics and actual demand, making demand assessment based on real operating data, improving the practicality of the results, and providing an accurate and reliable basis for equipment reserve planning.

[0022] In step S5, when the system similarity between the similar system and the k-th system is less than or equal to a preset system similarity threshold, an abnormal similarity is determined, and the demand for power equipment α at the current moment is adjusted to [a value]. R is a demand adjustment coefficient, and R is a real number greater than 1, which is used to obtain the demand of all power equipment in the k-th power system. This provides a risk mitigation and accurate correction mechanism for judging equipment demand in scenarios with abnormal similarity. When the similarity between similar systems and newly added systems does not reach the threshold, the reliability of the original reference data will have gaps, and directly using the previous demand results is prone to underestimation due to reference bias. By introducing a demand adjustment coefficient greater than 1, the demand results corresponding to the original reference fault number are adjusted upwards, which can effectively make up for the judgment error caused by insufficient similarity, and avoid the situation where equipment shortages are caused by underestimation of demand, thus affecting the normal operation and maintenance of the power system. This targeted adjustment not only retains the basic value of the reference data, but also fully considers the risks of abnormal scenarios, so that equipment demand forecasts can still adapt to actual needs in complex situations, improve the fault tolerance and reliability of demand judgment, and ensure the rationality of equipment reserve planning for newly added systems.

[0023] In step S6, a demand and inventory comparison image coordinate system is established on the visualization platform. The horizontal axis represents the time point, and the vertical axis represents the demand and inventory. The number of demand and inventory comparison image coordinate systems is the same as the total number of power equipment in the k-th power system. When the demand exceeds the inventory, an inventory shortage alarm is issued, prompting managers to replenish the inventory. This makes the supply and demand management of power equipment more intuitive and efficient, and at the same time, it establishes a timely early warning mechanism for inventory risks. By building a demand and inventory comparison image on the visualization platform, the originally scattered supply and demand data is transformed into an intuitive and correlated presentation in the time dimension. Managers no longer need to manually sort and analyze complex data, and can quickly and clearly grasp the dynamic changes in the supply and demand of various types of equipment. When the demand exceeds the inventory, an automatic alarm is issued, which can remind managers to replenish the inventory in time, avoiding equipment shortages due to failure to detect inventory shortages in time, which could affect the operation and maintenance progress or stable operation of the power system. This significantly improves the response efficiency of equipment inventory management and provides a strong guarantee for the continuous and stable operation of the power system.

[0024] A power equipment defect visualization analysis system based on fault tree, the system includes: a power data acquisition module, an equipment similarity analysis module, a system similarity selection module, a normal demand prediction module, an abnormal demand adjustment module, and a supply and demand visualization planning module; The power data acquisition module is used to acquire data from the power system, including equipment data and historical fault data. The equipment similarity analysis module is used when adding a new power system to analyze the data of the new power system and the existing power system, and analyzes the equipment operation similarity between the new power system and the existing power system according to the equipment type. The system similarity selection module is used to comprehensively consider the equipment type and equipment replenishment difficulty of the power system, analyze the similarity between the new power system and the existing power system, and then select the most similar existing power system as the similar system to establish an operational feature comparison library. The normal demand forecasting module is used to predict the demand for equipment caused by equipment failure, taking into account the equipment operating status, if the similarity between the newly added power system and similar systems is normal. The abnormal demand adjustment module is used to adjust the demand if the similarity between the newly added power system and similar systems is abnormal, thereby increasing the predicted demand. The supply and demand visualization planning module is used to create a visual coordinate system comparing demand and inventory on the visualization platform after forecasting demand.

[0025] Example 1: When conducting visual analysis of power equipment defects, the first step is data collection. Staff must obtain the necessary authorization before collecting data from multiple power systems. This involves not only statistically analyzing the specific availability of various types of power equipment in each system, but also meticulously recording the types of faults that have occurred in the past for each type of equipment, as well as the operational characteristics exhibited by the equipment during fault occurrences. This collected basic equipment data and historical fault data are then organized and stored in a database, providing a complete and standardized data resource for subsequent analysis.

[0026] When a new power system needs to be included in the analysis, the system compatibility analysis phase begins. Staff retrieve the inventory status of various types of equipment in the new system and compare it with the corresponding equipment inventory data of existing systems in the database. Simultaneously, they statistically analyze the frequency of different faults for each type of equipment in both the new and existing systems. Combining the system's monitoring duration and equipment inventory, they calculate the frequency of different faults for each type of equipment. Based on the fault frequencies of corresponding equipment in the two systems, they calculate the similarity of the operational status of each type of equipment, forming operational similarity data for various types of equipment between the new and existing systems.

[0027] After completing the equipment-level similarity calculation, a system-wide similarity analysis is further conducted. Staff will calculate the proportion of each equipment type's freight cycle to the total freight cycles of all equipment based on the time from the last request to the final receipt of the equipment (i.e., the freight cycle). This proportion will be used as the weight of that equipment type in the system similarity analysis. Combining the previously obtained operational similarities and corresponding weights for each type of equipment, the overall similarity between the new system and each existing system is calculated. The existing system with the highest overall similarity is selected as the similar system for the new system, and an operational feature comparison library is constructed. This library stores the equipment operational features collected from similar systems at fixed intervals, as well as the number of equipment failures within one freight cycle after each feature collection.

[0028] If the overall similarity between the similar system and the new system is higher than the preset standard, it is judged that the similarity between the two is normal. At this time, the current operating characteristics of any one of the equipment in a certain type of equipment in the new system are collected in real time. Multiple sets of historical operating characteristics of this type of equipment are retrieved from the operating characteristic comparison library. The similarity between the current operating characteristics and each set of historical characteristics is calculated. The historical operating characteristic with the highest similarity is taken as a reference. The number of equipment failures in one freight cycle after the collection of the reference characteristic is checked and determined as the current demand of the equipment.

[0029] If the overall similarity between the similar system and the new system does not meet the preset standard, the similarity is judged to be abnormal. In order to avoid the deviation of demand forecast, the staff will multiply the previously calculated equipment demand by an adjustment coefficient greater than 1. The demand forecast result will be optimized by adjusting the coefficient, and then the final demand of all equipment in the new system will be determined.

[0030] Finally, the visualization and early warning stage begins. On the visualization platform, staff create supply and demand comparison charts for each type of equipment in the new system. The horizontal dimension of the chart is marked with time, and the vertical dimension simultaneously displays the demand and inventory levels of the equipment. When the demand value for a certain type of equipment in the chart exceeds the inventory value, the platform automatically triggers an alarm, promptly reminding managers to replenish the inventory of that type of equipment, ensuring the stable operation of the power system maintenance work.

[0031] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary sensing device embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for visualizing and analyzing defects in power equipment based on fault trees, characterized in that: The method includes the following steps: S1. Collect data from the power system to obtain equipment data and historical fault data. S2. When adding a new power system, analyze the data of the new power system and the existing power system, and analyze the similarity of equipment operation between the new power system and the existing power system according to the equipment type; S3. Taking into account the equipment types and equipment replenishment difficulties of the power system, analyze the similarity between the new power system and the existing power system, and then select the most similar existing power system as the similar system to establish an operational feature comparison library. S4. If the similarity between the newly added power system and similar systems is normal, the demand for equipment caused by equipment failure should be predicted by comprehensively considering the equipment operating status. S5. If the similarity between the newly added power system and similar systems is abnormal, adjust the demand to increase the predicted demand. S6. After completing the forecast of demand, establish a graph coordinate system for comparing demand and inventory on the visualization platform.

2. The power equipment defect visualization analysis method based on fault tree according to claim 1, characterized in that: In step S1, after authorization, data is collected from M power systems to obtain equipment data and historical fault data from the M power systems. The number of N types of power equipment in the m-th power system is {A}. m_1 A m_2 ,…,A m_n ,…,A m_N Substitute m=1,2,…,M one by one to get the number of N types of electrical equipment in M ​​power systems. Store the number of N types of electrical equipment in M ​​power systems into the database. Collect historical fault data of the nth type of electrical equipment in the mth power system. The historical fault data of the nth type of electrical equipment includes the historical fault type of the nth type of electrical equipment and the characteristics of the electrical equipment when the fault occurred, n=1,2,…,N.

3. The power equipment defect visualization analysis method based on fault tree according to claim 2, characterized in that: In step S2, when adding the kth power system, the matching degree between the kth power system and the mth power system is analyzed, and the number of N types of power equipment in the kth power system is {A}. k_1 A k_2 ,…,A k_n ,…,A k_N }, the number of N types of power devices in the m-th power system called {A m_1 A m_2 ,…,A m_n ,…,A m_N In the k-th power system, for the n-th type of power equipment, the historical fault data of the n-th type of power equipment includes X types of faults, where the number of occurrences of the x-th type of fault is B. k_x This leads to the occurrence frequency C of the x-th type of fault in the n-th type of power equipment in the k-th power system. k_x , T k Let x be the number of monitoring cycles in the k-th power system. Substitute each of these into x = 1, 2, ..., X to obtain the frequency of X types of faults in the n-th type of power equipment in the k-th power system {C}. k_1 C k_2 ,…,C k_x ,…,C k_X In the m-th power system, for the n-th type of power equipment, the number of occurrences of the x-th type of fault in the n-th type of power equipment is B. m_x This leads to the occurrence frequency C of the x-th type of fault in the n-th type of power equipment in the m-th power system. m_x , Substituting x = 1, 2, ..., X into each value, we obtain the frequency of fault type X of the nth type of power equipment in the mth power system {C}. m_1 C m_2 ,…,C m_x ,…,C m_X } Calculate the operational similarity D between the m-th power system and the n-th type of power equipment in the k-th power system. m_k_n : ; Substituting each value into n=1,2,…,N, we obtain the operational similarity {D} of the N types of power equipment between the m-th power system and the k-th power system. m_k_1 D m_k_2 ,…,D m_k_n ,…,D m_k_N } 4. The power equipment defect visualization analysis method based on fault tree according to claim 3, characterized in that: In step S3, after obtaining the operational similarity of N types of power equipment between the m-th power system and the k-th power system, the system similarity E between the m-th power system and the k-th power system is calculated. m_k : ； Among them, Z n Z represents the weight of the system similarity analysis for the nth type of power equipment. n It is the ratio of the previous freight cycle of the nth type of electrical equipment to the sum of the previous freight cycles of the Nth type of electrical equipment, with the current time as the endpoint. The freight cycle represents the length of time from the submission of equipment demand to the receipt of electrical equipment.

5. The power equipment defect visualization analysis method based on fault tree according to claim 4, characterized in that: Substituting each value into m = 1, 2, ..., M, we obtain the system similarity {E} between the M power systems and the k-th power system. 1_k E 2_k ,…,E m_k ,…,E M_k }, and then obtain the system similarity {E} 1_k E 2_k ,…,E m_k ,…,E M_k The maximum value in} is selected as the power system with the highest system similarity as the similar system of the k-th power system. An operation feature comparison library is established, which includes: the operation features of a set of equipment in the similar system obtained at each interval of a collection cycle, and the number of equipment failures in a freight cycle after each set of equipment operation features is collected.

6. The power equipment defect visualization analysis method based on fault tree according to claim 5, characterized in that: In step S4, when the system similarity between the similar system and the k-th system is higher than the preset system similarity threshold, the similarity level is judged to be normal. The operating characteristics of any power device α in the n-th type of equipment in the k-th power system are collected in real time. The current operating characteristics of power device α are {G1, G2, ..., G...} y ,…,G Y }, call the runtime characteristic comparison library to obtain the Q group of runtime characteristics for the nth type of device, and the qth group of runtime characteristics is {G 1_q G 2_q ,…,G y_q ,…,G Y_q }, and then obtain the similarity between the current running feature and the y-th feature of the q-th group of running features. The similarity between the current running feature and the y-th feature of the q-th group of running features is |(G y -G y_q ) / G y |, and then obtain the comprehensive similarity H between the current running features and the q-th group of running features. q The comprehensive similarity between the current operating feature and the q-th group of operating features is represented by the average of the similarity of the Y features between the current operating feature and the q-th group of operating features. Substitute each of these values ​​into q=1,2,…,Q to obtain the comprehensive similarity between the current operating feature and the Q groups of operating features. Select the group of operating features with the largest comprehensive similarity as the reference operating feature. Then, call the number of equipment failures β in the freight cycle of the n-th type of equipment after collecting the reference operating feature, and use β as the demand of the power equipment α at the current moment.

7. The power equipment defect visualization analysis method based on fault tree according to claim 6, characterized in that: In step S5, when the system similarity between the similar system and the k-th system is less than or equal to a preset system similarity threshold, an abnormal similarity is determined, and the demand for power equipment α at the current moment is adjusted to [a value]. R is the demand adjustment coefficient and is a real number greater than 1, thus obtaining the demand of all power equipment in the k-th power system.

8. The power equipment defect visualization analysis method based on fault tree according to claim 6, characterized in that: In step S6, a demand and inventory comparison image coordinate system is established on the visualization platform. The horizontal axis represents the time point, and the vertical axis represents the demand and inventory. The number of demand and inventory comparison image coordinate systems is the same as the total number of power equipment in the k-th power system. When the demand exceeds the inventory, an inventory shortage alarm is issued to prompt the management personnel to replenish the inventory.

9. A fault tree-based power equipment defect visualization analysis system, wherein the system is applied to the fault tree-based power equipment defect visualization analysis method according to any one of claims 1-8, characterized in that: The system includes: a power data acquisition module, an equipment similarity analysis module, a system similarity selection module, a normal demand forecasting module, an abnormal demand adjustment module, and a supply and demand visualization planning module. The power data acquisition module is used to acquire data from the power system, including equipment data and historical fault data. The equipment similarity analysis module is used to analyze the data of the new power system and the existing power system when adding a new power system, and to analyze the equipment operation similarity between the new power system and the existing power system according to the equipment type. The system similarity selection module is used to comprehensively consider the equipment type and equipment replenishment difficulty of the power system, analyze the similarity between the new power system and the existing power system, and then select the most similar existing power system as the similar system to establish an operational feature comparison library. The normal demand forecasting module is used to predict the demand for equipment caused by equipment failure if the similarity between the newly added power system and similar systems is normal, taking into account the equipment operating status. The abnormal demand adjustment module is used to adjust the demand if the similarity between the newly added power system and similar systems is abnormal, thereby increasing the predicted demand. The supply and demand visualization planning module is used to predict the demand and then establish a coordinate system for comparing the demand and inventory on the visualization platform.

Images