Intelligent fault early warning system and equipment in power distribution room installation project, and medium

Abstract

The invention relates to the technical field of fault early warning, in particular to an intelligent fault early warning system and device in power distribution room installation engineering and a medium. The method comprises the following steps: firstly, acquiring multi-dimensional data including installation process parameters, quality data, environmental parameters and process videos through an engineering data acquisition module, and then identifying abnormal data by using a data anomaly detection module; the fault risk assessment module innovatively adopts a credibility distribution and evidence synthesis method to comprehensively analyze the abnormal data, and finally the early warning execution module implements graded early warning according to the risk grade and gives a disposal suggestion; and the accuracy and timeliness of fault early warning are improved.

Description

Technical Field

[0001] This application relates to the technical field of fault warning, and in particular to an intelligent fault warning system, device and medium in a distribution substation installation project. Background Technique

[0002] With the rapid development of power grid construction, distribution substations, as key infrastructure in the power system, their installation quality is directly related to the safe and stable operation of the power system. Especially against the background of the accelerating urbanization process, the quantity and scale of distribution substation installation projects are constantly expanding, putting forward higher requirements for installation quality and construction safety.

[0003] At present, distribution substation installation projects mainly rely on automated monitoring systems and intelligent sensor networks to monitor the construction process in real time, and evaluate the installation quality by collecting and analyzing various construction parameters. These systems can detect and alarm abnormal situations in real time, providing data support for construction management; however, there is a lack of effective correlation analysis among various monitoring data in the existing monitoring systems, making it difficult to accurately identify fault risks, and this situation needs to be further improved. Summary of the Invention

[0004] In order to solve the problem that there is a lack of effective correlation analysis among various monitoring data in the existing monitoring systems and it is difficult to accurately identify fault risks, this application provides an intelligent fault warning system, device and medium in a distribution substation installation project, and adopts the following technical solutions: In the first aspect, this application provides an intelligent fault warning system in a distribution substation installation project, including: An engineering data acquisition module, configured to acquire on-site construction data of the distribution substation installation project, where the on-site construction data includes installation process parameters, installation quality data, construction environment parameters, and construction process videos, to obtain an on-site construction data set; A data anomaly detection module, configured to identify abnormal data according to the on-site construction data set to obtain an abnormal data set; A fault risk assessment module, based on the abnormal data set, assigns credibility to the abnormal data and synthesizes evidence, and calculates to obtain a fault risk level; A warning execution module, configured to execute hierarchical warnings according to the fault risk level, and push warning information and emergency handling suggestions to relevant personnel.

[0005] By adopting the above technical solution, due to the complex interrelationships and influencing factors among various types of data during the installation process of the power distribution room, a single threshold judgment method is difficult to accurately identify potential fault risks. First, this application obtains multi-dimensional data including installation process parameters, quality data, environmental parameters, and process videos through the engineering data acquisition module. Then, the data anomaly detection module is used to identify abnormal data. Furthermore, the fault risk assessment module innovatively adopts the credibility assignment and evidence synthesis methods to comprehensively analyze the abnormal data. Finally, the early warning execution module implements hierarchical early warning according to the risk level and gives disposal suggestions, improving the accuracy and timeliness of fault early warning.

[0006] Optionally, the data anomaly detection module specifically includes: The characteristic parameter monitoring unit monitors the construction site data set in real time according to a preset set of characteristic threshold parameters, and the set of characteristic threshold parameters includes the normal value ranges of various types of data determined based on historical construction data and expert experience. The abnormal data identification unit identifies abnormal data that exceeds the normal range according to the monitoring results of the set of characteristic threshold parameters. The abnormal type determination unit conducts fault type analysis and hierarchical determination on the abnormal data.

[0007] By adopting the above technical solution, this application first constructs a dynamic set of characteristic threshold parameters by combining historical data and expert experience through the characteristic parameter monitoring unit to achieve real-time monitoring of the construction site data. Then, the abnormal data identification unit is used to identify abnormal data based on the set of characteristic threshold parameters. Finally, the abnormal type determination unit conducts in-depth analysis and hierarchical determination on the abnormal data. Through the dynamic threshold mechanism that integrates historical data and expert experience, the adaptability and accuracy of anomaly detection are improved.

[0008] Optionally, the process of determining the set of characteristic threshold parameters specifically includes the following steps: Analyze the equipment system structure of the power distribution room and expert knowledge, determine the types of monitoring parameters corresponding to each fault type, establish the mapping relationship between the monitoring parameters and the fault types, and obtain the monitoring parameter mapping table. According to the monitoring parameter mapping table, collect and analyze historical construction data, and calculate the initial parameter threshold range for the distribution characteristics of each monitoring parameter under different fault types. Based on the initial parameter threshold range, combine expert experience for evaluation and correction, and set the threshold intervals corresponding to different fault levels to obtain the corrected set of characteristic threshold parameters.

[0009] By adopting the above technical solutions, the present application first establishes a monitoring parameter mapping table by combining the equipment system structure and expert knowledge to establish the corresponding relationship between fault types and monitoring parameters; secondly, based on the analysis of historical construction data, the distribution characteristics of parameters under different fault types are obtained to get the initial threshold range; finally, the threshold is corrected and graded through expert experience to form a complete set of characteristic threshold parameters.

[0010] Optionally, the fault risk assessment module specifically includes: A probability assignment unit, according to a preset fault risk identification framework, calculates the confidence of each basic risk hypothesis based on the deviation degree of abnormal data, and the fault risk identification framework includes basic fault risk hypotheses corresponding to various types of abnormal data; An evidence fusion unit, which is used to perform evidence synthesis on the basic fault risk hypotheses corresponding to various types of abnormal data by using the D-S combination rule to determine the comprehensive fault risk degree; A risk level determination unit, which determines the fault risk level according to the comprehensive fault risk degree.

[0011] By adopting the above technical solutions, the present application first assigns confidence to each basic risk hypothesis by the probability assignment unit based on the deviation degree of abnormal data; then the evidence fusion unit innovatively uses the D-S combination rule to perform evidence synthesis on multi-source abnormal data; finally, the final risk level is determined by the risk level determination unit; by introducing the D-S evidence theory to handle the uncertainty of data, the accuracy and reliability of risk assessment are improved.

[0012] Optionally, the construction process of the fault risk identification framework includes the following steps: According to the preset data format specification, standardize the installation process parameters, installation quality data, construction environment parameters and construction process videos to obtain standardized construction site data; Based on the standardized construction site data, perform correlation analysis and influencing factor analysis on construction fault factors to obtain the correlation analysis results of fault factors; According to the correlation analysis results of the fault factors, establish a construction fault risk identification framework to determine the basic fault risk hypotheses corresponding to various types of abnormal data.

[0013] By adopting the above technical solutions, the present application first establishes a data format specification to standardize multi-source heterogeneous data and realize the unified expression of data; secondly, through correlation analysis and influencing factor analysis, deeply explores the internal relationship between fault factors; finally, based on the analysis results, constructs a complete risk identification framework to establish the corresponding relationship between abnormal data and basic risk hypotheses; improves the comprehensiveness and accuracy of risk identification.

[0014] Optionally, based on the standardized construction site data, perform correlation analysis and influencing factor analysis on construction fault factors to obtain the correlation analysis results of the fault factors, which specifically include the following steps: Perform time series data analysis on construction fault factors to obtain the time feature sequences of each fault factor; Based on the time feature sequences, adopt the grey correlation analysis method to calculate the correlation degrees between pairwise fault factors to obtain the fault factor correlation degree matrix; According to the fault factor correlation degree matrix, identify the dominant fault factors and subordinate fault factors, and determine the fault factor hierarchical structure diagram; Based on the fault factor hierarchical structure diagram, construct a fault factor correlation network to obtain the fault propagation path diagram.

[0015] By adopting the above technical solution, the present application first performs time series data analysis on fault factors to extract time feature sequences; introduces the grey correlation analysis method to calculate the correlation degree matrix between fault factors; then identifies the dominant and subordinate fault factors based on the correlation degree matrix and establishes a hierarchical structure diagram; finally constructs a fault factor correlation network to form a complete fault propagation path diagram; which can not only accurately identify the root cause and propagation path of faults, but also provide a theoretical basis for fault prevention and control.

[0016] In a second aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the functions of the intelligent fault warning system in the above-mentioned distribution substation installation project.

[0017] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the functions of the intelligent fault warning system in the above-mentioned distribution substation installation project.

[0018] In summary, the present application includes at least one of the following beneficial technical effects: 1. Since there are complex mutual correlations and influence relationships among various types of data during the installation process of the distribution substation, a single threshold judgment method is difficult to accurately identify potential fault risks; the present application first obtains multi-dimensional data including installation process parameters, quality data, environmental parameters, and process videos through an engineering data acquisition module, then uses a data anomaly detection module to identify abnormal data, and then innovatively adopts a credibility assignment and evidence synthesis method to comprehensively analyze the abnormal data through a fault risk assessment module. Finally, the warning execution module implements hierarchical warnings according to the risk level and gives disposal suggestions; improving the accuracy and timeliness of fault warnings; 2. The present application first constructs a dynamic characteristic threshold parameter set through the characteristic parameter monitoring unit in combination with historical data and expert experience to achieve real-time monitoring of the construction site data; then uses the abnormal data identification unit to identify abnormal data based on the characteristic threshold parameter set; finally, deeply analyzes and classifies and determines the abnormal data through the abnormal type determination unit; through the dynamic threshold mechanism that integrates historical data and expert experience, the adaptability and accuracy of abnormal detection are improved; 3. The present application first establishes a monitoring parameter mapping table by combining the equipment system structure and expert knowledge to establish the corresponding relationship between the fault type and the monitoring parameters; secondly, based on the historical construction data analysis, the distribution characteristics of the parameters under different fault types are obtained to obtain the initial threshold range; finally, the threshold is corrected and classified through expert experience to form a complete characteristic threshold parameter set. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic structural diagram of the intelligent fault warning system in the distribution room installation project of the embodiment of the present application; Figure 2 is a schematic structural diagram of the data anomaly detection module in the embodiment of the present application; Figure 3 is a schematic flow diagram of determining the characteristic threshold parameter set in the embodiment of the present application; Figure 4 is a schematic structural diagram of the fault risk assessment module in the embodiment of the present application; Figure 5 is a schematic flow diagram of constructing the fault risk identification framework in the embodiment of the present application; Figure 6 is a schematic flow diagram of fault factor correlation analysis in the embodiment of the present application; Figure 7 is an internal structural diagram of an electronic device in the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term " / and / " used in the present application refers to any or all possible combinations including one or more of the listed items.

[0021] Hereinafter, the terms "first" and "second" are for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0022] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings of the specification.

[0023] In a first aspect, the present application provides an intelligent fault warning system in a distribution substation installation project. Referring to Figure 1 , it includes: An engineering data collection module, configured to collect on-site data of the distribution substation installation project to obtain an on-site data set.

[0024] Among them, the on-site data includes installation process parameters, installation quality data, construction environment parameters, and construction process videos. The engineering data collection module adopts a distributed data collection architecture, including an on-site data collection unit, a data preprocessing unit, and a data storage unit. The on-site data collection unit collects on-site data through a variety of sensing devices and data interfaces, including but not limited to temperature sensors, humidity sensors, current transformers, high-definition cameras, etc.; the data preprocessing unit cleans, formats, and standardizes the collected raw data; the data storage unit uses a distributed database to store the processed data to ensure the reliability and accessibility of the data.

[0025] Specifically, the installation process parameters mainly include operating parameters such as equipment operating temperature, current, and voltage, which are collected in real time by sensors installed on the distribution equipment; the installation quality data includes quality inspection data such as equipment fastening torque and insulation resistance, which are regularly detected and recorded by construction personnel using professional detection instruments; the construction environment parameters include environmental temperature, humidity, and dust concentration, which are continuously collected through environmental monitoring equipment; the construction process video is recorded by high-definition cameras deployed on-site, focusing on key construction nodes and the installation process of important equipment.

[0026] A data anomaly detection module, configured to identify anomaly data according to the on-site data set to obtain an anomaly data set.

[0027] Among them, the data anomaly detection module performs real-time analysis and anomaly detection on the collected on-site data based on a preset set of feature threshold parameters. The set of feature threshold parameters includes the normal value range and warning thresholds of various monitoring parameters, which are determined based on equipment technical specifications, historical experience data, and expert knowledge. When the monitored data exceeds the preset threshold range, the system will automatically mark it as anomaly data and record the time, location, and specific parameter values of the anomaly occurrence.

[0028] Specifically, this embodiment adopts a multi-level threshold detection method for anomaly identification: for numerical parameters (such as temperature, current, etc.), three levels of thresholds are set, corresponding to slight deviations, obvious anomalies and serious anomalies respectively; for quality inspection data, qualification standards are set based on national standards and industry specifications, and data that does not meet the standard requirements is marked as abnormal; for video data, abnormal construction actions and process deviations are identified through video analysis algorithms.

[0029] The fault risk assessment module, based on the abnormal data set, assigns credibility and synthesizes evidence to the abnormal data, and calculates the fault risk level.

[0030] Among them, the fault risk assessment module adopts a multi-source data fusion method based on evidence theory to conduct comprehensive analysis and risk assessment of the detected abnormal data.

[0031] Specifically, for example, when a circuit breaker is detected to have both abnormal temperature (credibility 0.7, weight 0.4) and abnormal insulation resistance (credibility 0.8, weight 0.6), the comprehensive risk value of 0.76 is calculated through evidence synthesis, and it is judged to be a high risk level.

[0032] The early warning execution module executes graded early warnings according to the fault risk level, and pushes early warning information and emergency response suggestions to relevant personnel.

[0033] Among them, the early warning execution module automatically triggers the early warning mechanism of the corresponding level according to the fault risk level obtained by the assessment, and generates targeted disposal suggestions. The early warning mechanism adopts a graded response strategy, and different risk levels correspond to different early warning methods and disposal processes to ensure that the early warning information can be delivered to the relevant responsible persons in a timely and accurate manner.

[0034] Specifically, this embodiment adopts a three-level early warning mechanism: for low-risk early warnings, early warning information is displayed through the system interface to remind on-site personnel to pay attention; for medium-risk early warnings, in addition to system display, the construction manager and quality supervision personnel are notified via text messages; for high-risk early warnings, the emergency response mechanism is activated, and relevant personnel at all levels are notified through various methods such as phone calls, text messages, system pop-ups, etc., and the emergency disposal process is immediately initiated. For example, when the system determines that a circuit breaker has a high-risk fault, it sends early warning information to the construction manager, quality director, and technical supervisor at the same time. The early warning content includes the fault location, abnormal parameters, risk level, and recommended emergency disposal measures, such as immediately stopping construction and checking key components.

[0035] In one embodiment, referring to Figure 2 , data anomaly detection module, specifically including: The characteristic parameter monitoring unit monitors the construction site data set in real time according to the preset characteristic threshold parameter set.

[0036] Among them, the characteristic threshold parameter set includes the normal value ranges of various types of data determined based on historical construction data and expert experience.

[0037] In this embodiment, the process of monitoring characteristic parameters is as follows: for numerical parameters (such as voltage, current, etc.), set standard values and allowable deviation ranges, and the system collects data at fixed time intervals and compares it with the thresholds; for waveform data (such as harmonics, voltage fluctuations, etc.), set the limits of waveform distortion and distortion rate; for environmental parameters, set safety limits according to the equipment operation requirements. For example, in a distribution substation installation project, the standard value of the secondary current of the current transformer of the 10kV switchgear is 5A, the allowable deviation range is ±0.25A, the safe range of environmental temperature is -5°C to 40°C, and the relative humidity shall not exceed 85%.

[0038] The abnormal data identification unit identifies abnormal data that exceeds the normal range according to the monitoring results of the characteristic threshold parameter set.

[0039] Among them, the abnormal data identification unit not only considers the threshold exceeding situation of a single parameter, but also pays attention to the correlation abnormality between multiple parameters.

[0040] In this embodiment, for abnormal data identification, first, perform threshold comparison on a single parameter to identify obvious over-limit abnormalities; second, analyze the change trend of the parameter to identify gradual abnormalities that may cause faults; finally, analyze the ratio relationship between related parameters to identify associated abnormalities between parameters.

[0041] The abnormal type determination unit performs fault type analysis and grading determination on the abnormal data.

[0042] Among them, the abnormal type determination unit performs pattern matching and type recognition on the detected abnormal data based on a pre-established fault feature library.

[0043] Specifically, the abnormal type determination in this embodiment adopts a rule-based grading determination method: first, classify the faults into three categories: equipment faults, process faults, and environmental faults according to the nature of the abnormal data; then determine the fault level according to factors such as the severity, duration, and influence range of the abnormality; finally, generate a fault type determination report, and mark the possible fault causes (such as moisture, aging, etc.) and the influence degree in the determination report.

[0044] In one embodiment, referring to Figure 3 , the process of determining the characteristic threshold parameter set specifically includes the following steps: S310. Analyze the distribution substation equipment system structure and expert knowledge, determine the type of monitoring parameters corresponding to each fault type, establish the mapping relationship between the monitoring parameters and the fault types, and obtain the monitoring parameter mapping table.

[0045] In this embodiment, the power distribution room equipment system is hierarchically decomposed in advance to establish the corresponding relationship between equipment, components and functions. This process needs to fully consider the working principle, structural characteristics and potential failure modes of the equipment, and at the same time combine the experience data in the expert knowledge base to systematically sort out the characteristic manifestations of various faults and the corresponding monitoring parameters.

[0046] Specifically, first, the power distribution room equipment is divided into a primary equipment system and a secondary equipment system according to functions, and then the key equipment of each system is analyzed for its functions and failure modes. For example, for the key equipment of the circuit breaker, its core components such as the opening and closing mechanism, arc extinguishing chamber, and operating mechanism are analyzed to identify the main failure types such as mechanical failure, insulation failure, and heating failure, and the corresponding monitoring parameters are determined, such as mechanical characteristic curves, insulation resistance values, temperature, etc. Through this systematic analysis, a complete mapping table containing information such as equipment type, failure mode, monitoring parameters, and parameter units is finally formed.

[0047] S320. According to the monitoring parameter mapping table, collect and analyze historical construction data, and calculate the initial parameter threshold range for the distribution characteristics of each monitoring parameter under different failure types.

[0048] In this embodiment, first, the construction data of the past three years is collected, and each type of monitoring parameter is classified and statistically analyzed according to the equipment type and working conditions; then the 3σ principle is used to determine the normal fluctuation range of the parameters, and the data outside this range will be initially identified as abnormal. For example, the statistical mean of the operating mechanism temperature of a certain type of circuit breaker under normal working conditions is 35°C, and the standard deviation is 5°C, then the initial judgment threshold for temperature abnormality is set to 50°C (i.e., the mean plus 3 standard deviations). For quality inspection data, the initial threshold range is mainly determined with reference to national standards and industry specifications.

[0049] S330. Based on the initial parameter threshold range, combine expert experience for evaluation and correction, and set the threshold intervals corresponding to different failure levels to obtain the corrected characteristic threshold parameter set.

[0050] In this embodiment, first, the initial threshold and its determination basis are provided to the expert group, and the experts score and give suggestions on the rationality of the threshold according to their experience; then the threshold is corrected according to the expert opinions, and multiple rounds of feedback are carried out until a consensus is reached.

[0051] In one embodiment, referring to Figure 4 , the fault risk assessment module specifically includes: A probability assignment unit, according to the preset fault risk identification framework, calculates the trust degree of each basic risk assumption based on the deviation degree of the abnormal data. The fault risk identification framework includes basic fault risk assumptions corresponding to various abnormal data.

[0052] Among them, the probability assignment unit establishes a fault risk identification framework based on fuzzy set theory, which maps abnormal data to the corresponding basic risk hypothesis space. The identification framework includes multiple basic hypotheses such as equipment failures, environmental factors, and human factors. Each abnormal data can correspond to one or more basic hypotheses according to its characteristics and deviation degree, forming a complete risk identification system.

[0053] Specifically, in this embodiment, the probability assignment process adopts a distance-based trust calculation method: first, determine the standard value and allowable fluctuation range of each monitoring parameter, then calculate the basic trust according to the degree of deviation of the abnormal data from the standard value, and finally correct it considering data reliability.

[0054] The evidence fusion unit is used to synthesize evidence based on the basic fault risk hypotheses corresponding to various abnormal data by using the D-S combination rule to determine the comprehensive fault risk degree.

[0055] Among them, the evidence fusion unit uses the improved D-S evidence theory for multi-source information fusion. First, evaluate the reliability of each evidence source to determine the evidence weight, and then use the D-S combination rule to synthesize the information of multiple evidence sources to obtain a comprehensive fault risk judgment result.

[0056] Specifically, in this embodiment, first, locally fuse the data of the same type of sensors to obtain the risk assessment results at the subsystem level; then globally fuse the assessment results of different subsystems to obtain the final risk judgment. For example, when it is detected that a certain power distribution equipment has both temperature anomalies (trust degree 0.7) and vibration anomalies (trust degree 0.6) at the same time, the comprehensive trust degree of equipment failure calculated by the D-S combination rule is 0.82, which is significantly higher than the judgment results of single evidence sources, improving the reliability of risk assessment.

[0057] The risk level determination unit determines the fault risk level according to the comprehensive fault risk degree.

[0058] In this embodiment, a risk level evaluation model is established based on fuzzy decision theory. The model maps the comprehensive risk degree to a predefined risk level interval, determines the final risk level through fuzzy inference rules, and appropriately adjusts the risk level considering factors such as equipment importance and maintenance difficulty.

[0059] In one embodiment, referring to Figure 5 , the construction process of the fault risk identification framework includes the following steps: S510. Standardize the installation process parameters, installation quality data, construction environment parameters, and construction technology videos according to the preset data format specifications to obtain standardized construction site data.

[0060] S520. Based on the standardized construction site data, perform correlation analysis and influencing factor analysis on construction fault factors to obtain the correlation analysis results of the fault factors.

[0061] In this embodiment, by analyzing the correlation between various construction parameters and the occurrence of faults, key influencing factors are identified, and a correlation network between fault factors is established.

[0062] Specifically, first use the correlation coefficient to analyze the linear correlation between numerical parameters; then use the principal component analysis method to identify the main influencing factors; finally, determine the weights of each factor through the analytic hierarchy process. For example, through analysis, it is found that the correlation coefficient between the operating speed of a certain type of circuit breaker and the ambient temperature is -0.85, indicating a significant negative correlation between the two; at the same time, it is found that the lubrication state is the primary factor affecting the operating speed, with a weight of 0.4.

[0063] S530. According to the correlation analysis results of the fault factors, establish a construction fault risk identification framework to determine the basic fault risk assumptions corresponding to various abnormal data.

[0064] In this embodiment, a tree structure is adopted to classify various faults that may occur during the construction process according to their nature and severity, and establish the corresponding relationship between abnormal data and fault types.

[0065] Specifically, the risk identification framework is divided into three layers: the first layer is the major fault categories, including equipment body faults, installation process faults, and environmental factor faults; the second layer is the specific fault types, such as mechanical faults, electrical faults, operation errors, etc.; the third layer is the corresponding abnormal data characteristics.

[0066] In one embodiment, referring to Figure 6 , based on the standardized construction site data, perform correlation analysis and influencing factor analysis on construction fault factors to obtain the correlation analysis results of the fault factors, which specifically include the following steps: S610. Perform time series data analysis on construction fault factors to obtain the time feature sequences of each fault factor.

[0067] S620. Based on the time feature sequences, use the grey correlation analysis method to calculate the correlation degrees between pairwise fault factors to obtain the fault factor correlation degree matrix.

[0068] In this embodiment, first perform dimensionless processing on the time feature sequences, then calculate the grey correlation coefficients between the sequences, and finally obtain the overall correlation degree through weighted averaging to form a complete correlation degree matrix.

[0069] Specifically, the following grey relational analysis steps are adopted in this embodiment: First, select the mother sequence such as the equipment failure state and the child sequences such as various monitoring parameters, and calculate the reference sequence and the comparison sequences; then set the resolution coefficient, usually taking 0.5, and calculate the correlation coefficients; finally, obtain the correlation degree matrix. For example, the analysis shows that the correlation degree between the operation time of the circuit breaker and the lubrication state is 0.85, the correlation degree with the ambient temperature is 0.62, and the correlation degree with the number of operations is 0.73, indicating that the lubrication state is the most important factor affecting the operation time.

[0070] S630. According to the fault factor correlation degree matrix, identify the dominant fault factors and subordinate fault factors, and determine the fault factor hierarchical structure diagram.

[0071] In this embodiment, the correlation degree matrix is analyzed by the clustering analysis method. According to the strength of the correlation degree, the fault factors are divided into different levels, the master-slave relationship between the factors is determined, a hierarchical fault factor structure is constructed, and finally the hierarchical structure diagram is drawn.

[0072] S640. Based on the fault factor hierarchical structure diagram, construct a fault factor association network to obtain the fault propagation path diagram.

[0073] Specifically, first set the connection weights according to the correlation degree, and establish connections between factors with a correlation degree greater than 0.6; then calculate the degree centrality and betweenness centrality of the nodes to identify the key nodes; finally, analyze the fault propagation path through the shortest path algorithm.

[0074] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0075] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as Figure 7 shown. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the functions of the intelligent fault warning system in the above power distribution room installation project.

[0076] Those skilled in the art can understand, Figure 7The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the electronic device to which the solution of this application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have a different component arrangement.

[0077] In one embodiment, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0078] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The above computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to the memory, storage, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0079] The above are all preferred embodiments of this application. The protection scope of this application is not limited accordingly. Therefore, all equivalent changes made according to the structure, shape, and principle of this application should be covered within the protection scope of this application.

Claims

1. An intelligent fault warning system in a power distribution room installation project, characterized in that: include: The engineering data acquisition module is used to collect the construction site data of the power distribution room installation project, wherein the construction site data includes installation process parameters, installation quality data, construction environment parameters and construction process video, and obtain the construction site data set; A data anomaly detection module, which identifies abnormal data based on the construction site data set to obtain an abnormal data set; A fault risk assessment module, based on the abnormal data set, performs credibility assignment and evidence synthesis on the abnormal data, and calculates the fault risk level; The early warning execution module executes graded early warning according to the fault risk level and pushes early warning information and emergency response suggestions to relevant personnel.

2. The intelligent fault early warning system in the power distribution room installation project according to claim 1 is characterized in that: The data anomaly detection module specifically includes: A characteristic parameter monitoring unit monitors the construction site data set in real time according to a preset characteristic threshold parameter set, wherein the characteristic threshold parameter set includes a normal value range of various types of data determined according to historical construction data and expert experience; an abnormal data identification unit, for identifying abnormal data beyond a normal range according to the monitoring result of the characteristic threshold parameter set; The abnormality type determination unit performs fault type analysis and classification determination on the abnormal data.

3. The intelligent fault early warning system in the power distribution room installation project according to claim 2 is characterized in that: The process of determining the characteristic threshold parameter set specifically includes the following steps: Analyze the distribution room equipment system structure and expert knowledge, determine the monitoring parameter type corresponding to each fault type, establish a mapping relationship between monitoring parameters and fault types, and obtain a monitoring parameter mapping table; According to the monitoring parameter mapping table, historical construction data is collected and analyzed, and the initial parameter threshold range is calculated based on the distribution characteristics of each monitoring parameter under different fault types; Based on the initial parameter threshold range, evaluation and correction are performed in combination with expert experience, threshold intervals corresponding to different fault levels are set, and a corrected characteristic threshold parameter set is obtained.

4. The intelligent fault early warning system in the power distribution room installation project according to claim 1 is characterized in that: The fault risk assessment module specifically includes: A probability allocation unit calculates the trustworthiness of each basic risk hypothesis based on the degree of deviation of the abnormal data according to a preset fault risk identification framework, wherein the fault risk identification framework includes basic fault risk hypotheses corresponding to various types of abnormal data; The evidence fusion unit is used to synthesize evidence based on the basic fault risk assumptions corresponding to various abnormal data using the DS combination rule to determine the comprehensive fault risk level; The risk level determination unit determines the fault risk level according to the comprehensive fault risk degree.

5. The intelligent fault warning system in the power distribution room installation project according to claim 4 is characterized in that: The construction process of the fault risk identification framework includes the following steps: According to the preset data format specifications, the installation process parameters, installation quality data, construction environment parameters and construction process videos are standardized to obtain standardized construction site data; Based on the standardized construction site data, correlation analysis and influencing factor analysis are performed on construction failure factors to obtain correlation analysis results of failure factors; According to the correlation analysis results of the fault factors, a construction fault risk identification framework is established to determine the basic fault risk assumptions corresponding to various types of abnormal data.

6. The intelligent fault early warning system in the power distribution room installation project according to claim 5 is characterized in that: Based on the standardized construction site data, correlation analysis and influencing factor analysis are performed on construction failure factors to obtain correlation analysis results of failure factors, which specifically includes the following steps: Conduct time series data analysis on construction failure factors to obtain the time characteristic sequence of each failure factor; Based on the time characteristic sequence, a grey correlation analysis method is used to calculate the correlation between the fault factors and obtain a fault factor correlation matrix; According to the fault factor correlation matrix, the dominant fault factors and the subordinate fault factors are identified, and a fault factor hierarchy diagram is determined; Based on the fault factor hierarchical structure diagram, a fault factor association network is constructed to obtain a fault propagation path diagram.

7. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the function of the intelligent fault warning system in the power distribution room installation project described in any one of claims 1 to 6 is realized.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the function of the intelligent fault warning system in the power distribution room installation project described in any one of claims 1-6 is realized.

Images