A power collection line online detection system and method

Abstract

This invention provides an online detection system and method for power collection lines, belonging to the field of power detection technology. It includes: a data acquisition module for acquiring historical operating data of the power collection line and real-time operating data; a data construction module for determining the normal operating range of the power collection line based on historical operating data and constructing a fault detection model; a fault determination module for determining real-time fault data of the power collection line based on real-time operating data and the normal operating range; and a fault detection module for detecting faults in the real-time fault data of the power collection line based on the fault detection model and generating a fault report. This system enables real-time and accurate acquisition and processing of operating data, accurately identifies and locates key fault nodes, achieves high efficiency and accuracy in intelligent fault detection, improves the safety and stability of power collection lines, reduces outage risks, and optimizes the allocation of maintenance resources and maintenance strategies.

Description

Technical Field

[0001] This invention relates to the field of power detection technology, and in particular to an online detection system and method for power collection lines. Background Technology

[0002] Online monitoring of power collection lines is a crucial technology in the power industry for ensuring their stable operation. With increasing power loads and aging equipment, the risk of faults in power collection lines is gradually increasing. Traditional manual inspection methods are not only inefficient but also fail to detect potential faults in real time. To address this issue, the power industry began introducing online monitoring technology as early as the late 20th century to monitor the operating status of power collection lines in real time. By combining sensors with data acquisition equipment, electrical parameter data of the lines can be collected in real time. With advancements in big data analytics and artificial intelligence, fault prediction and intelligent diagnosis have gradually become core functions of online monitoring systems. While existing monitoring systems can provide basic monitoring functions, they still have shortcomings in terms of intelligent fault diagnosis and preventative maintenance.

[0003] Therefore, the present invention provides an online detection system and method for power distribution lines. Summary of the Invention

[0004] This invention provides an online detection system and method for power collection lines. By acquiring historical operating data of the power collection lines, collecting real-time operating data of the power collection lines, determining the normal operating range, constructing a fault detection model, determining real-time fault data of the power collection lines based on the real-time operating data and the normal operating range, and performing fault detection and generating fault reports in conjunction with the fault detection model, it can achieve real-time and accurate acquisition and processing of operating data, accurately identify and locate key fault nodes, realize the efficiency and accuracy of intelligent fault detection, improve the safety and stability of power collection lines, reduce the risk of outages, and optimize the allocation of maintenance resources and maintenance strategies.

[0005] On one hand, the present invention provides an online detection system for power collection lines, comprising:

[0006] Data Acquisition Module: Acquires historical operating data of the power collection line and collects real-time operating data of the power collection line;

[0007] Construction module: Determine the normal operating range of the collection line based on historical operating data, and construct a fault detection model;

[0008] Determining module: Determines real-time fault data of the collector line based on real-time operating data and normal operating range;

[0009] Fault module: Based on the fault detection model, it performs fault detection on real-time fault data of the power collection line and generates fault reports.

[0010] According to the present invention, an online detection system for power lines includes a data acquisition module comprising:

[0011] Historical sub-operation data unit: acquires historical sub-operation data of the collection line over multiple specified historical time periods. The historical sub-operation data includes historical normal sub-operation data and historical fault sub-operation data. The historical normal sub-operation data includes a historical normal operation matrix, and the historical fault sub-operation data includes a historical fault operation vector and historical fault type.

[0012] Historical normal operation data and historical fault operation data unit: Historical normal operation data is determined based on historical normal sub-operation data of the collection line in all historical sub-operation data of all historical specified time periods. At the same time, historical fault operation data is determined based on historical fault sub-operation data of the collection line in all historical sub-operation data of all historical specified time periods.

[0013] Historical Operation Data Unit: This unit contains historical normal operation data and historical fault operation data.

[0014] According to the present invention, an online detection system for power lines includes a data acquisition module comprising:

[0015] Operating area unit: Multiple operating areas are determined based on historical fault operation data in the historical operation data;

[0016] Key node data unit: Based on the topology of the power collection line and all operating areas, key node data is determined. The key node data includes multiple key nodes, the data acquisition requirements of each key node, and the location of the key node.

[0017] Installation unit: Sensor groups are installed at the corresponding key node locations based on the data acquisition requirements of each key node;

[0018] Real-time operation data unit: Based on the real-time operation sub-data of each key node of the power collection line collected by the sensor group, the real-time operation sub-data of each key node is preprocessed, and the real-time operation data is determined based on the preprocessed real-time operation sub-data of all key nodes.

[0019] According to the present invention, an online detection system for power collection lines includes a construction module comprising:

[0020] Key node category unit: Based on the historical normal operation vectors in all historical normal operation sub-operation data in the historical operation data, cluster analysis is performed to determine multiple key node categories, where each key node category includes multiple key nodes;

[0021] Node category data unit: Extract the historical normal operation vectors of all key nodes in each key node category from the historical normal operation matrix of each historical normal sub-operation data, and determine the node category data of each key node category based on all historical normal operation vectors extracted from the historical normal operation matrix of all historical normal sub-operation data;

[0022] Normal operation matrix unit: Based on the node category data of each key node category, determine the normal operation matrix of each node category data;

[0023] Normal operating range unit: Based on the normal operating range matrix of node category data for all key node categories, the normal operating range of the collection line is determined;

[0024] Construction Unit: The historical fault operation vectors in all historical fault sub-operation data in the historical fault operation data are used as the input of the fault detection model, and the historical fault types in all historical fault sub-operation data in the historical fault operation data are used as the output of the fault detection model;

[0025] Training unit: Train the fault detection model based on historical fault operation data in the historical operation data.

[0026] According to the present invention, an online detection system for power collection lines, comprising a normally operating matrix unit, includes:

[0027] ;

[0028] ;

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] in, This represents the normal operation matrix of the k-th node category data. Let represent the lower limit and upper limit of the first feature of the category data of the k-th node, respectively. Let represent the lower limit and upper limit of the j-th feature of the k-th node category data, respectively. Let represent the lower limit and upper limit of the N1-th feature of the k-th node category data, respectively, where N1 represents the number of features in the historical normal operation vector. This represents the average value of the j-th feature of the k-th node category data. This represents the standard deviation of the j-th feature of the k-th node category data. This represents the eigenvalue of the j-th feature in the clustering vector of the k-th node category data. Let j represent the feature value of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category data at the t-th historical specified time period. This represents the number of historical normal operation vectors in the category data of the k-th node. This represents the eigenvalue of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category across all historical specified time periods. The eigenvalue of the j-th feature of the clustering vector of the k-th node category data. similarity value, Indicates the time smoothing factor. This indicates the first adjustment parameter. This indicates the second adjustment parameter. This indicates the third adjustment parameter. This represents the median of all j-th features sorted by the category data of the k-th node. This represents the 5th quantile after sorting all j-th features of the k-th node category data. This represents the 95th quantile after sorting all j-th features of the k-th node category data.

[0034] According to the present invention, an online detection system for power collection lines includes a determining module comprising:

[0035] Real-time running vector unit: Extract features from the preprocessed real-time running sub-data of each key node in the real-time running data to determine the real-time running vector of each key node;

[0036] Fault-critical node unit: The real-time running vector of each critical node is compared with the normal operation matrix of the node category data of the critical node category corresponding to each critical node in the normal operation range. If the eigenvalue of any feature of the real-time running vector of the critical node is not between the lower limit and the upper limit of the corresponding normal operation matrix, it is determined to be a fault-critical node; otherwise, it is determined to be a normal critical node.

[0037] Real-time fault data unit: Real-time fault data is determined based on all critical fault nodes and the real-time operation vector of each critical fault node.

[0038] According to the present invention, an online detection system for power collection lines includes a fault module comprising:

[0039] Fault prediction unit: Input all real-time running vectors from the real-time fault data into the fault detection model, and determine the predicted fault type and fault maintenance optimization suggestions for each critical fault node based on the output structure of the fault detection model;

[0040] Maintenance and optimization unit: Performs maintenance and optimization for each critical fault node based on the predicted fault type and fault maintenance and optimization suggestions;

[0041] Generation Unit: Generates a fault report based on real-time fault data, predicted fault types of all critical fault nodes, fault maintenance and optimization suggestions, and maintenance and optimization results.

[0042] On the other hand, the present invention also provides an online detection method for power collection lines, comprising:

[0043] Step 1: Obtain historical operating data of the power collection line and collect real-time operating data of the power collection line;

[0044] Step 2: Determine the normal operating range of the collection line based on historical operating data and construct a fault detection model;

[0045] Step 3: Determine the real-time fault data of the collector line based on real-time operating data and normal operating range;

[0046] Step 4: Based on the fault detection model, perform fault detection on the real-time fault data of the collector line and generate a fault report.

[0047] Compared with the prior art, the beneficial effects of this application are as follows:

[0048] By acquiring historical operating data of the power collection lines, collecting real-time operating data of the power collection lines, determining the normal operating range, constructing a fault detection model, determining real-time fault data of the power collection lines based on real-time operating data and the normal operating range, and combining the fault detection model to perform fault detection and generate fault reports, it is possible to achieve real-time and accurate operating data acquisition and processing, accurately identify and locate key fault nodes, realize the efficiency and accuracy of intelligent fault detection, improve the safety and stability of the power collection lines, reduce the risk of outages, and optimize the allocation of maintenance resources and maintenance strategies. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0050] Figure 1This is a schematic diagram of the structure of an online detection system for power collection lines provided in an embodiment of the present invention.

[0051] Figure 2 This is a flowchart illustrating an online detection method for power collection lines provided in an embodiment of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0053] Example 1:

[0054] This invention provides an online detection system for power collection lines, such as... Figure 1 As shown, it includes:

[0055] Data Acquisition Module: Acquires historical operating data of the power collection line and collects real-time operating data of the power collection line;

[0056] Construction module: Determine the normal operating range of the collection line based on historical operating data, and construct a fault detection model;

[0057] Determining module: Determines real-time fault data of the collector line based on real-time operating data and normal operating range;

[0058] Fault module: Based on the fault detection model, it performs fault detection on real-time fault data of the power collection line and generates fault reports.

[0059] In this embodiment, historical and real-time operating data of the collector line are acquired. Historical operating data includes information such as the equipment's past operating status and fault conditions, while real-time operating data consists of real-time parameters (such as voltage, current, and temperature) dynamically collected during actual operation.

[0060] In this embodiment, based on collected historical operating data, the normal operating status of the power collection line is analyzed to determine its normal operating range. The normal operating range includes the upper and lower limits of all electrical parameters, representing the range of parameter fluctuations during normal operation. A fault detection model also needs to be constructed, which can identify potential faults based on real-time fault data.

[0061] In this embodiment, the operating status of the power collection line is monitored in real time by combining real-time operating data and a determined normal operating range to identify and determine whether a fault exists. By comparing the real-time data with the normal operating range, if the data exceeds the normal range, a real-time fault in the power collection line is determined.

[0062] In this embodiment, a constructed fault detection model is used to analyze real-time fault data and generate a fault report based on the model results.

[0063] The beneficial effects of the above technical solution are as follows: By acquiring historical operating data of the power collection line, collecting real-time operating data of the power collection line, determining the normal operating range, constructing a fault detection model, determining real-time fault data of the power collection line based on real-time operating data and the normal operating range, and combining the fault detection model to perform fault detection and generate fault reports, it is possible to achieve real-time and accurate operating data acquisition and processing, accurately identify and locate key fault nodes, realize the efficiency and accuracy of intelligent fault detection, improve the safety and stability of the power collection line, reduce the risk of outage, and optimize the allocation of maintenance resources and maintenance strategies.

[0064] Example 2:

[0065] This invention provides an online detection system for power lines, including a data acquisition module comprising:

[0066] Historical sub-operation data unit: acquires historical sub-operation data of the collection line over multiple specified historical time periods. The historical sub-operation data includes historical normal sub-operation data and historical fault sub-operation data. The historical normal sub-operation data includes a historical normal operation matrix, and the historical fault sub-operation data includes a historical fault operation vector and historical fault type.

[0067] Historical normal operation data and historical fault operation data unit: Historical normal operation data is determined based on historical normal sub-operation data of the collection line in all historical sub-operation data of all historical specified time periods. At the same time, historical fault operation data is determined based on historical fault sub-operation data of the collection line in all historical sub-operation data of all historical specified time periods.

[0068] Historical Operation Data Unit: This unit contains historical normal operation data and historical fault operation data.

[0069] In this embodiment, historical sub-operational data of the collector line within multiple specified historical time periods are acquired. This data is divided into two categories: historical normal sub-operational data, which includes detailed data of the collector line during normal operation, specifically represented as a historical normal operation matrix. This is a two-dimensional data structure that records the normal values ​​of various indicators (such as current, temperature, etc.) at different time points; and historical fault sub-operational data, which includes detailed data of the collector line when a fault occurs, specifically represented as a historical fault operation vector. This is a one-dimensional data structure that describes the key indicators when a fault occurs. It also includes historical fault types, i.e., the types of faults that occurred (such as short circuits, overloads, etc.).

[0070] In this embodiment, complete historical normal operation data is determined based on historical normal sub-operation data in all historical specified time periods, providing benchmark data for subsequent analysis. At the same time, complete historical fault operation data is determined based on historical fault sub-operation data in all historical specified time periods, which is used to identify and warn of potential future faults.

[0071] In this embodiment, historical normal operation data and historical fault operation data are integrated to form the final historical operation data.

[0072] The beneficial effects of the above technical solution are: obtaining historical operating data of the power collection line can provide an accurate data foundation for determining the normal operating range and building a fault detection model, thereby improving the accuracy of fault detection.

[0073] Example 3:

[0074] This invention provides an online detection system for power lines, including a data acquisition module comprising:

[0075] Operating area unit: Multiple operating areas are determined based on historical fault operation data in the historical operation data;

[0076] Key node data unit: Based on the topology of the power collection line and all operating areas, key node data is determined. The key node data includes multiple key nodes, the data acquisition requirements of each key node, and the location of the key node.

[0077] Installation unit: Sensor groups are installed at the corresponding key node locations based on the data acquisition requirements of each key node;

[0078] Real-time operation data unit: Based on the real-time operation sub-data of each key node of the power collection line collected by the sensor group, the real-time operation sub-data of each key node is preprocessed, and the real-time operation data is determined based on the preprocessed real-time operation sub-data of all key nodes.

[0079] In this embodiment, multiple operating areas are identified by analyzing fault data from the historical operation of the power collection line. These operating areas can be locations with significant load fluctuations: for areas with large load fluctuations, such as large shopping malls or factory production workshops, the cable nodes in these areas require focused monitoring. Sudden load changes can cause significant fluctuations in cable current and voltage, affecting cable insulation and equipment operation. Installing sensors at these nodes allows for real-time monitoring of load changes, timely adjustment of power supply strategies, and prevention of cable overload. The middle sections of long-distance cables are also key areas: long-distance cables experience voltage drops and overheating during transmission, and the operating conditions at these middle sections significantly impact the overall performance of the cable line. Setting up critical nodes at the middle sections of long-distance cables and installing sensors to monitor cable temperature, voltage, and other parameters allows for timely detection of abnormalities in the middle sections of the cable, enabling appropriate measures to be taken to ensure stable cable operation.

[0080] In this embodiment, based on the topology of the power collection line, key node data is determined. Key nodes refer to important points in the power collection line that affect system operation, such as substations and connection points. The data acquisition requirements for each key node include the type and number of sensors, as well as the parameters they need to collect (such as current, voltage, temperature, etc.). The location of the key nodes is also determined in this step to facilitate precise installation.

[0081] In this embodiment, based on the data acquisition requirements of each key node, the system will install appropriate sensor groups at the corresponding key node locations. These sensors are used to collect various operational data of the power collection line in real time.

[0082] In this embodiment, after the sensor array is installed, the sensors begin to collect real-time operational data from each key node. This data is preprocessed (e.g., noise reduction, standardization) and combined with the data from all key nodes to form the final real-time operational data.

[0083] The beneficial effects of the above technical solution are: real-time acquisition of the real-time operation data of the power collection line can ensure real-time monitoring of key points of the power collection line, realize real-time and accurate operation data acquisition and processing, and provide data basis for determining real-time fault data.

[0084] Example 4:

[0085] This invention provides an online detection system for power lines, comprising a construction module including:

[0086] Key node category unit: Based on the historical normal operation vectors in all historical normal operation sub-operation data in the historical operation data, cluster analysis is performed to determine multiple key node categories, where each key node category includes multiple key nodes;

[0087] Node category data unit: Extract the historical normal operation vectors of all key nodes in each key node category from the historical normal operation matrix of each historical normal sub-operation data, and determine the node category data of each key node category based on all historical normal operation vectors extracted from the historical normal operation matrix of all historical normal sub-operation data;

[0088] Normal operation matrix unit: Based on the node category data of each key node category, determine the normal operation matrix of each node category data;

[0089] Normal operating range unit: Based on the normal operating range matrix of node category data for all key node categories, the normal operating range of the collection line is determined;

[0090] Construction Unit: The historical fault operation vectors in all historical fault sub-operation data in the historical fault operation data are used as the input of the fault detection model, and the historical fault types in all historical fault sub-operation data in the historical fault operation data are used as the output of the fault detection model;

[0091] Training unit: Train the fault detection model based on historical fault operation data in the historical operation data.

[0092] In this embodiment, based on historical normal operation sub-operation data, particularly historical normal operation vectors, cluster analysis is used to identify and determine multiple key node categories. Cluster analysis groups nodes with similar operational characteristics to create different key node categories. Each category includes multiple key nodes with similar characteristics.

[0093] In this embodiment, all historical normal operation vectors under each key node category are extracted from the historical normal operation matrix, and the node category data of each key node category is determined based on these data.

[0094] In this embodiment, node category data for each key node category are used to construct a normal operation matrix for each node category. The normal operation matrix records the operating status data of each node under normal conditions, including the upper and lower limits of parameters such as current, temperature, and pressure.

[0095] In this embodiment, the overall normal operating range of the collector line is determined based on the normal operating matrix of all key node categories. This range is derived from the matrix data of each node category and represents the normal operating conditions of the collector line.

[0096] In this embodiment, historical fault operation vectors from historical fault operation data are used as input, and historical fault types are used as output to construct a fault detection model. The goal of this model is to predict future potential faults by learning the characteristics of fault operation data.

[0097] In this embodiment, a fault detection model is trained using a machine learning algorithm based on historical fault operation data. The training process involves adjusting the model parameters to enable it to accurately identify historical fault types and provide effective fault warnings in practical applications.

[0098] The beneficial effects of the above technical solution are as follows: Based on historical operating data, the normal operating range of the collection line is determined, and a fault detection model is constructed. This model can accurately identify the normal operating matrix of different nodes, realize intelligent and efficient fault detection, improve the safety and stability of the collection line, reduce the risk of outage, and optimize maintenance strategies.

[0099] Example 5:

[0100] This invention provides an online detection system for power collection lines, comprising a matrix unit for normal operation, including:

[0101] ;

[0102] ;

[0103] ;

[0104] ;

[0105] ;

[0106] ;

[0107] in, This represents the normal operation matrix of the k-th node category data. Let represent the lower limit and upper limit of the first feature of the category data of the k-th node, respectively. Let represent the lower limit and upper limit of the j-th feature of the k-th node category data, respectively. Let represent the lower limit and upper limit of the N1-th feature of the k-th node category data, respectively, where N1 represents the number of features in the historical normal operation vector. This represents the average value of the j-th feature of the k-th node category data. This represents the standard deviation of the j-th feature of the k-th node category data. This represents the eigenvalue of the j-th feature in the clustering vector of the k-th node category data. Let j represent the feature value of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category data at the t-th historical specified time period. This represents the number of historical normal operation vectors in the category data of the k-th node. This represents the eigenvalue of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category across all historical specified time periods. The eigenvalue of the j-th feature of the clustering vector of the k-th node category data. similarity value, Indicates the time smoothing factor. This indicates the first adjustment parameter. This indicates the second adjustment parameter. This indicates the third adjustment parameter. This represents the median of all j-th features sorted by the category data of the k-th node. This represents the 5th quantile after sorting all j-th features of the k-th node category data. This represents the 95th quantile after sorting all j-th features of the k-th node category data.

[0108] In this embodiment, the first adjustment parameter The standard deviation of the j-th feature based on the k-th node category data. Adjust the parameters.

[0109] In this embodiment, the second adjustment parameter The number is the average of the j-th feature based on the k-th node category data. The eigenvalue of the j-th feature of the clustering vector of the k-th node category data. The adjustment parameter is the absolute value of the difference.

[0110] In this embodiment, the third adjustment parameter The adjustment parameter is the difference between the median and the 5th quantile of all j-th features sorted based on the k-th node category data, and the difference between the 95th quantile and the median of all j-th features sorted based on the k-th node category data.

[0111] The beneficial effects of the above technical solution are as follows: Based on the node category data of each key node category, the normal operation matrix of each node category data is determined, which can provide an accurate data foundation for determining the normal operation range and realize intelligent and efficient fault detection.

[0112] Example 6:

[0113] This invention provides an online detection system for power collection lines, including a determination module comprising:

[0114] Real-time running vector unit: Extract features from the preprocessed real-time running sub-data of each key node in the real-time running data to determine the real-time running vector of each key node;

[0115] Fault-critical node unit: The real-time running vector of each critical node is compared with the normal operation matrix of the node category data of the critical node category corresponding to each critical node in the normal operation range. If the eigenvalue of any feature of the real-time running vector of the critical node is not between the lower limit and the upper limit of the corresponding normal operation matrix, it is determined to be a fault-critical node; otherwise, it is determined to be a normal critical node.

[0116] Real-time fault data unit: Real-time fault data is determined based on all critical fault nodes and the real-time operation vector of each critical fault node.

[0117] In this embodiment, after preprocessing the real-time operational sub-data of each key node, key features are extracted to form a real-time operational vector. The real-time operational vector includes feature values ​​of all relevant parameters of each key node during real-time monitoring, such as current, voltage, and temperature, to reflect the health status of the node.

[0118] In this embodiment, the real-time operating vector of each critical node is compared with its corresponding normal operating matrix. If a certain feature value in the real-time operating vector exceeds the range formed by the upper and lower limits of the normal operating matrix for that node category, the node is determined to be a faulty critical node. If all feature values ​​are within the normal range, the node is considered a normal critical node.

[0119] In this embodiment, real-time fault data is generated using all critical fault nodes and their real-time operational vectors. This data contains feature information about all critical fault nodes.

[0120] The beneficial effects of the above technical solution are as follows: Based on real-time operating data and normal operating range, the real-time fault data of the collection line can be determined, which can accurately identify and locate the critical fault nodes, improve the operating efficiency and fault response speed of the collection line, optimize the maintenance strategy, reduce system downtime and maintenance costs, and enhance the stability and safety of the line.

[0121] Example 7:

[0122] This invention provides an online detection system for power lines, including a fault module comprising:

[0123] Fault prediction unit: Input all real-time running vectors from the real-time fault data into the fault detection model, and determine the predicted fault type and fault maintenance optimization suggestions for each critical fault node based on the output structure of the fault detection model;

[0124] Maintenance and optimization unit: Performs maintenance and optimization for each critical fault node based on the predicted fault type and fault maintenance and optimization suggestions;

[0125] Generation Unit: Generates a fault report based on real-time fault data, predicted fault types of all critical fault nodes, fault maintenance and optimization suggestions, and maintenance and optimization results.

[0126] In this embodiment, all real-time running vectors from the real-time fault data are input into a pre-trained fault detection model. Based on the model's output, the system can predict the possible fault types (e.g., overload, short circuit) for each critical fault node and generate maintenance optimization suggestions for each node based on the prediction results. These suggestions may include repairs, component replacements, increased monitoring, and other operations aimed at optimizing the maintenance process and reducing downtime.

[0127] In this embodiment, specific maintenance optimization measures are formulated based on the predicted fault type and maintenance optimization suggestions for each critical fault node. These measures help to effectively maintain the critical fault nodes, ensure the system returns to normal operation, and minimize the impact of faults on the system.

[0128] In this embodiment, a fault report is generated based on real-time fault data, predicted fault types for all critical fault nodes, fault maintenance optimization suggestions, and maintenance optimization results. The report details the fault diagnosis results, predicted fault types, maintenance optimization suggestions, and implemented maintenance measures.

[0129] The beneficial effects of the above technical solution are as follows: Based on the fault detection model, the real-time fault data of the collection line is used to detect faults and generate fault reports, which can improve the accuracy of fault detection. The proactive maintenance strategy can effectively reduce system downtime, optimize the allocation of maintenance resources, reduce maintenance costs, and improve the operational safety and stability of the collection line.

[0130] Example 8:

[0131] This invention provides an online detection method for power collection lines, such as... Figure 2 As shown, it includes:

[0132] Step 1: Obtain historical operating data of the power collection line and collect real-time operating data of the power collection line;

[0133] Step 2: Determine the normal operating range of the collection line based on historical operating data and construct a fault detection model;

[0134] Step 3: Determine the real-time fault data of the collector line based on real-time operating data and normal operating range;

[0135] Step 4: Based on the fault detection model, perform fault detection on the real-time fault data of the collector line and generate a fault report.

[0136] The beneficial effects of the above technical solution are as follows: By acquiring historical operating data of the power collection line, collecting real-time operating data of the power collection line, determining the normal operating range, constructing a fault detection model, determining real-time fault data of the power collection line based on real-time operating data and the normal operating range, and combining the fault detection model to perform fault detection and generate fault reports, it is possible to achieve real-time and accurate operating data acquisition and processing, accurately identify and locate key fault nodes, realize the efficiency and accuracy of intelligent fault detection, improve the safety and stability of the power collection line, reduce the risk of outage, and optimize the allocation of maintenance resources and maintenance strategies.

[0137] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / ROM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An online detection system for power collection lines, characterized in that, include: Data Acquisition Module: Acquires historical operating data of the power collection line and collects real-time operating data of the power collection line; Construction Module: Based on historical operating data, determine the normal operating range of the collection line and construct a fault detection model; the construction module includes: Key node category unit: Based on the historical normal operation vectors in all historical normal operation sub-operation data in the historical operation data, cluster analysis is performed to determine multiple key node categories, where each key node category includes multiple key nodes; Node category data unit: Extract the historical normal operation vectors of all key nodes in each key node category from the historical normal operation matrix of each historical normal sub-operation data, and determine the node category data of each key node category based on all historical normal operation vectors extracted from the historical normal operation matrix of all historical normal sub-operation data; Normal Operation Matrix Unit: Based on the node category data for each key node category, a normal operation matrix is ​​determined for each node category. The normal operation matrix unit includes: ； ； ； ； ； ； in, This represents the normal operation matrix of the k-th node category data. Let represent the lower limit and upper limit of the first feature of the category data of the k-th node, respectively. Let represent the lower limit and upper limit of the j-th feature of the k-th node category data, respectively. Let represent the lower limit and upper limit of the N1-th feature of the k-th node category data, respectively, where N1 represents the number of features in the historical normal operation vector. This represents the average value of the j-th feature of the k-th node category data. This represents the standard deviation of the j-th feature of the k-th node category data. This represents the eigenvalue of the j-th feature in the clustering vector of the k-th node category data. Let j represent the feature value of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category data at the t-th historical specified time period. This represents the number of historical normal operation vectors in the category data of the k-th node. This represents the eigenvalue of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category across all historical specified time periods. The eigenvalue of the j-th feature of the clustering vector of the k-th node category data. similarity value, Indicates the time smoothing factor. This indicates the first adjustment parameter. This indicates the second adjustment parameter. This indicates the third adjustment parameter. This represents the median of all j-th features sorted by the category data of the k-th node. This represents the 5th quantile after sorting all j-th features of the k-th node category data. This represents the 95th quantile after sorting all j-th features of the k-th node category data; Normal operating range unit: Based on the normal operating range matrix of node category data for all key node categories, the normal operating range of the collection line is determined; Construction Unit: The historical fault operation vectors in all historical fault sub-operation data in the historical fault operation data are used as the input of the fault detection model, and the historical fault types in all historical fault sub-operation data in the historical fault operation data are used as the output of the fault detection model; Training unit: Train the fault detection model based on historical fault operation data from the historical operation data; Determining module: Determines real-time fault data of the collector line based on real-time operating data and normal operating range; Fault module: Based on the fault detection model, it performs fault detection on real-time fault data of the power collection line and generates fault reports.

2. The online detection system for power collection lines according to claim 1, characterized in that, The data acquisition module includes: Historical sub-operation data unit: acquires historical sub-operation data of the collection line over multiple specified historical time periods. The historical sub-operation data includes historical normal sub-operation data and historical fault sub-operation data. The historical normal sub-operation data includes a historical normal operation matrix, and the historical fault sub-operation data includes a historical fault operation vector and historical fault type. Historical normal operation data and historical fault operation data unit: Historical normal operation data is determined based on historical normal sub-operation data of the collection line in all historical sub-operation data of all historical specified time periods. At the same time, historical fault operation data is determined based on historical fault sub-operation data of the collection line in all historical sub-operation data of all historical specified time periods. Historical Operation Data Unit: This unit contains historical normal operation data and historical fault operation data.

3. The online detection system for power collection lines according to claim 2, characterized in that, The data acquisition module includes: Operating area unit: Multiple operating areas are determined based on historical fault operation data in the historical operation data; Key node data unit: Based on the topology of the power collection line and all operating areas, key node data is determined. The key node data includes multiple key nodes, the data acquisition requirements of each key node, and the location of the key node. Installation unit: Sensor groups are installed at the corresponding key node locations based on the data acquisition requirements of each key node; Real-time operation data unit: Based on the real-time operation sub-data of each key node of the power collection line collected by the sensor group, the real-time operation sub-data of each key node is preprocessed, and the real-time operation data is determined based on the preprocessed real-time operation sub-data of all key nodes.

4. The online detection system for power collection lines according to claim 1, characterized in that, The module to be determined includes: Real-time running vector unit: Extract features from the preprocessed real-time running sub-data of each key node in the real-time running data to determine the real-time running vector of each key node; Fault-critical node unit: The real-time running vector of each critical node is compared with the normal operation matrix of the node category data of the critical node category corresponding to each critical node in the normal operation range. If the eigenvalue of any feature of the real-time running vector of the critical node is not between the lower limit and the upper limit of the corresponding normal operation matrix, it is determined to be a fault-critical node; otherwise, it is determined to be a normal critical node. Real-time fault data unit: Real-time fault data is determined based on all critical fault nodes and the real-time operation vector of each critical fault node.

5. The online detection system for power collection lines according to claim 1, characterized in that, Fault module, including: Fault prediction unit: Input all real-time running vectors from the real-time fault data into the fault detection model, and determine the predicted fault type and fault maintenance optimization suggestions for each critical fault node based on the output structure of the fault detection model; Maintenance and optimization unit: Performs maintenance and optimization for each critical fault node based on the predicted fault type and fault maintenance and optimization suggestions; Generation Unit: Generates a fault report based on real-time fault data, predicted fault types of all critical fault nodes, fault maintenance and optimization suggestions, and maintenance and optimization results.

6. A method for online detection of power collection lines, characterized in that, include: Step 1: Obtain historical operating data of the power collection line and collect real-time operating data of the power collection line; Step 2: Determine the normal operating range of the collector line based on historical operating data and construct a fault detection model, including: Key node category unit: Based on the historical normal operation vectors in all historical normal operation sub-operation data in the historical operation data, cluster analysis is performed to determine multiple key node categories, where each key node category includes multiple key nodes; Node category data unit: Extract the historical normal operation vectors of all key nodes in each key node category from the historical normal operation matrix of each historical normal sub-operation data, and determine the node category data of each key node category based on all historical normal operation vectors extracted from the historical normal operation matrix of all historical normal sub-operation data; Normal Operation Matrix Unit: Based on the node category data for each key node category, a normal operation matrix is ​​determined for each node category. The normal operation matrix unit includes: ； ； ； ； ； ； in, This represents the normal operation matrix of the k-th node category data. Let represent the lower limit and upper limit of the first feature of the category data of the k-th node, respectively. Let represent the lower limit and upper limit of the j-th feature of the k-th node category data, respectively. Let represent the lower limit and upper limit of the N1-th feature of the k-th node category data, respectively, where N1 represents the number of features in the historical normal operation vector. This represents the average value of the j-th feature of the k-th node category data. This represents the standard deviation of the j-th feature of the k-th node category data. This represents the eigenvalue of the j-th feature in the clustering vector of the k-th node category data. Let j represent the feature value of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category data at the t-th historical specified time period. This represents the number of historical normal operation vectors in the category data of the k-th node. This represents the eigenvalue of the j-th feature of the historical normal operation vector of the i-th key node in the key node category of the k-th node category across all historical specified time periods. The eigenvalue of the j-th feature of the clustering vector of the k-th node category data. similarity value, Indicates the time smoothing factor. This indicates the first adjustment parameter. This indicates the second adjustment parameter. This indicates the third adjustment parameter. This represents the median of all j-th features sorted by the category data of the k-th node. This represents the 5th quantile after sorting all j-th features of the k-th node category data. This represents the 95th quantile after sorting all j-th features of the k-th node category data; Normal operating range unit: Based on the normal operating range matrix of node category data for all key node categories, the normal operating range of the collection line is determined; Construction Unit: The historical fault operation vectors in all historical fault sub-operation data in the historical fault operation data are used as the input of the fault detection model, and the historical fault types in all historical fault sub-operation data in the historical fault operation data are used as the output of the fault detection model; Training unit: Train the fault detection model based on historical fault operation data from the historical operation data; Step 3: Determine the real-time fault data of the collector line based on real-time operating data and normal operating range; Step 4: Based on the fault detection model, perform fault detection on the real-time fault data of the collector line and generate a fault report.

Images