Distribution network multi-parameter data fusion fault positioning method and system

Abstract

The invention discloses a distribution network multi-parameter data fusion fault positioning method and system, and the method and system achieve the omnibearing monitoring of a power distribution network fault through the collection of multiple types of data, such as electrical signals, video images, meteorological information and environmental parameters. Compared with a traditional fault positioning method of a single information source, the system can reflect the fault condition more truly, and the positioning accuracy and reliability are remarkably improved. Machine learning or a deep learning model is utilized to analyze fusion data, fault types and positions are automatically identified, intelligent diagnosis is realized, manual intervention is reduced, the operation and maintenance cost is reduced, and the processing efficiency and accuracy are improved. The real-time data acquisition and transmission technology guarantees the system to monitor in real time and rapidly alarm potential faults. According to the method, historical data and an expert knowledge base are combined, fault causes are deeply analyzed, accurate information and maintenance suggestions are provided for maintenance personnel, operation and maintenance decisions are optimized, and the maintenance efficiency and quality are enhanced. The system provides an efficient and intelligent solution for distribution network fault positioning.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a distribution network multi-parameter data fusion fault locating method and system. Background Art

[0002] In the power system, the distribution network is the key link between the transmission network and the end users. With the continuous expansion of the power grid and the increasingly complex operating environment, the rapid and accurate location of distribution network faults has become an important means to improve power supply reliability and service quality.

[0003] Traditional fault location methods mainly rely on traveling wave fault location or recording wave fault location devices, which estimate the location of the fault point by capturing specific signals such as traveling waves or voltage / current waveform changes generated when a fault occurs, combined with line parameters and algorithms. However, these methods often only focus on the changes in electrical signals, while ignoring other external factors that may affect the occurrence of faults.

[0004] In order to gain a more comprehensive understanding of the fault situation, some advanced fault location systems have begun to integrate video monitoring functions to capture the environment and abnormal phenomena around the line through real-time video images. However, the application of this single visual information still cannot fully cover all potential causes of faults, especially in complex and changeable natural environments. For example, extreme weather conditions such as strong winds, heavy rains, lightning, etc. may cause tree branches to break and touch the wires, causing short circuits, or high temperatures may cause equipment to overheat and cause failures. In addition, line aging is also a factor that cannot be ignored. Lines in long-term operation may experience reduced insulation performance due to material fatigue, corrosion, etc., thereby increasing the risk of failure.

[0005] Therefore, relying solely on electrical signal analysis and video monitoring can no longer meet the high standards of fault management in modern distribution networks. A more comprehensive approach is needed to assess and predict the occurrence of faults, which requires the integration and analysis of multiple types of data. Summary of the invention

[0006] In order to solve the above problems, the present invention provides a distribution network multi-parameter data fusion fault location method, which aims to solve the limitations of the existing technology and improve the accuracy and efficiency of fault location by integrating various types of data sources.

[0007] A first aspect of an embodiment of the present invention discloses a distribution network multi-parameter data fusion fault location method, comprising the following steps:

[0008] A distribution network multi-parameter data fusion fault location method, characterized in that it includes the following steps:

[0009] Step S1, multi-source data collection: using a multi-parameter fault location device installed along the distribution line to collect various types of data from different sources in real time, and transmit them to the Internet of Things platform in real time through wireless communication technology;

[0010] Step S2, data preprocessing and feature extraction: cleaning and preprocessing the various data received on the IoT platform to eliminate noise and outliers; and extracting features for each data type from these data to extract feature information required for fault detection and location;

[0011] Step S3, multi-parameter data fusion: using a data fusion algorithm to combine the feature information data from different sources extracted in step S2 to obtain a fused multi-parameter data set;

[0012] Step S4, fault detection and location: using machine learning or deep learning models to analyze the fused multi-parameter data set, and automatically identifying the fault type, fault location, and fault signs;

[0013] Step S5, fault cause analysis: after determining the fault location, analyze the possible fault causes;

[0014] Step S6, report generation and feedback: According to the identified fault type, fault location, fault signs and analyzed possible fault causes, a detailed fault analysis report is automatically generated to provide maintenance personnel with accurate fault information and recommended maintenance measures.

[0015] Preferably, the multiple types of data described in step S1 include: electrical signals, video images, meteorological information and environmental parameters.

[0016] Preferably, in step S2, "extracting features from these data for each data type to extract feature information required for fault detection and location" includes:

[0017] Extract the fluctuation characteristics of current and voltage from electrical signals; extract abnormal phenomena from video images; extract extreme weather conditions that may affect the status of the line from meteorological information; extract temperature and humidity changes from environmental parameters.

[0018] Preferably, the machine learning or deep learning model in step S4 is pre-trained with a large amount of fault data, and the model can:

[0019] Analyze the fused multi-parameter data to distinguish the fault signs caused by different reasons;

[0020] Automatically and accurately identify the specific type and location of the fault;

[0021] Providing fault location results based on model analysis, which reflect the actual location and potential causes of the fault.

[0022] Preferably, the method further comprises the following steps:

[0023] When potential signs of failure are detected, an alarm signal is generated and relevant information is pushed to the operation and maintenance personnel;

[0024] When an alarm signal is received, the multi-parameter fault location device will immediately activate the linkage mechanism and re-evaluate all relevant data sources to determine the cause of the alarm.

[0025] Preferably, the step S3 "multi-parameter data fusion: using a data fusion algorithm to integrate the feature information data from different sources extracted in step S2 to obtain a fused multi-parameter data set" includes the following sub-steps:

[0026] Select one or more data fusion algorithms from weighted average, Bayesian network, or deep learning data fusion algorithms to comprehensively process the feature information data from different data sources extracted in step S2;

[0027] Integrate the processed data into a unified data display window, which is used to intuitively present the fused multi-parameter data;

[0028] The integrated data is stored and processed to form a fused multi-parameter data set for use in subsequent steps.

[0029] A second aspect of an embodiment of the present invention discloses a distribution network multi-parameter data fusion fault location system, which adopts the method described in the first aspect and includes:

[0030] The data collection module 1 is used to collect electrical signals, video images, meteorological information and environmental parameters in real time through a multi-parameter fault location device installed along the distribution line, and transmit the collected data to the Internet of Things platform in real time through wireless communication technology;

[0031] Data preprocessing module 2 is used to clean and preprocess the received data on the IoT platform, eliminate noise and outliers, and extract feature information that is helpful for fault detection and location from these data;

[0032] Feature extraction module 3, used to extract features for each data type, including fluctuation characteristics of electrical signals, abnormal phenomena in video images, extreme weather conditions in meteorological information, and temperature and humidity changes in environmental parameters;

[0033] Fault detection and location module 4 uses machine learning or deep learning models to analyze the fused data and automatically identify the fault type and location;

[0034] Alarm generation module 5, when the system detects potential fault signs, generates an alarm signal and pushes relevant information to the operation and maintenance personnel;

[0035] A linkage module 6 is used to start the linkage mechanism of the multi-parameter fault location device after receiving the alarm signal, and re-evaluate all relevant data sources to determine the cause of the alarm;

[0036] The data fusion module 7 uses one or more data fusion methods such as weighted average, Bayesian network or deep learning to integrate data from different sources to form a unified data display window;

[0037] The alarm cause analysis and judgment module 8 is used to judge the specific cause of the alarm through in-depth analysis of multi-parameter data;

[0038] The report generation and feedback module 9 is used to automatically generate a detailed fault analysis report, provide maintenance personnel with accurate fault information and recommended maintenance measures, and continuously optimize model parameters according to the fault handling results.

[0039] Preferably, the data collection module 1 also includes a wireless communication module 11 for real-time data transmission, and the wireless communication module 11 supports 4G / 5G network wireless communication technology.

[0040] Preferably, the feature extraction module 3 also includes: a current and voltage feature extraction submodule 31 for extracting the fluctuation characteristics of current and voltage in electrical signals, an image feature extraction submodule 32 for extracting abnormal phenomena in video images, a feature extraction submodule 33 for extracting extreme weather conditions that may affect the line status in meteorological information; and a feature extraction submodule 34 for extracting temperature and humidity changes in environmental parameters.

[0041] A third aspect of an embodiment of the present invention discloses a computer device, comprising: a memory 100, a processor 200, and executable instructions stored in the memory and executable in the processor, wherein the processor implements the method described in the first aspect when executing the executable instructions.

[0042] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium having computer-executable instructions stored thereon, wherein the executable instructions, when executed by a processor, implement the method described in the first aspect.

[0043] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0044] 1. Implementation Example of this Case This case scheme realizes comprehensive monitoring of distribution network faults by collecting various types of data such as electrical signals, video images, meteorological information, and environmental parameters. Compared with the traditional fault location method that only relies on electrical signals or single visual information, the scheme of this case can more comprehensively reflect the actual situation of the fault and improve the accuracy and reliability of fault location. The fused multi-parameter data is analyzed by machine learning or deep learning models to automatically identify the type and location of the fault, realize intelligent diagnosis of the fault, reduce the need for manual intervention, reduce operation and maintenance costs, and improve the efficiency and accuracy of fault handling. Real-time data acquisition and transmission technology ensures that the system can monitor the status of the distribution network in real time and quickly generate alarm signals when potential fault signs are detected. Combined with historical data and expert knowledge base, the scheme of this case can deeply analyze the possible causes of the fault, provide maintenance personnel with accurate fault information and recommended maintenance measures, help optimize the operation and maintenance decision-making process, and improve maintenance efficiency and quality.

[0045] 2. In this case, the current and voltage fluctuation characteristics extracted from the electrical signals can directly reflect the operating status of the electrical equipment in the distribution network. When these characteristics exceed the normal range, it often means that the equipment has a fault or abnormality, such as a short circuit or open circuit. Abnormal phenomena such as sparks and smoke in the video image can provide intuitive fault indications. By extracting these features, the location and type of the fault can be quickly identified. Moreover, the specific manifestations of the current and voltage fluctuation characteristics, such as the fluctuation amplitude and frequency, can help determine the specific location of the fault and provide accurate fault location information for maintenance personnel. The abnormal phenomena in the video image combined with the geographic location information can further accurately locate the fault and improve maintenance efficiency. By extracting extreme weather conditions such as high temperature, strong wind, and heavy rain from meteorological information, potential fault risks can be warned in advance, providing enough time for operation and maintenance personnel to perform preventive maintenance. By extracting the temperature and humidity changes of environmental parameters, potential problems can be discovered and handled in a timely manner. In addition, by extracting these key feature information, rich input data can be provided for machine learning or deep learning models, enabling the model to more accurately identify the type and location of faults. In summary, the extraction of the above-mentioned types of data can help improve the intelligence level of operation and maintenance decisions, enabling operation and maintenance personnel to make more informed decisions based on more comprehensive data and information.

[0046] 3. Embodiment 2 of this case Through the multi-parameter fault location device and wireless communication module in the data collection module, the system can collect and transmit various data such as electrical signals, video images, meteorological information and environmental parameters in real time, ensuring the timeliness and integrity of the data, and providing a basis for the rapid detection and location of faults. The received data is cleaned, preprocessed and feature extracted by the data preprocessing module and the feature extraction module, effectively eliminating noise and outliers, and improving the accuracy and reliability of the data. The fault detection and location module uses machine learning or deep learning models to analyze the fused data, which can automatically identify the type and location of the fault, and realize intelligent detection and location of the fault. After receiving the alarm signal, the linkage module will start the linkage mechanism of the multi-parameter fault location device, re-evaluate all relevant data sources to determine the specific cause of the alarm, which helps the operation and maintenance personnel to quickly locate and solve the problem. The alarm cause analysis and judgment module can determine the specific cause of the alarm through in-depth analysis of multi-parameter data, providing more accurate fault information for the operation and maintenance personnel. The data fusion module uses one or more data fusion methods such as weighted average, Bayesian network or deep learning to integrate data from different sources to form a unified data display window, so that operation and maintenance personnel can intuitively understand the status and fault conditions of the distribution network. The setting of the report generation and feedback module allows maintenance personnel to provide accurate fault information and recommended maintenance measures, improving the accuracy and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 It is a schematic diagram of the process of the first embodiment of the present invention;

[0049] Figure 2 It is a structural block diagram of the second embodiment of the present invention.

[0050] Figure 3 It is a structural diagram of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be noted that the terms "first", "second", "third", "fourth", etc. in the specification and claims of the present invention are used to distinguish different objects rather than to describe a specific order. The terms "including" and "having" in the embodiments of the present invention and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] The embodiment of the present invention discloses a distribution network multi-parameter data fusion fault location method and system, which can simplify the identification construction process and improve the identification efficiency, and is conducive to the precise tuning of the identification method in the later stage.

[0054] Embodiment 1

[0055] like Figure 1 As shown, a distribution network multi-parameter data fusion fault location method includes the following steps:

[0056] Step S1: Multi-source data collection, using multi-parameter fault location devices installed along the distribution lines to collect various types of data including electrical signals such as current, voltage, video images, meteorological information such as temperature, humidity, wind speed, and environmental parameters such as temperature and humidity in real time, and transmit them to the Internet of Things platform in real time through wireless communication technologies such as 4G / 5G;

[0057] Step S2: Data preprocessing and feature extraction: cleaning and preprocessing the received data on the IoT platform to eliminate noise and outliers, and extracting features for each data type from these data to obtain the feature information required for fault detection and location;

[0058] Step S3: multi-parameter data fusion, using one or more advanced data fusion algorithms such as weighted average, Bayesian network or deep learning to combine the feature information data from different sources extracted in step S2 to obtain fused multi-parameter data;

[0059] Step S4: Fault detection and location, using machine learning or deep learning models to analyze the fused multi-parameter data and automatically identify the fault type and location;

[0060] Step S5: Fault cause analysis: after determining the fault location, possible fault causes are analyzed by combining historical data and expert knowledge base;

[0061] Step S6: Report generation and feedback. Based on the identified fault type, fault location and analyzed possible fault causes, a detailed fault analysis report including the fault type, location, cause and maintenance suggestions is automatically generated through preset templates and algorithms, providing maintenance personnel with accurate fault information and recommended maintenance measures.

[0062] As mentioned above, this solution realizes comprehensive monitoring of distribution network faults by collecting various types of data such as electrical signals, video images, meteorological information, and environmental parameters. Compared with the traditional fault location method that only relies on electrical signals or single visual information, this solution can more comprehensively reflect the actual situation of the fault and improve the accuracy and reliability of fault location. The fused multi-parameter data is analyzed by machine learning or deep learning models to automatically identify the fault type and location, realize intelligent diagnosis of faults, reduce the need for manual intervention, reduce operation and maintenance costs, and improve the efficiency and accuracy of fault handling. Real-time data acquisition and transmission technology ensures that the system can monitor the status of the distribution network in real time and quickly generate alarm signals when potential fault signs are detected. Combined with historical data and expert knowledge base, this solution can deeply analyze the possible causes of faults, provide maintenance personnel with accurate fault information and recommended maintenance measures, and help optimize the operation and maintenance decision-making process and improve maintenance efficiency and quality.

[0063] As a preferred embodiment, the multiple types of data described in step S1 include: electrical signals, video images, meteorological information, and environmental parameters. In this way, by collecting electrical signals such as current and voltage, which are traditional and critical fault indication data, combined with the intuitive on-site conditions provided by video images, and supplemented by meteorological information such as temperature, humidity, wind speed, and environmental parameters such as temperature, humidity, and air quality, it is possible to more comprehensively reflect the operating status of the distribution network and the background of the fault, which helps to more accurately locate the fault location, reduce false alarms and missed alarms, and improve the accuracy of fault location.

[0064] As a preferred implementation, in step S2, "extracting features from the data for each data type to extract feature information required for fault detection and location" includes:

[0065] Extract the fluctuation characteristics of current and voltage from electrical signals; extract abnormal phenomena such as sparks and smoke from video images; extract extreme weather conditions that may affect the line status from meteorological information; extract temperature and humidity changes from environmental parameters. In specific implementation, in the power system, the propagation speed of the traveling waves of current and voltage in the cable or transmission line is relatively fixed. When a fault occurs, the fault point will generate reflected waves, which will propagate back and forth between the fault point and the measurement point. By measuring the time it takes for the traveling wave to travel back and forth between the measurement point and the fault point, combined with the propagation speed of the traveling wave, the location of the fault point can be roughly determined.

[0066] As mentioned above, in this case, the current and voltage fluctuation characteristics extracted from the electrical signals can directly reflect the operating status of the electrical equipment in the distribution network. When these characteristics exceed the normal range, it often means that the equipment has a fault or abnormality, such as a short circuit or open circuit. Abnormal phenomena such as sparks and smoke in the video image can provide intuitive fault indications. By extracting these features, the location and type of the fault can be quickly identified. Moreover, the specific manifestations of the current and voltage fluctuation characteristics, such as the fluctuation amplitude and frequency, can help determine the specific location of the fault and provide accurate fault location information for maintenance personnel. The abnormal phenomena in the video image combined with the geographic location information can further accurately locate the fault and improve maintenance efficiency. By extracting extreme weather conditions such as high temperature, strong wind, and heavy rain from meteorological information, potential fault risks can be warned in advance, providing enough time for operation and maintenance personnel to perform preventive maintenance. By extracting the temperature and humidity changes of environmental parameters, potential problems can be discovered and handled in a timely manner. In addition, by extracting these key feature information, rich input data can be provided for machine learning or deep learning models, enabling the model to more accurately identify the type and location of faults. In summary, the extraction of the above-mentioned types of data can help improve the intelligence level of operation and maintenance decisions, enabling operation and maintenance personnel to make more informed decisions based on more comprehensive data and information.

[0067] As a preferred implementation, the machine learning or deep learning model in step S4 is pre-trained with a large amount of fault data, and the model can:

[0068] Analyze the fused multi-parameter data to distinguish the fault signs caused by different reasons;

[0069] Automatically and accurately identify the specific type and location of the fault;

[0070] Providing fault location results based on model analysis, which reflect the actual location and potential causes of the fault.

[0071] As described above, in step S4, through the training of a large amount of fault data, the model can learn the inherent laws and characteristics of the fault data, so as to more accurately analyze the fused multi-parameter data. The model can distinguish the signs of faults caused by different reasons, avoiding the misjudgment caused by confusion of causes in traditional methods. The model can automatically identify the specific type and location of the fault without manual intervention, which greatly improves the efficiency of fault identification. Compared with manual judgment, the model can locate the fault more accurately, reducing the misjudgment and missed judgment caused by human factors. The fault location results output by the model not only reflect the actual location of the fault, but also provide an analysis of the potential causes, which provides strong support for subsequent fault handling and repair. In addition, since the model can automatically and accurately identify the type and location of the fault, it can greatly shorten the time of fault handling and improve the operating efficiency of the equipment. At the same time, the potential cause analysis provided by the model helps maintenance personnel find the root cause of the fault more quickly and develop a more effective repair plan.

[0072] As a preferred embodiment, the method further comprises the following steps:

[0073] When potential signs of failure are detected, an alarm signal is generated and relevant information is pushed to the operation and maintenance personnel;

[0074] When an alarm signal is received, the multi-parameter fault location device will immediately activate the linkage mechanism and re-evaluate all relevant data sources to determine the cause of the alarm.

[0075] When potential signs of failure are detected, the system can quickly generate an alarm signal and push relevant information to the operation and maintenance personnel. In specific implementation, after receiving the alarm signal and related data, the operation and maintenance personnel can make more informed operation and maintenance decisions based on this information. For example, they can decide whether to shut down the machine for maintenance immediately or take other preventive measures based on the severity and location of the failure.

[0076] As mentioned above, this case helps to reduce the time window for fault development by setting up an immediate alarm mechanism, reduce the impact of the fault on the equipment or system, and improve the stability and reliability of the overall system. And by immediately starting the linkage mechanism after receiving the alarm signal and re-evaluating all relevant data sources, it helps to further confirm the cause of the alarm and reduce the possibility of false alarms. By introducing the combination of alarm and linkage mechanism, operation and maintenance personnel can more easily track and record fault conditions, providing strong support for subsequent fault analysis and processing.

[0077] As a preferred implementation, the step S3 "multi-parameter data fusion: using a data fusion algorithm to integrate the feature information data from different sources extracted in step S2 to obtain a fused multi-parameter data set" includes the following sub-steps:

[0078] Select one or more appropriate algorithms from weighted average, Bayesian network, and deep learning data fusion algorithms;

[0079] Taking the characteristic information data from different data sources such as current, voltage, temperature and other sensors extracted in step S2 as input;

[0080] The selected algorithm is used to comprehensively process these feature information data to extract higher-level fusion features. For example, when using a weighted average data fusion algorithm, a weight can be assigned to each data source according to its importance or reliability, and then the feature information data of each data source is multiplied by the corresponding weight, and then the sum is calculated to obtain the fused features.

[0081] Integrate the processed data into a unified data structure or format;

[0082] Design and implement a data display window that can intuitively present the fused multi-parameter data, including but not limited to data charts, dashboards or dynamic data streams;

[0083] Ensure that the data display window can clearly reflect the correlation and integration effects between different data sources.

[0084] The integrated data is properly stored, such as format conversion, compression or encryption;

[0085] The processed data is stored to form a fused multi-parameter data set, which includes feature information from different data sources and the fusion results between them;

[0086] Ensure that the data set can be easily accessed and used by subsequent steps such as fault location analysis and diagnosis.

[0087] As mentioned above, by selecting one or more appropriate algorithms from weighted average, Bayesian network and deep learning data fusion algorithms, customized fusion processing can be performed according to actual data characteristics and requirements, thereby improving the accuracy of data fusion. By designing a data display window, the fused multi-parameter data is presented in the form of intuitive data charts, dashboards or dynamic data streams, making the data easier to understand and analyze; at the same time, it can visually reflect the correlation and fusion effect between different data sources, providing a strong basis for decision support. By appropriately storing and processing the integrated data, such as format conversion, compression or encryption, the integrity, security and accessibility of the data can be ensured. In addition, since the fused multi-parameter data set contains feature information from different data sources and the fusion results between them, it provides comprehensive and accurate data support for subsequent steps such as fault location analysis and diagnosis.

[0088] Embodiment 2

[0089] A distribution network multi-parameter data fusion fault location system, comprising:

[0090] The data collection module 1 is used to collect electrical signals, video images, meteorological information and environmental parameters in real time through a multi-parameter fault location device installed along the distribution line, and transmit the collected data to the Internet of Things platform in real time through wireless communication technology;

[0091] Data preprocessing module 2 is used to clean and preprocess the received data on the IoT platform, eliminate noise and outliers, and extract feature information that is helpful for fault detection and location from these data;

[0092] Feature extraction module 3, used to extract features for each data type, including fluctuation characteristics of electrical signals, abnormal phenomena in video images, extreme weather conditions in meteorological information, and temperature and humidity changes in environmental parameters;

[0093] Fault detection and location module 4 uses machine learning or deep learning models to analyze the fused data and automatically identify the fault type and location;

[0094] Alarm generation module 5, when the system detects potential fault signs, generates an alarm signal and pushes relevant information to the operation and maintenance personnel;

[0095] A linkage module 6 is used to start the linkage mechanism of the multi-parameter fault location device after receiving the alarm signal, and re-evaluate all relevant data sources to determine the cause of the alarm;

[0096] The data fusion module 7 uses one or more data fusion methods such as weighted average, Bayesian network or deep learning to integrate data from different sources to form a unified data display window;

[0097] The alarm cause analysis and judgment module 8 is used to judge the specific cause of the alarm through in-depth analysis of multi-parameter data;

[0098] The report generation and feedback module 9 is used to automatically generate a detailed fault analysis report, provide maintenance personnel with accurate fault information and recommended maintenance measures, and continuously optimize model parameters according to the fault handling results.

[0099] The data collection module 1 also includes a wireless communication module 11 for real-time data transmission, and the wireless communication module 11 supports 4G / 5G network wireless communication technology.

[0100] As described above, through the multi-parameter fault location device and wireless communication module 11 in the data collection module 1, the system can collect and transmit various data such as electrical signals, video images, meteorological information and environmental parameters in real time, ensuring the timeliness and integrity of the data, and providing a basis for rapid detection and location of faults. The received data is cleaned, preprocessed and feature extracted by the data preprocessing module 2 and the feature extraction module 3, effectively eliminating noise and outliers, and improving the accuracy and reliability of the data. The fused data is analyzed by the fault detection and location module 4 using machine learning or deep learning models, which can automatically identify the fault type and location, and realize intelligent detection and location of faults.

[0101] After receiving the alarm signal, the linkage module 6 will start the linkage mechanism of the multi-parameter fault location device and re-evaluate all relevant data sources to determine the specific cause of the alarm, which helps the operation and maintenance personnel to quickly locate and solve the problem. The alarm cause analysis and judgment module 8 can determine the specific cause of the alarm through in-depth analysis of multi-parameter data, providing more accurate fault information for the operation and maintenance personnel. The data fusion module 7 uses one or more data fusion methods such as weighted average, Bayesian network or deep learning to integrate data from different sources to form a unified data display window, so that the operation and maintenance personnel can intuitively understand the status and fault conditions of the distribution network. The setting of the report generation and feedback module 9 is to facilitate maintenance personnel to provide accurate fault information and recommended maintenance measures, thereby improving the accuracy and reliability of the system.

[0102] As a preferred embodiment, the feature extraction module 3 also includes: a current and voltage feature extraction submodule 31 for extracting the fluctuation characteristics of current and voltage in electrical signals, an image feature extraction submodule 32 for extracting abnormal phenomena in video images, a feature extraction submodule 33 for extracting extreme weather conditions that may affect the line status in meteorological information; and a feature extraction submodule 34 for extracting temperature and humidity changes in environmental parameters.

[0103] Embodiment 3

[0104] like Figure 3 As shown, a computer device includes: a memory 100, a processor 200, and executable instructions stored in the memory and executable in the processor, and the processor implements the method described in Example 1 when executing the executable instructions.

[0105] Embodiment 4

[0106] A computer-readable storage medium stores computer-executable instructions, wherein the executable instructions, when executed by a processor, implement the method described in Embodiment 1.

[0107] In summary, the present invention significantly improves the efficiency, accuracy and adaptability of power grid planning through intelligent and automated means, optimizes the overall layout and operation effect of the power grid, and provides strong technical support for the construction and transformation of the power grid.

[0108] The above is a detailed introduction to a distribution network multi-parameter data fusion fault location method and system disclosed in an embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A distribution network multi-parameter data fusion fault location method, characterized in that: The following steps are involved: Step S1, multi-source data collection: using a multi-parameter fault location device installed along the distribution line to collect various types of data from different sources in real time, and transmit them to the Internet of Things platform in real time through wireless communication technology; Step S2, data preprocessing and feature extraction: cleaning and preprocessing the received data on the IoT platform to eliminate noise and outliers; And perform feature extraction on each data type from these data to extract the feature information required for fault detection and location; Step S3, multi-parameter data fusion: using a data fusion algorithm to combine the feature information data from different sources extracted in step S2 to obtain a fused multi-parameter data set; Step S4, fault detection and location: using machine learning or deep learning models to analyze the fused multi-parameter data set, and automatically identifying the fault type, fault location, and fault signs; Step S5, fault cause analysis: after determining the fault location, analyze the possible fault causes; Step S6, report generation and feedback: According to the identified fault type, fault location, fault signs and analyzed possible fault causes, a detailed fault analysis report is automatically generated to provide maintenance personnel with accurate fault information and recommended maintenance measures.

2. The distribution network multi-parameter data fusion fault location method according to claim 1 is characterized in that: The various types of data described in step S1 include: electrical signals, video images, meteorological information, and environmental parameters.

3. The distribution network multi-parameter data fusion fault location method according to claim 2 is characterized in that In step S2, "extracting features from these data for each data type to extract feature information required for fault detection and location" includes: Extract the fluctuation characteristics of current and voltage from electrical signals; extract abnormal phenomena from video images; extract extreme weather conditions that may affect the status of the line from meteorological information; extract temperature and humidity changes from environmental parameters.

4. The distribution network multi-parameter data fusion fault location method according to claim 1 is characterized in that: The machine learning or deep learning model in step S4 is pre-trained with a large amount of fault data, and the model can: Analyze the fused multi-parameter data to distinguish the fault signs caused by different reasons; Automatically and accurately identify the specific type and location of the fault; Providing fault location results based on model analysis, which reflect the actual location and potential causes of the fault.

5. The distribution network multi-parameter data fusion fault location method according to claim 1, characterized in that: The following steps are also included: When potential signs of failure are detected, an alarm signal is generated and relevant information is pushed to the operation and maintenance personnel; When an alarm signal is received, the multi-parameter fault location device will immediately activate the linkage mechanism and re-evaluate all relevant data sources to determine the cause of the alarm.

6. The distribution network multi-parameter data fusion fault location method according to claim 1, characterized in that: The step S3 "multi-parameter data fusion: using a data fusion algorithm to combine the feature information data from different sources extracted in step S2 to obtain a fused multi-parameter data set" includes the following sub-steps: Select one or more data fusion algorithms from weighted average, Bayesian network, or deep learning data fusion algorithms to comprehensively process the feature information data from different data sources extracted in step S2; Integrate the processed data into a unified data display window, which is used to intuitively present the fused multi-parameter data; The integrated data is stored and processed to form a fused multi-parameter data set for use in subsequent steps.

7. A distribution network multi-parameter data fusion fault location system, characterized in that: include: A data collection module (1) is used to collect electrical signals, video images, meteorological information and environmental parameters in real time through a multi-parameter fault location device installed along the distribution line, and transmit the collected data in real time to the Internet of Things platform through wireless communication technology; A data preprocessing module (2) is used to clean and preprocess the received data on the IoT platform, eliminate noise and outliers, and extract feature information from the data that is helpful for fault detection and location; A feature extraction module (3) is used to extract features for each data type, including fluctuation features of electrical signals, abnormal phenomena in video images, extreme weather conditions in meteorological information, and temperature and humidity changes in environmental parameters; Fault detection and location module (4), which uses machine learning or deep learning models to analyze the fused data and automatically identify the fault type and location; An alarm generation module (5) generates an alarm signal when the system detects potential fault signs and pushes relevant information to operation and maintenance personnel; A linkage module (6) is used to start the linkage mechanism of the multi-parameter fault location device after receiving the alarm signal, and re-evaluate all relevant data sources to determine the cause of the alarm; A data fusion module (7) uses one or more data fusion methods such as weighted average, Bayesian network or deep learning to integrate data from different sources to form a unified data display window; The alarm cause analysis and judgment module (8) is used to judge the specific cause of the alarm through in-depth analysis of multi-parameter data; The report generation and feedback module (9) is used to automatically generate a detailed fault analysis report, provide maintenance personnel with accurate fault information and recommended maintenance measures, and continuously optimize model parameters according to the fault handling results.

8. The multi-parameter data fusion analysis system according to claim 7, characterized in that: The data collection module (1) also includes a wireless communication module (11) for real-time data transmission, and the wireless communication module (11) supports 4G / 5G network wireless communication technology.

9. The multi-parameter data fusion analysis system according to claim 7, characterized in that: The feature extraction module (3) further comprises: a current and voltage feature extraction submodule (31) for extracting the fluctuation features of current and voltage in electrical signals, an image feature extraction submodule (32) for extracting abnormal phenomena in video images, a feature extraction submodule (33) for extracting extreme weather conditions that may affect the line status in meteorological information; and a feature extraction submodule (34) for extracting temperature and humidity change features in environmental parameters.

Images