Power distribution network fault section positioning method based on multi-source information fusion and related device

Abstract

The invention provides a power distribution network fault section positioning method based on multi-source information fusion and a related device, and belongs to the field of power grid safety. Comprising the steps of collecting multi-source data of a power distribution network area; preprocessing the collected multi-source data, and establishing a data mapping relationship among different data sources, so as to obtain integrated data; respectively determining a fault judgment value and a fault probability of each section of the power distribution network by utilizing the integrated data, and further determining a fault section of the power distribution network; the fault analysis result of the fault section of the power distribution network is determined by combining the image data of the multi-source data, the solution of the fault section is obtained by using the big data, and the fault positioning and analysis result is stored so as to provide reference for next fault positioning. By collecting and integrating data from a plurality of information sources and processing and analyzing the information, the fault diagnosis and repair time can be effectively shortened, the loss caused by faults is reduced, and the reliability of power supply service is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of power grid safety, and particularly relates to a power distribution network fault section positioning method based on multi-source information fusion and a related device. BACKGROUND

[0002] With the rapid development of social economy and the continuous improvement of people's living standards, society has increasingly stringent requirements for the reliability and stability of power supply. As a key energy for the operation of modern society, electricity is widely used in industrial production, commercial operation and residential life and other fields. Any interruption or instability of power supply may cause production stagnation, commercial losses or even affect the normal life order of residents, causing huge economic losses and social impact. Under this environment, the efficient and stable operation of the power system has become one of the core goals of the sustainable development of the power industry.

[0003] With the rapid development of social economy and the continuous improvement of people's living standards, society has increasingly stringent requirements for the reliability and stability of power supply. As a key energy for the operation of modern society, electricity is widely used in industrial production, commercial operation and residential life and other fields. Any interruption or instability of power supply may cause production stagnation, commercial losses or even affect the normal life order of residents, causing huge economic losses and social impact. Under this environment, the efficient and stable operation of the power system has become one of the core goals of the sustainable development of the power industry. SUMMARY

[0004] Therefore, the present application aims to overcome the defects of the existing power distribution network fault section positioning technology and provide a power distribution network fault section positioning method based on multi-source information fusion. By integrating multi-source data obtained by various monitoring means, the actual operation state of the power distribution network is comprehensively and accurately reflected, so as to improve the accuracy and timeliness of fault positioning and effectively avoid misjudgment and missed judgment under complex faults and data errors.

[0005] In order to achieve the above-mentioned purpose, the technical scheme provided by the present application is as follows:

[0006] In the first aspect, the present application provides a power distribution network fault section positioning method based on multi-source information fusion, comprising the following steps:

[0007] Collecting multi-source data of the power distribution network area; the multi-source data at least includes operation state data for reflecting the operation state of the power distribution network, image data of the power distribution network site situation and work report data for recording the working condition of the power distribution network node;

[0008] The collected multi-source data is preprocessed, and the mapping relationship between the data of different data sources is established, so as to obtain integrated data;

[0009] Determine the fault judgment value and the fault probability of each section of the power distribution network by using the operation state data and the work report data in the integrated data respectively, and determine the fault section of the power distribution network by comprehensively determining the fault judgment value and the fault probability.

[0010] Further, the operation state data in the integrated data is used to determine the fault judgment value, including:

[0011] Based on big data, the data of each section of the power distribution network when there is an anomaly or a fault is obtained, and the fault features are obtained therefrom;

[0012] Each type of data in the operation state data collected by each section node of the power distribution network is matched with the corresponding fault feature, and the fault judgment value based on each type of data is obtained according to the similarity between the data;

[0013] The fault judgment values meeting the matching condition are fused to obtain the final fault judgment value.

[0014] Further, in the step of obtaining the fault judgment value based on each type of data according to the similarity between the data, the similarity between the collected data and the fault feature data is calculated by using the cosine similarity formula, and the basic fault judgment value is determined according to the calculated similarity.

[0015] Further, the work report data in the integrated data is used to determine the fault probability, including:

[0016] The historical fault records of each section of the power distribution network are obtained according to the work report data;

[0017] The number of faults in a unit time is divided by the unit time to obtain the fault probability.

[0018] Further, the fault section of the power distribution network is determined by comprehensively determining the fault judgment value and the fault probability, including:

[0019] The fault probability of each section node of the power distribution network is fused with the corresponding fault judgment value to obtain the fault coefficient of each section node;

[0020] All section nodes of the power distribution network are traversed, and the fault coefficient values of each node are compared;

[0021] The section of the power distribution network corresponding to the node with the largest fault coefficient value is selected as the fault section of the power distribution network.

[0022] Further, the multi-source data of the power distribution network region is collected, including:

[0023] The operation state parameters of the power distribution network are collected by various types of sensors in the power distribution network to obtain the operation state data;

[0024] The image data of the change of the field environment of the power grid, the appearance state of the power distribution network and the personnel activity are acquired through the cameras between the regional nodes of the power distribution network transmission line;

[0025] The work report data is obtained by collecting the inspection records, the maintenance reports of the power distribution network and the operation and maintenance logs automatically generated by the system from each node of the power distribution network.

[0026] Further, the preprocessing of the collected multi-source data includes:

[0027] According to the pre-set key information related to fault positioning, the corresponding data subset is extracted from the multi-source data;

[0028] The data in the data subset is cleaned and converted to obtain the unified structured data.

[0029] In the second aspect, the present application provides a power distribution network fault section positioning device based on multi-source information fusion, comprising:

[0030] The data monitoring module is used for collecting the multi-source data of the power distribution network region; the multi-source data at least includes the operation state data for reflecting the operation state of the power distribution network, the image data of the field situation of the power distribution network and the work report data for recording the work situation of the power distribution network node;

[0031] The data integration module is used for preprocessing the collected multi-source data and establishing the mapping relationship between the data of different data sources, so as to obtain the integrated data;

[0032] The analysis and positioning module is used for determining the fault judgment value and the fault probability of each section of the power distribution network by using the operation state data and the work report data in the integrated data respectively, and determining the fault section of the power distribution network by comprehensively determining the fault judgment value and the fault probability;

[0033] The intelligent diagnosis module is used for determining the fault analysis result of the fault section of the power distribution network by combining the image data of the multi-source data, and obtaining the solution of the fault section by using big data, and storing the fault positioning and analysis result, so as to provide a reference for the next fault positioning.

[0034] In the third aspect, the present application provides a computer device, which comprises a processor and a memory:

[0035] The memory is used for storing the computer program and sending the instructions of the computer program to the processor;

[0036] The processor executes the method for positioning the fault section of the power distribution network based on multi-source information fusion according to the instructions of the computer program.

[0037] In a fourth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for locating a fault section of a power distribution network based on multi-source information fusion according to the first aspect.

[0038] To sum up, the present application provides a method for locating a fault section of a power distribution network based on multi-source information fusion and related devices, which comprises collecting multi-source data of a power distribution network area; the multi-source data at least includes operation state data for reflecting an operation state of the power distribution network, image data of a field situation of the power distribution network, and work report data for recording a work situation of a node of the power distribution network; the collected multi-source data is preprocessed, and a mapping relationship of data between different data sources is established, so as to obtain integrated data; the operation state data and the work report data in the integrated data are used to determine a fault judgment value and a fault probability of each section of the power distribution network, and the fault judgment value and the fault probability are comprehensively determined to determine a fault section of the power distribution network; the image data of the multi-source data is combined to determine a fault analysis result of the fault section of the power distribution network, and a solution of the fault section is obtained by using big data, and the fault positioning and analysis result are stored to provide a reference for next time fault positioning. The present application collects and integrates data from multiple information sources, processes and analyzes these information, so as to realize accurate and rapid positioning of the fault section, which can effectively shorten the fault diagnosis and repair time, reduce the loss caused by the fault, and improve the reliability of power supply service. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0040] Figure 1 A flow chart of a method for locating a fault section of a power distribution network based on multi-source information fusion is provided for the embodiments of the present application;

[0041] Figure 2 An analysis and positioning flow chart is provided for the embodiments of the present application;

[0042] Figure 3 A composition block diagram of a device for locating a fault section of a power distribution network based on multi-source information fusion is provided for the embodiments of the present application;

[0043] Figure 4 A composition block diagram of a computer device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0044] In order to make the objectives, characteristics and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the embodiments described below are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0045] Please refer to Figure 1 The embodiment of the present application provides a power distribution network fault section positioning method based on multi-source information fusion, comprising the following steps:

[0046] S1: Collecting multi-source data of the power distribution network area; the multi-source data at least includes operation state data for reflecting the operation state of the power distribution network, image data for recording the on-site situation of the power distribution network and work report data for recording the working condition of the nodes of the power distribution network.

[0047] It should be noted that the operation state data is used to reflect the operation state of the power distribution network, such as voltage, current, power and other electrical parameters. Abnormal fluctuations of these parameters may indicate the occurrence of a fault. The image data records the on-site situation of the power distribution network, such as the appearance of equipment, the condition of lines and the like, and directly shows the physical state of the equipment, whether there are visible signs of damage, overheating and the like. The work report data records the working condition of the nodes of the power distribution network, including the daily inspection records of the staff, the equipment maintenance records and the like, and provides data support from the aspects of artificial experience and historical working condition.

[0048] S2: Preprocessing the collected multi-source data and establishing the mapping relationship between the data of different data sources, so as to obtain integrated data.

[0049] It should be noted that the collected original data is subjected to cleaning, denoising, normalization and the like. For example, there may be abnormal values in the operation state data due to sensor errors or interference, which need to be removed through data cleaning. The image data may have problems such as blurring and uneven lighting, which need to be processed through image enhancement and the like. The work report data may have problems such as non-uniform format and missing information, which need to be standardized and supplemented.

[0050] Since the data structures and meanings of different data sources are different, the corresponding relationship between them needs to be established. For example, a node number in the operation state data is associated with the equipment image of the node in the image data and the record about the node in the work report data, so that different types of data can be verified and supplemented with each other to form integrated data.

[0051] S3: Determine the fault judgment value and the fault probability of each section of the power distribution network by using the running state data and the work report data in the integrated data respectively, and determine the fault section of the power distribution network by comprehensively analyzing the fault judgment value and the fault probability.

[0052] It should be noted that the fault judgment value of each section can be calculated according to the electrical parameters in the running state data. For example, if the current of a certain section exceeds the normal range to a certain extent, the fault judgment value of the section will increase accordingly. According to the historical fault information, equipment maintenance records and other information recorded in the work report data, the probability of failure of each section can be calculated. For example, a certain section has frequent failures in the past and the equipment is seriously aging, so the failure probability of the section will be higher. The fault judgment value and the fault probability are comprehensively analyzed to determine which section is most likely to fail. For example, when the fault judgment value and the fault probability of a certain section are both high, the section can be determined as a fault section.

[0053] The embodiment provides a power distribution network fault section positioning method based on multi-source information fusion. By collecting and integrating data from multiple information sources, the information is processed and analyzed to accurately and quickly locate the fault section, which can effectively shorten the fault diagnosis and repair time, reduce the loss caused by the fault, and improve the reliability of power supply service.

[0054] In one embodiment, multi-source data of the power distribution network region is collected, including:

[0055] The running state parameters of the power distribution network are collected by various types of sensors in the power distribution network to obtain the running state data.

[0056] For example, various sensors such as temperature sensors, current sensors, voltage sensors, vibration sensors, etc. are installed at the node positions of the power distribution network. These sensors collect real-time data such as temperature, current, voltage, power factor, load rate and equipment vibration related to the operation of the power distribution network, which reflects the real-time running state of the power distribution network from the electrical performance perspective.

[0057] Image data of environmental changes, appearance states of the power distribution network and personnel activities are obtained by cameras between the nodes in the power transmission line area of the power distribution network.

[0058] For example, high-definition cameras are installed at key positions between nodes in the power transmission line area of the power distribution network. The cameras continuously capture environmental changes in the power grid site, such as whether there is construction influence around, whether there are foreign objects close by, etc. The cameras shoot the appearance state of the power distribution network, including whether the equipment shell is damaged, whether the line is obviously broken, etc. The cameras record personnel activities, such as whether there are personnel operating irregularly, etc. The image data can intuitively show the actual scene of the power distribution network site.

[0059] The work report data is obtained by collecting inspection records from each node of the power distribution network, power distribution network maintenance reports, and system automatically generated operation and maintenance logs.

[0060] For example, the inspection records generated by each node of the power distribution network are collected, which contain the on-site observation records of the equipment state by the inspection personnel; the power distribution network maintenance reports, which detail the maintenance time, maintenance content, and equipment state after maintenance; and the system automatically generated operation and maintenance logs, which cover the equipment running time, automatic alarm information, and the like. The work report data provides a text record of the historical operation and maintenance of the power distribution network.

[0061] In one embodiment, the preprocessing of the collected multi-source data includes:

[0062] S21: According to the pre-set key information related to fault location, a corresponding data subset is extracted from the multi-source data.

[0063] For the purpose of locating the fault section of the power distribution network, the key information related to fault location is pre-set. For example, for line short-circuit fault, the abnormal change of current and voltage is the key information; for transformer fault, the temperature, load rate and other parameters are crucial. From the collected multi-source data such as operation state data, image data and work report data, the corresponding data subset is extracted according to these key information. In the operation state data, the data related to the key electrical parameters is extracted; in the image data, the image segments that can reflect the key parts of the equipment or the environment area that may cause the fault are extracted; in the work report data, the records containing the key contents such as fault occurrence time, location, equipment state description, etc. are extracted. The purpose of this is to filter out the data that has actual value for fault location, remove a large amount of irrelevant or redundant data, and improve the efficiency and pertinence of subsequent processing.

[0064] S22: Data cleaning and conversion are performed on the data in the data subset to obtain unified structured data.

[0065] The data in the extracted data subset is cleaned. This step is mainly to improve the quality and availability of data. In the running state data, there may be abnormal data (such as values exceeding the normal range) and missing data due to sensor failure, communication interference, etc. Through data cleaning, statistical analysis methods (such as calculating the mean and standard deviation to identify outliers) and data filling techniques (such as linear interpolation and machine learning-based prediction algorithm to fill missing values) are used to process these data to ensure the accuracy and integrity of the data. For image data, cleaning operations include removing blurred, damaged or incomplete images, and removing noise through image recognition and noise reduction algorithms (such as Gaussian filtering and median filtering) to improve image clarity and quality for subsequent accurate image analysis. In the work report data, cleaning mainly checks and corrects data format errors (such as inconsistent date formats and text formats), removes duplicate records and irrelevant redundant information, making the data more standardized and accurate.

[0066] After completing data cleaning, the data is converted to convert different types and formats of data into unified structured data. For running state data, data collected by different sensors with different units and dimensions are unified in units and standardized to make them comparable.

[0067] Through data cleaning and conversion, unified structured data is obtained, so that data from different sources and types can be processed and analyzed in a common framework. Then the mapping relationship between data from different data sources is established, and the data is aggregated by matching and associating data from different data sources through common attributes, and the associated data is stored for subsequent analysis.

[0068] Please refer to Figure 2 , Figure 2 a flow for analyzing and positioning fault sections is shown. The following describes other embodiments of the present application in combination with the flow shown in Figure 2 .

[0069] In one embodiment, the running state data in the integrated data is used to determine the fault judgment value, including:

[0070] S31: Based on big data, the data situation when each section of the power distribution network has an anomaly or a fault is obtained, and the fault features are obtained therefrom.

[0071] With the help of big data technology, a large amount of historical data in the operation process of the power distribution network is collected, and these massive historical data are deeply analyzed and mined. Machine learning, data statistics and other methods are used to identify the data features presented when each section of the power distribution network has an anomaly or a fault, i.e. the fault features.

[0072] S32: Match each type of operation state data collected by each section node of the power distribution network with the corresponding fault feature respectively, and obtain the fault judgment value of each type of data based on the similarity between the data.

[0073] The operation state data collected by the section nodes of the power distribution network usually contains multiple types, such as current, voltage, temperature, power factor, etc. A suitable similarity calculation method, such as cosine similarity, Euclidean distance, etc., is used to measure the similarity between the collected operation state data and the fault feature data.

[0074] Specifically, for the data collected by the current section node of the power distribution network and the obtained fault feature, the following formula can be used for matching:

[0075] F = g(D)

[0076] Where F is the output fault feature vector, g is the function, D is the collected node data, by comparing the output F value with a set of fault feature data obtained by big data, the fault feature value is preliminarily judged, and the remaining feature data is compared to obtain the fault feature matching result value of the current section node of the power distribution network.

[0077] S33: Fuse each fault judgment value that meets the matching condition to obtain the final fault judgment value.

[0078] In order to ensure the accuracy of fault judgment, certain matching conditions are set. Only when the fault judgment value of a certain type of data meets these conditions, it will be included in the subsequent fusion calculation. The comprehensive processing of each fault judgment value that meets the matching condition can use fusion methods such as weighted average method, voting method, etc.

[0079] In further embodiments, in obtaining the fault judgment value of each type of data based on the similarity between the data, the cosine similarity formula is used to calculate the similarity between the collected data and the fault feature data, and the basic fault judgment value is determined according to the calculated similarity, as follows:

[0080]

[0081] Wherein V1 is the collected operating state data of the distribution network section node, such as voltage and current data; V2 is the corresponding data of the fault feature obtained by big data, such as voltage and current data. Taking voltage and current data as an example, V1=(x1, y2), V2=(x2, y2), wherein x is the voltage value, and y is the current value. By comparison, it is preliminarily judged whether the current voltage value of the current section node matches the current voltage value obtained by big data, to obtain a basic fault judgment value Q, and further judgment is continued on the section node. If it matches the remaining fault conditions, the basic fault judgment value is increased synchronously Q, and the fault coefficient is calculated.

[0082] In one embodiment, further, the working report data in the integrated data is used to determine the fault probability, including:

[0083] S34: Obtain the historical fault records of each section of the distribution network according to the working report data.

[0084] The working report data is an important information carrier generated in the daily operation and maintenance process of the distribution network, and contains a large amount of detailed information about each section of the distribution network. By organizing these working report data, the contents related to the historical faults of each section of the distribution network can be extracted therefrom.

[0085] S35: Divide the number of faults in a unit time by the unit time to obtain the fault probability.

[0086] The unit time is a predefined time interval. After the unit time is determined, the number of faults occurring in the unit time for each section of the distribution network is counted. The number of faults counted in the unit time for each section is divided by the unit time, and the fault probability of the section in the time period is obtained. Specifically as follows:

[0087]

[0088] Wherein n is the number of faults in the unit time, t is the unit time, and A is the fault probability

[0089] In one embodiment, the fault section of the distribution network is determined by combining the fault judgment value and the fault probability, including:

[0090] S36: Fuse the fault probability of each section node of the distribution network with the corresponding fault judgment value to obtain the fault coefficient of each section node. The fusion can be performed according to the following formula:

[0091]

[0092] Wherein B(P i ) is the fault coefficient of the node of the distribution network, P i is the i-th node position of the distribution network, P is the distribution network, and Ai is the fault probability of the i-th node of the distribution network, Q i is the fault judgment value of the i-th node of the distribution network, and the node with the largest fault coefficient interval is determined as the fault interval.

[0093] S37: Traverse all interval nodes of the distribution network, and compare the fault coefficient values of the nodes.

[0094] S38: Select the distribution network interval corresponding to the node with the largest fault coefficient value as the fault section of the distribution network.

[0095] In one embodiment, the method further comprises:

[0096] S4: Determine the fault analysis result of the fault section of the distribution network based on the image data of the multi-source data, obtain the solution of the fault section by using big data, store the fault positioning and analysis result, so as to provide a reference for the next fault positioning.

[0097] It should be noted that the fault analysis result is analyzed according to the specific reason of the fault based on the image data of the fault section, combined with professional knowledge and experience. For example, it is observed from the image that a certain line has obvious damage or a certain device component has burning signs, so that the type and possible cause of the fault are determined. Then, by using big data technology, the processing records and solutions of similar faults in history are analyzed, combined with the specific situation of the current fault, to obtain a solution suitable for the current fault. For example, for a certain type of device fault, big data can provide information such as the best maintenance method, required parts, and maintenance personnel's experience. Finally, the fault positioning result (which section has a fault), the fault analysis result (the cause of the fault), and the solution are stored to form a fault case library. When a similar fault occurs in the distribution network next time, historical cases can be referred to, and the fault positioning and processing can be faster, thereby improving the efficiency and accuracy of fault processing.

[0098] Based on the same inventive concept, the embodiments of the present application also provide a multi-source information fusion based distribution network fault section positioning device for implementing the above-mentioned multi-source information fusion based distribution network fault section positioning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in the following multi-source information fusion based distribution network fault section positioning device embodiment can be referred to the limitations of the multi-source information fusion based distribution network fault section positioning method described above, which will not be repeated here.

[0099] Please refer to Figure 3 The embodiments of the present application also provide a multi-source information fusion based distribution network fault section positioning device, which comprises:

[0100] The data monitoring module is used for real-time monitoring of the power distribution network based on sensors, cameras and work reports. Sensors are installed at each node of the power distribution network, including temperature sensors, current sensors, voltage sensors and vibration sensors. Real-time collection and transmission of operating state parameters of the power distribution network are performed. The monitored parameters include temperature, current, voltage, power factor, load rate and equipment vibration. High-definition cameras are installed between regional nodes of the power transmission line of the power distribution network to capture real-time environmental changes, appearance status of the power distribution network and personnel activities. The data monitoring module also collects and analyzes work reports from each node of the power distribution network to obtain power grid operating state information. The work reports include inspection records, power distribution network maintenance reports and system automatically generated operation and maintenance logs. The obtained data is uploaded to the data integration module for integrated processing.

[0101] The data integration module is used for integrating the data of the power distribution network nodes in the obtained multi-source data, extracting a data subset related to the integration target, removing repeated, missing and erroneous data, unifying the format of the data, establishing a mapping relationship between the data of different data sources, performing aggregation processing on the data, matching and associating the data of different data sources through common attributes, storing the associated data, and uploading the data to the data analysis module for analysis.

[0102] The data integration means in the present application are all existing technologies, and will not be described in detail here. In the data integration process, repeated, missing and erroneous data are removed to ensure the accuracy and integrity of the integrated data. High-quality data is the basis for subsequent analysis and positioning accuracy, which helps to improve the accuracy and reliability of fault identification. Different sources of data often have different formats and coding methods. The data integration module unifies the data format and coding standard, so that the data between different data sources can be seamlessly connected and interacted. This not only facilitates subsequent data processing and analysis, but also improves the readability and maintainability of the data.

[0103] The analysis and positioning module is used for obtaining data conditions of existing abnormalities and faults of the power distribution network based on big data. The abnormalities and faults of the power distribution network include line breakage and short circuit conditions, transformer fault conditions and switch device fault conditions. The state data of the power distribution network under each abnormality and fault condition is different. In the line breakage and short circuit conditions of the power distribution network, the current increases, the voltage upstream of the breakage point increases, and the voltage downstream decreases. In the transformer fault condition, the current of the power distribution network increases, the voltage decreases and disappears, and high temperature is generated. In the switch device fault condition, the circuit is interrupted and the current is 0.

[0104] Based on the power distribution network historical fault record obtained in the work report, the fault probability of the power distribution network section is judged, and then the data collected by each power distribution network section node is matched with the obtained fault characteristics, and the fault coefficient of each power distribution network section node is judged by combining analysis, and the fault coefficient of the most abnormal power distribution network section node is obtained. The section node of the fault coefficient is determined as the fault section of the power distribution network.

[0105] The fault condition analysis of the power distribution network in the application is based on big data, and the working parameters are not consistent under different fault conditions. The system systematically collects, organizes and analyzes the historical fault records of the power distribution network from the work report, and records the time, place, type, cause and repair measures key information in detail. Through statistical analysis of these data, the system can identify the high-fault section, the frequency of specific type of fault and the main factors causing the fault. Based on this, the system can preliminarily evaluate the fault probability of each section of the power distribution network, lay a foundation for subsequent data matching and fault judgment. The system will accurately match the real-time or recently collected power distribution network section node data according to the identified fault characteristics. These data include current, voltage, temperature, humidity, load level and any monitoring index that may reflect the health status of the equipment. Through complex algorithms and models, the system can analyze the correlation between these data and known fault characteristics, and calculate the fault coefficient of each power distribution network section node. This fault coefficient is a quantitative index for indicating the possibility or risk degree of failure of the node in the current state.

[0106] The fault probability in the application is a quantitative index describing the possibility of failure of equipment or system within a certain time. Since the occurrence of equipment or system failure is random, it is difficult to accurately predict its exact occurrence time, so the fault probability becomes an important parameter for evaluating the reliability of equipment or system. Cosine similarity measures the similarity of two vectors in direction, without considering their size. It calculates the cosine value of the angle between two vectors to get the similarity score.

[0107] The intelligent diagnosis module is used to obtain the current power distribution network section node fault reason based on the analysis result of the analysis positioning module combined with the field image data, input the obtained fault reason, obtain the fault solution based on big data, and the working personnel first time to the positioning power distribution network node for troubleshooting, real-time record and save the fault result, make a decision for subsequent positioning.

[0108] The intelligent diagnosis module can quickly analyze and locate the fault cause, significantly shortening the time from fault discovery to diagnosis. Traditional fault troubleshooting often relies on manual experience and step-by-step troubleshooting, which is time-consuming and inefficient. However, the intelligent diagnosis module can quickly lock the fault root cause through big data analysis and algorithm model, so that the staff can handle the problem in the first time, greatly improving the efficiency of fault handling,

[0109] The intelligent diagnosis module is based on big data and machine learning technology, which can comprehensively consider various factors, including historical fault records, equipment operating status, and environmental parameters, to more accurately determine the fault cause. Compared with manual judgment, the intelligent diagnosis module can avoid the interference of subjective factors and improve the accuracy and reliability of fault diagnosis.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0111] With reference to Figure 4 The embodiment of the application also provides a computer device, comprising a memory and a processor and a computer program stored in the memory, when the computer program is executed on the processor, the method for locating fault section of power distribution network based on multi-source information fusion is realized.

[0112] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The computer device can include, but is not limited to, a processor and a memory. Those skilled in the art can understand, Figure 4 The computer device is only an example and does not limit the computer device, which can include more or fewer components than shown, or combine certain components, or different components, for example, it can also include input and output devices, network access devices and the like.

[0113] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0114] The memory can be an internal storage unit of the computer device in some embodiments, for example, a hard disk or a memory of the computer device. The memory can also be an external storage device of the computer device in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory can include both the internal storage unit and the external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory can also be used to temporarily store data that has been output or will be output.

[0115] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is run by a processor to implement the power distribution network fault section locating method based on multi-source information fusion.

[0116] In the embodiment, the integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-described embodiment methods through a computer program to instruct relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. The computer program is executed by a processor, and can implement the steps of each method embodiment described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0117] The embodiment of the present application provides a computer program product, including a computer program, which is executed by a processor to implement the power distribution network fault section positioning method based on multi-source information fusion as described in any of the above methods.

[0118] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0119] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0120] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other manners. For example, the described apparatus / terminal device embodiments are merely schematic. For example, the division of the modules or units is merely logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0121] The above embodiments are merely used to describe the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent; and the modification or replacement does not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for locating fault sections in a distribution network based on multi-source information fusion, characterized in that: The steps include: Collecting multi-source data of the distribution network area; the multi-source data includes at least operating status data for reflecting the operating status of the distribution network, image data of the distribution network on-site conditions, and work report data for recording the working conditions of the distribution network nodes; Preprocessing the collected multi-source data and establishing a mapping relationship between data from different data sources to obtain integrated data; The operating status data and the work report data in the integrated data are respectively used to determine the fault judgment value and the fault probability of each section of the distribution network, and the fault section of the distribution network is determined by combining the fault judgment value and the fault probability.

2. The method for locating a fault section in a distribution network based on multi-source information fusion according to claim 1, characterized in that: Determining a fault judgment value using the operating status data in the integrated data includes: Based on big data, we can obtain data on abnormalities and faults in each section of the distribution network and obtain fault characteristics from them; Matching each type of data in the operating status data collected by each interval node of the distribution network with the corresponding fault characteristics, and obtaining the fault judgment value based on each type of data according to the similarity between the data; The fault judgment values ​​that meet the matching conditions are merged to obtain the final fault judgment value.

3. The method for locating a fault section in a distribution network based on multi-source information fusion according to claim 2, characterized in that: In obtaining the fault judgment value based on various data according to the similarity between the data, the cosine similarity formula is used to calculate the similarity between the collected data and the fault feature data, and the basic fault judgment value is determined according to the calculated similarity.

4. The method for locating a fault section in a distribution network based on multi-source information fusion according to claim 2, characterized in that: Determining a failure probability using the work report data in the integrated data includes: Obtaining historical fault records of each section of the distribution network based on the work report data; The failure probability is obtained by dividing the number of failures per unit time in each section by the unit time.

5. The method for locating a fault section in a distribution network based on multi-source information fusion according to claim 1, characterized in that: Determining the fault section of the distribution network by combining the fault judgment value and the fault probability includes: The fault probability of each distribution network interval node is integrated with the corresponding fault judgment value to obtain the fault coefficient of each interval node; Traversing all the nodes in the distribution network and comparing the numerical values ​​of the fault coefficients of the nodes; The distribution network section corresponding to the node with the largest fault coefficient value is selected as the distribution network fault section.

6. The method for locating a fault section in a distribution network based on multi-source information fusion according to claim 1, characterized in that: Collect multi-source data in the distribution network area, including: Collecting distribution network operating status parameters through various types of sensors in the distribution network to obtain the operating status data; Through cameras between nodes in the distribution network transmission line area, image data of grid site environment changes, distribution network appearance status and personnel activities are obtained; The work report data is obtained by collecting inspection records from various nodes of the distribution network, distribution network maintenance reports and operation and maintenance logs automatically generated by the system.

7. The method for locating a fault section in a distribution network based on multi-source information fusion according to claim 1, characterized in that: Preprocessing the collected multi-source data includes: Extracting a corresponding data subset from the multi-source data based on pre-set key information related to fault location; The data in the data subset is cleaned and converted to obtain unified structured data.

8. A distribution network fault section location device based on multi-source information fusion, characterized in that: include: A data monitoring module is used to collect multi-source data in the distribution network area; the multi-source data includes at least operating status data for reflecting the operating status of the distribution network, image data of the distribution network on-site conditions, and work report data for recording the working conditions of the distribution network nodes; A data integration module is used to pre-process the collected multi-source data and establish a mapping relationship between the data of different data sources to obtain integrated data; An analysis and positioning module is used to respectively use the operating status data and the work report data in the integrated data to determine the fault judgment value and fault probability of each section of the distribution network, and to determine the fault section of the distribution network by combining the fault judgment value and the fault probability.

9. A computer device, characterized in that: The device includes a processor and a memory: The memory is used to store the computer program and send instructions of the computer program to the processor; The processor executes the method for locating a fault section in a distribution network based on multi-source information fusion according to any one of claims 1 to 7 according to the instructions of the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for locating a fault section in a distribution network based on multi-source information fusion according to any one of claims 1 to 7 is implemented.

Images