A portable distribution intelligent gateway operation and maintenance device with low-voltage fault location and active emergency repair functions

Abstract

The present disclosure relates to a portable distribution intelligent gateway operation and maintenance device with low-voltage fault location and active emergency repair functions, and relates to the technical field of distribution networks; the portable distribution intelligent gateway operation and maintenance device includes: an intelligent gateway unit, a fault location unit, and an emergency repair decision-making unit. The intelligent gateway unit is equivalent to a primary operation and maintenance unit for preliminarily determining low-voltage fault types and fault data; the fault location unit is equivalent to a secondary operation and maintenance unit for locating low-voltage faults; the emergency repair decision-making unit is equivalent to a tertiary operation and maintenance unit for formulating active emergency repair strategies. Through hierarchical monitoring of the distribution network, the device has the functions of low-voltage fault location and active emergency repair. Since the three units are respectively used to implement different functions, it can be regarded as an integrated portable distribution intelligent gateway operation and maintenance device. It can achieve accurate low-voltage fault location and formulate reasonable active emergency repair strategies, thereby improving the reliability, stability, and safety of the distribution network.

Description

Technical Field

[0001] The present disclosure relates to the technical field of distribution networks, and more particularly, to a portable distribution intelligent gateway operation and maintenance device with low-voltage fault location and active repair functions. Background Art

[0002] A distribution network refers to a power grid that receives electric energy from a transmission network or a regional power plant and distributes it locally through distribution facilities or step by step according to voltage levels to various users. It is composed of overhead lines, cables, poles, distribution transformers, disconnect switches, reactive power compensators, and some ancillary facilities, and plays an important role in distributing electric energy in the power grid.

[0003] In order to ensure the reliability, safety, and stability of the operation of the distribution network, it is necessary to monitor the operation status of the distribution network for faults. Summary of the Invention

[0004] The object of the present disclosure is to provide a portable distribution intelligent gateway operation and maintenance device with low-voltage fault location and active repair functions. The portable distribution intelligent gateway operation and maintenance device can achieve accurate low-voltage fault location and formulate reasonable active repair strategies, thereby improving the reliability, stability, and safety of the distribution network.

[0005] To achieve the above object, the present disclosure provides a portable distribution intelligent gateway operation and maintenance device with low-voltage fault location and active repair functions, including: an intelligent gateway unit connected to the distribution network and configured to obtain distribution network data and determine a low-voltage fault type and fault data according to the distribution network data, the low-voltage fault type being used to characterize the cause of the low-voltage fault in the distribution network; a fault location unit connected to the intelligent gateway unit and configured to determine a low-voltage fault location result according to the low-voltage fault type and the fault data, the low-voltage fault location result being used to characterize the location where the low-voltage fault in the distribution network occurs, and the location where the low-voltage fault occurs being indicated by distribution network equipment; a repair decision-making unit connected to the intelligent gateway unit and the fault location unit respectively and configured to determine an active repair strategy according to the low-voltage fault location result and the low-voltage fault type and execute the active repair strategy.

[0006] Optionally, the low-voltage fault types include a first fault type, a second fault type, and a third fault type. Among them, the first fault type is used to characterize that the low-voltage fault of the distribution network is caused by a line fault, the second fault type is used to characterize that the low-voltage fault of the distribution network is caused by external reasons, and the third fault type is used to characterize that the low-voltage fault of the distribution network is caused by a line fault and external reasons; correspondingly, when the low-voltage fault type is the first fault type, the fault data includes line data, when the low-voltage fault type is the second fault type, the fault data includes external environment impact data, and when the low-voltage fault type is the third fault type, the fault data includes line data, external environment impact data, the corresponding impact weight of the line data, and the impact weight corresponding to the external environment impact data.

[0007] Optionally, the distribution network data includes line data and external environment impact data. The intelligent gateway unit is further configured to: compare the line data with first preset abnormal line data; if the line data matches the first preset abnormal line data, determine that the low-voltage fault type is the first fault type, and determine the line data as the fault data; if the line data does not match the first preset abnormal line data, compare the line data with second preset abnormal line data, and determine the low-voltage fault type and the fault data according to the comparison result.

[0008] Optionally, the intelligent gateway unit is further configured to: if the line data matches the second preset abnormal line data, determine that the low-voltage fault type is the third fault type, determine the line data and the external environment impact data as the fault data, and determine the corresponding impact weight of the line data and the impact weight corresponding to the external environment impact data according to the mismatch degree between the line data and the first preset abnormal line data and the match degree between the line data and the second preset abnormal line data; if the line data does not match the second preset abnormal line data, compare the external environment impact data with preset abnormal external environment impact data; if the external environment impact data matches the preset abnormal external environment impact data, determine that the low-voltage fault type is the second fault type, and determine the external environment impact data as the fault data.

[0009] Optionally, the fault location unit is further configured to: extract fault features from the fault data according to the low-voltage fault type, where the low-voltage fault type is used to indicate the extraction method of the fault features; determine the low-voltage fault location result according to the fault features and a pre-trained low-voltage fault location model.

[0010] Optionally, the fault location unit is further configured to: if the low-voltage fault type is the first fault type, extract abnormal line data and line data related to the abnormal line data from the line data as the fault feature; if the low-voltage fault type is the second fault type, extract abnormal environmental impact data from the external environmental impact data as the fault feature; if the low-voltage fault type is the third fault type, extract abnormal line data and line data related to the abnormal line data from the line data as the first fault feature, extract abnormal environmental impact data from the external environmental impact data as the second fault feature, and perform feature combination on the first fault feature and the second fault feature according to the corresponding influence weights of the line data and the external environmental impact data to obtain the final fault feature.

[0011] Optionally, the fault location unit is further configured to: obtain a training data set, where the training data set includes a plurality of first training samples and a plurality of second training samples. Each first training sample includes a first sample fault feature and a first sample label, and each second training sample includes a second sample fault feature and a second sample label. The first sample fault feature is a fault feature extracted based on line data, and the second sample feature is a fault feature extracted based on external environmental impact data. The first sample label and the second sample label respectively indicate the low-voltage fault generation location through the distribution network device identifier; train the to-be-trained low-voltage fault location model according to the training data set to obtain the pre-trained low-voltage fault model.

[0012] Optionally, the fault location unit is further configured to: perform primary training on the to-be-trained low-voltage fault location model according to the plurality of first training samples to obtain a primary-trained low-voltage fault location model; perform secondary training on the primary-trained low-voltage fault location model according to the plurality of second training samples to obtain a secondary-trained low-voltage fault location model; obtain third training samples and test samples according to the plurality of first training samples and the plurality of second training samples; perform tertiary training on the secondary-trained low-voltage fault location model according to the third training samples to obtain a tertiary-trained low-voltage fault location model; perform optimization training on the tertiary-trained low-voltage fault location model according to the test samples to obtain the pre-trained low-voltage fault location model.

[0013] Optionally, the emergency repair decision-making unit is further configured to: determine a first active emergency repair level according to the low-voltage fault type; determine a second active emergency repair level according to the distribution network equipment indicated by the low-voltage fault location result; and determine an active emergency repair strategy according to the first active emergency repair level, the second active emergency repair level, and a preset corresponding relationship, where the preset corresponding relationship includes: multiple preset emergency repair levels and emergency repair strategies respectively corresponding to the multiple preset emergency repair levels, and the emergency repair strategies include emergency repair personnel information, emergency repair response time, and emergency repair reference information.

[0014] Optionally, the portable distribution network intelligent gateway operation and maintenance device further includes: a visualization front end, which is respectively connected to the intelligent gateway unit, the fault location unit, and the emergency repair decision-making unit, and is configured to visually display the distribution network data, the low-voltage fault location result, and the emergency repair strategy.

[0015] Through the above technical solution, the portable distribution network intelligent gateway operation and maintenance device includes: an intelligent gateway unit, a fault location unit, and an emergency repair decision-making unit. Among them, the intelligent gateway unit is equivalent to a first-level operation and maintenance unit, which can preliminarily determine the low-voltage fault type and fault data; the fault location unit is equivalent to a second-level operation and maintenance unit, which can perform low-voltage fault location; the emergency repair decision-making unit is equivalent to a third-level operation and maintenance unit, which can formulate an active emergency repair strategy. Thus, the device has the functions of low-voltage fault location and active emergency repair through hierarchical distribution network monitoring. Moreover, since the three units are respectively used to implement different functions, it can be regarded as an integrated portable distribution network intelligent gateway operation and maintenance device. Therefore, the portable distribution network intelligent gateway operation and maintenance device can achieve accurate low-voltage fault location and formulate reasonable active emergency repair strategies, thereby improving the reliability, stability, and safety of the distribution network.

[0016] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification. Together with the following specific implementation, they are used to explain the present disclosure, but do not constitute a limitation to the present disclosure. In the accompanying drawings:

[0018] Figure 1 is a block diagram of a portable distribution network intelligent gateway operation and maintenance device shown according to an exemplary embodiment.

[0019] Figure 2 is a schematic diagram of a hierarchical data processing link shown according to an exemplary embodiment.

[0020] Figure 3It is a schematic diagram of model training shown according to an exemplary embodiment.

[0021] Figure 4 It is a block diagram of another portable power distribution intelligent gateway operation and maintenance device shown according to an exemplary embodiment.

[0022] Figure 5 It is a flowchart of a power distribution intelligent gateway operation and maintenance method shown according to an exemplary embodiment.

[0023] Figure 6 It is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0024] The following will describe the detailed implementation manners of the present disclosure with reference to the accompanying drawings. It should be understood that the detailed implementation manners described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0025] The distribution network refers to the power network that receives electric energy from the transmission network or regional power plant and distributes it locally through distribution facilities or by voltage levels to various users. It is composed of overhead lines, cables, poles, distribution transformers, disconnect switches, reactive power compensators, and some auxiliary facilities, etc., and is a network that plays an important role in distributing electric energy in the power network.

[0026] In order to ensure the reliability, safety, and stability of the distribution network operation, it is necessary to monitor the operation status of the distribution network for faults.

[0027] The intelligent gateway also plays an important role in the remote operation and maintenance of the distribution network. It can collect data such as the operation status, workload, and fault information of the distribution network in real time, and transmit the data to the cloud platform or local control system through the Internet or local area network to realize functions such as remote fault diagnosis and elimination, remote control and adjustment, and real-time monitoring and alarm.

[0028] Currently, in the operation and maintenance scenario of the distribution network, the intelligent gateway is usually used to monitor the faults of the distribution network. In this fault monitoring method, all data processing functions are integrated on the intelligent gateway, which makes the pressure on the intelligent gateway relatively large, and thus it is also impossible to provide a portable power distribution intelligent gateway.

[0029] Based on this, the embodiments of the present disclosure provide a portable power distribution intelligent gateway operation and maintenance device with low-voltage fault location and active emergency repair functions. This device classifies the fault monitoring function of the distribution network, and different hardware units perform different data processing operations. On the basis of realizing the low-voltage fault location and active emergency repair functions, the portability of the device can also be realized.

[0030] Figure 1It is a block diagram of a portable power distribution intelligent gateway operation and maintenance device shown according to an exemplary embodiment. As Figure 1 shown, the device includes: an intelligent gateway unit, a fault location unit, and a rush repair decision-making unit.

[0031] In some embodiments, the device may include a device body, and the intelligent gateway unit, the fault location unit, and the rush repair decision-making unit may be arranged inside the device body.

[0032] In some embodiments, the implementation manner of the device body, such as parameters like shape, weight, size, and material, etc., can be configured in combination with the requirements for portable devices in different application scenarios, which will not be limited herein. For example, if the requirement for the portable device is lightness, materials with relatively small weight can be adopted as much as possible.

[0033] In some embodiments, the device may further include: a communication unit, and the communication unit includes an external communication unit and an internal communication unit. Among them, the external communication unit may be an Internet of Things communication unit, which can realize the communication connection between any one of the intelligent gateway unit, the fault location unit, and the rush repair decision-making unit and the outside, and the internal communication unit may be a communication bus, which can realize the communication between the intelligent gateway unit, the fault location unit, and the rush repair decision-making unit with each other.

[0034] In some embodiments, the intelligent gateway unit can establish a communication connection with the power distribution network to obtain power distribution network data from the power distribution network. Regarding the Internet of Things communication method between the intelligent gateway and the power distribution network, the mature technologies in the art can be referred to.

[0035] Figure 2 It is a schematic diagram of a hierarchical data processing link shown according to an exemplary embodiment. As Figure 2 shown, the intelligent gateway unit, as a primary operation and maintenance unit, directly communicates with the power distribution network to obtain power distribution network data, and then determines the low-voltage fault type and fault data based on the power distribution network data. The fault location unit, as a secondary operation and maintenance unit, communicates with the intelligent gateway unit to obtain the low-voltage fault type and fault data, and then determines the low-voltage fault location result according to the low-voltage fault type and fault data. The rush repair decision-making unit, as a tertiary operation and maintenance unit, can communicate with the intelligent gateway unit and the fault location unit respectively to obtain the low-voltage fault location result and the low-voltage fault type, so as to determine the active rush repair strategy and execute the active rush repair strategy.

[0036] In some embodiments, when the rush repair decision-making unit executes the active rush repair strategy, it can also communicate with an external terminal, which will be specifically introduced in subsequent embodiments.

[0037] Regarding the intelligent gateway unit, it is configured to obtain distribution network data and determine the low-voltage fault type and fault data according to the distribution network data. The low-voltage fault type is used to characterize the cause of the low-voltage fault in the distribution network.

[0038] Regarding the fault location unit, it is configured to determine the low-voltage fault location result according to the low-voltage fault type and fault data. The low-voltage fault location result is used to characterize the location where the low-voltage fault in the distribution network occurs, and the location where the low-voltage fault occurs is indicated by distribution network equipment.

[0039] Regarding the emergency repair decision-making unit, it is configured to determine an active emergency repair strategy according to the low-voltage fault location result and the low-voltage fault type, and execute the active emergency repair strategy.

[0040] Next, the detailed implementation manners corresponding to each unit will be introduced.

[0041] In some embodiments, the faults in the distribution network involve various aspects of faults. In the embodiments of the present disclosure, it mainly focuses on low-voltage faults.

[0042] Regarding low-voltage faults, it can be understood as faults that may cause low-voltage phenomena, and they can be caused by various reasons.

[0043] Therefore, the low-voltage fault type and fault data can be determined first to facilitate low-voltage fault location. Among them, the low-voltage fault type is used to characterize the cause of the low-voltage fault in the distribution network.

[0044] In some embodiments, the low-voltage fault type may include a first fault type, a second fault type, and a third fault type. Among them, the first fault type is used to characterize that the low-voltage fault in the distribution network is caused by a line fault, the second fault type is used to characterize that the low-voltage fault in the distribution network is caused by external reasons, and the third fault type is used to characterize that the low-voltage fault in the distribution network is caused by a line fault and external reasons.

[0045] Exemplarily, common low-voltage faults may involve the following situations:

[0046] Short-circuit fault: When there is a connection between two points in a circuit that should not be directly connected, resulting in a sharp increase in current, this may cause the protection device to trip and cause a power supply interruption.

[0047] Poor contact: Due to the looseness, corrosion, or oxidation of the line connection point, the current transmission is blocked, which may cause a voltage drop, line heating, or equipment damage.

[0048] Line break: The low-voltage line is disconnected at a certain position, which may be caused by external force, aging, or material quality problems, resulting in a power supply interruption or a power outage in a local area.

[0049] Insulation fault: The insulation layer of the low-voltage line is cracked or damaged, resulting in current leakage, which may cause equipment failure or even fire.

[0050] Overload fault: The load current in the circuit exceeds the carrying capacity of the wire, causing the line to heat up, which may damage the wire and connected equipment.

[0051] Open-phase fault: In a three-phase power supply system, one of the phase lines is disconnected, resulting in unbalanced power supply, which may affect the operation of equipment such as motors.

[0052] Leakage fault: The line insulator is weathered or aged, resulting in current leakage, increasing the risk of electric shock and electrical fire.

[0053] Ground fault: The wire is damaged, and the ground wire fails to effectively insulate the wire from the ground, which may lead to a ground fault in the distribution line.

[0054] In the above example, short-circuit faults, overload faults, and open-phase faults can belong to the first fault type. Insulation faults and leakage faults can belong to the second fault type. Line breaks can belong to the third fault type.

[0055] It can be understood that the specific fault causes may not be limited to the above fault causes, and the above fault causes are only used as an example.

[0056] Furthermore, different low-voltage fault types may involve different fault data. Therefore, when the low-voltage fault type is the first fault type, the fault data includes line data; when the low-voltage fault type is the second fault type, the fault data includes external environment impact data; when the low-voltage fault type is the third fault type, the fault data includes line data, external environment impact data, the corresponding impact weights of line data, and the corresponding impact weights of external environment impact data.

[0057] In some embodiments, the line data may be current data, and the external environment impact temperature data may include: data such as temperature, humidity, wind force level, and weather conditions. The corresponding impact weight of the line data can represent the degree of influence of the line data on the fault, and the corresponding impact weight of the external environment impact data can represent the degree of influence of the external environment impact data on the fault. The higher the impact weight, the greater the influence on the fault.

[0058] Furthermore, in the distribution network data, it also includes: line data and external environment impact data. Based on the distribution network data, the low-voltage fault type and fault data can be determined.

[0059] In some embodiments, regarding the acquisition method of distribution network data, mature technologies in the art can be referred to. For example, for current, monitoring can be achieved through current monitoring sensors, and for data such as temperature, humidity, wind force level, and weather conditions, monitoring can be achieved by environmental monitoring sensors, etc.

[0060] As an alternative implementation, the determination of low-voltage fault types and fault data includes: comparing the line data with the first preset abnormal line data; if the line data matches the first preset abnormal line data, determining that the low-voltage fault type is the first fault type and determining the line data as the fault data; if the line data does not match the first preset abnormal line data, comparing the line data with the second preset abnormal line data and determining the low-voltage fault type and fault data according to the comparison result.

[0061] In this implementation, the intelligent gateway can first determine whether there is a low-voltage fault according to a general fault discrimination method, and on the basis of determining that there is a low-voltage fault, further screen out the fault data.

[0062] In some embodiments, the first preset abnormal line data can be data determined through actual measurement, which is used to determine whether there is a low-voltage fault and whether there is a low-voltage fault caused by a single line reason. Therefore, the first preset abnormal line data can be determined by measuring the line data when a low-voltage fault occurs due to a single line reason.

[0063] In some embodiments, the second preset abnormal line data can be data determined through actual measurement, which is used to determine whether there is a low-voltage fault and whether there is a low-voltage fault caused by non-single line reasons. Therefore, the second preset abnormal line data can be determined by measuring the line data when a low-voltage fault occurs due to non-single line reasons.

[0064] Among them, the first preset abnormal line data and the second preset abnormal line data can be, for example, an abnormal current value range.

[0065] Thus, first compare the line data with the first preset abnormal line data. If the line data matches the first preset abnormal line data, for example, the current is within the corresponding abnormal current value range, then it can be directly determined that the low-voltage fault type is the first fault type, and the line data can be directly determined as the fault data.

[0066] If the line data does not match the first preset abnormal line data, for example, the current is not within the corresponding abnormal current value range, then it can be further compared with the second preset abnormal line data, and the low-voltage fault type and fault data can be determined according to the comparison result.

[0067] In some embodiments, if the line data matches the second preset abnormal line data, the low-voltage fault type is determined to be the third fault type, the line data and the external environment impact data are determined as fault data, and according to the degree of mismatch between the line data and the first preset abnormal line data and the degree of match between the line data and the second preset abnormal line data, the corresponding impact weight of the line data and the corresponding impact weight of the external environment impact data are determined.

[0068] In some embodiments, if the line data matches the second preset abnormal line data, the third fault type can be directly determined as the low-voltage fault type, that is, the low-voltage fault is caused by the line and the external environment impact.

[0069] Furthermore, it is also possible to determine the corresponding impact weight of the line data and the corresponding impact weight of the external environment impact data according to the degree of mismatch between the line data and the first preset abnormal line data and the degree of match between the line data and the second preset abnormal line data.

[0070] In some embodiments, the degree of mismatch between the line data and the first preset abnormal line data can be determined according to the difference between the line data and the threshold of the first preset abnormal line data. For example, it is the ratio of the difference to the threshold. The degree of match between the line data and the second preset abnormal line data can be determined according to the difference between the line data and the threshold of the second preset abnormal line data. For example, it is the ratio of the difference to the threshold. Among them, the selection rules of the thresholds need to be consistent. For example, both the minimum value or both the maximum value are selected.

[0071] In some embodiments, the degree of mismatch between the line data and the first preset abnormal line data can represent the corresponding impact weight of the external environment impact data. The greater this degree of mismatch, the higher the corresponding impact weight of the external environment impact data. The degree of match between the line data and the second preset abnormal line data can represent the corresponding impact weight of the line data. The greater this degree of match, the higher the corresponding impact weight of the line data.

[0072] Therefore, based on the above relationships, and on the premise that the sum of the corresponding impact weight of the line data and the corresponding impact weight of the external environment impact data is 1, the corresponding impact weight of the line data and the corresponding impact weight of the external environment impact data can be determined respectively.

[0073] In some other embodiments, it is also possible to compare the two degrees of match. If the proximity of the two degrees of match is relatively high, then the corresponding impact weight of the line data is higher and the corresponding impact weight of the external environment impact data is smaller.

[0074] In practical applications, different methods for determining the impact weight can be selected according to different application scenarios, which are not limited herein.

[0075] Further, if the line data does not match the second preset abnormal line data, the external environment impact data is compared with the preset abnormal external environment impact data. Among them, the preset method of the preset abnormal external environment impact data can refer to the implementation method of the first preset abnormal line data and the second preset abnormal line data, that is, by measuring the external environment impact data in the case of a low-voltage fault caused by the external environment, the preset abnormal external environment impact data is determined.

[0076] Combined with the foregoing embodiments, the external environment impact data may involve abnormal value ranges in different aspects such as temperature, humidity, wind force level, and weather conditions.

[0077] Furthermore, when determining whether the external environment impact data matches the preset abnormal external environment impact data, the comparison can be made based on the data in different aspects respectively, and then multiple comparison results are integrated to determine whether there is a match. For example, if there is at least one piece of data that meets the abnormal value range, it is regarded as a match.

[0078] Furthermore, in the case where the external environment impact data matches the preset abnormal external environment impact data, the low-voltage fault type can be determined as the second fault type, and the external environment impact data is directly determined as the fault data.

[0079] Further, the fault location unit can perform low-voltage fault location based on the low-voltage fault type and the fault data.

[0080] As an alternative implementation, the process of low-voltage fault location includes: extracting fault features from the fault data according to the low-voltage fault type, where the low-voltage fault type is used to indicate the extraction method of the fault features; determining the low-voltage fault location result according to the fault features and the pre-trained low-voltage fault location model.

[0081] In this implementation, the fault features can be extracted based on the fault data first, and then the pre-trained low-voltage fault location model is used to determine the low-voltage fault location result according to the fault features.

[0082] In some embodiments, the low-voltage fault type can also be used to indicate the extraction method of the fault features, that is, for different low-voltage fault types, the fault feature extraction methods are different.

[0083] In some embodiments, if the low-voltage fault type is the first fault type, the abnormal line data and the line data related to the abnormal line data are extracted from the line data as the fault features.

[0084] In this embodiment, for the low-voltage fault types caused by a single line reason, abnormal line data and line data related to the abnormal line data are extracted. Among them, the abnormal line data can be data with a low frequency, or peak data, peak-valley data, etc. The related line data can be data near the abnormal line data (with similar acquisition times).

[0085] In some embodiments, the fault characteristics can be represented in vector form. For example, the abnormal line data is arranged in chronological order to obtain a fault characteristic vector with time series.

[0086] In some embodiments, if the low-voltage fault type is the second fault type, abnormal environmental impact data is extracted from the external environmental impact data as the fault characteristic.

[0087] In this embodiment, for a single external reason, abnormal environmental impact data is extracted as the fault characteristic. Among them, the abnormal environmental impact data can be data with a low frequency, or peak data, peak-valley data, etc.

[0088] In some embodiments, if the low-voltage fault type is the third fault type, abnormal line data and line data related to the abnormal line data are extracted from the line data as the first fault characteristic, and abnormal environmental impact data is extracted from the external environmental impact data as the second fault characteristic. According to the corresponding influence weights of the line data and the external environmental impact data, the first fault characteristic and the second fault characteristic are combined to obtain the final fault characteristic.

[0089] In this embodiment, for the case affected by two reasons, the first fault characteristic and the second fault characteristic can be extracted respectively, and then the final fault characteristic is obtained through characteristic combination according to the influence weights.

[0090] In some embodiments, based on the first fault characteristic, a first feature vector can be generated, and based on the second fault characteristic, a second feature vector can be generated. Then, according to the corresponding influence weight of the line data, the transformation strategy of the first feature vector is determined, and according to the corresponding influence weight of the external environmental impact data, the transformation strategy of the second feature vector is determined. Then, the first feature vector and the second feature vector are respectively transformed according to the corresponding transformation strategies, and the two transformed feature vectors are combined to obtain the final feature vector, which represents the final fault characteristic.

[0091] Among them, the influence weight can determine whether the eigenvector adopts an incremental transformation or a decremental transformation. For example, if the influence weight is greater than 0.5, a decremental transformation is adopted, and the degree of the decremental transformation is determined according to the difference from 0.5. The greater the difference, the higher the degree of the decremental transformation. If the influence weight is less than 0.5, an incremental transformation is adopted, and the degree of the incremental transformation is determined according to the difference from 0.5. The greater the difference, the higher the degree of the incremental transformation.

[0092] In some embodiments, the low-voltage fault location model is a pre-trained model, which can be a neural network model, a large model, etc., and is not limited herein.

[0093] As an alternative implementation, the training of the model includes: obtaining a training data set, which includes a plurality of first training samples and a plurality of second training samples. Each first training sample includes a first sample fault feature and a first sample label, and each second training sample includes a second sample fault feature and a second sample label. The first sample fault feature is a fault feature extracted based on line data, and the second sample feature is a fault feature extracted based on external environment influence data. The first sample label and the second sample label respectively indicate the low-voltage fault generation location through the distribution network device identifier; according to the training data set, training the to-be-trained low-voltage fault location model to obtain a pre-trained low-voltage fault model.

[0094] In this implementation, the corresponding fault data under a single fault cause is collected, sorted into fault features, and the distribution network device identifier is configured. Among them, the distribution network device identifier can represent the fault location.

[0095] In some embodiments, training the to-be-trained low-voltage fault location model according to the training data set to obtain a pre-trained low-voltage fault model may include: initially training the to-be-trained low-voltage fault location model according to a plurality of first training samples to obtain an initially trained low-voltage fault location model; secondarily training the initially trained low-voltage fault location model according to a plurality of second training samples to obtain a secondarily trained low-voltage fault location model; obtaining third training samples and test samples according to a plurality of first training samples and a plurality of second training samples; tertially training the secondarily trained low-voltage fault location model according to the third training samples to obtain a tertially trained low-voltage fault location model; and optimizing and training the tertially trained low-voltage fault location model according to the test samples to obtain a pre-trained low-voltage fault location model.

[0096] In this implementation, two types of training samples are respectively used for training, and then, the two types of training samples are integrated to obtain the finally trained samples and test samples for final training.

[0097] In some embodiments, obtaining a third training sample and a test sample based on a plurality of first training samples and a plurality of second training samples may include: randomly sampling the plurality of first training samples and the plurality of second training samples to obtain a test sample. And classifying the plurality of first training samples and the plurality of second training samples according to the same sample labels, and respectively selecting an equal or unequal number of samples from each sample label and integrating them into a third training sample.

[0098] Further, optimizing and training the low-voltage fault location model trained three times according to the test sample may include: determining the accuracy of the low-voltage fault location model according to the test sample. If the accuracy reaches the preset requirement, the training is completed. Otherwise, new training samples are selected for optimized training until the accuracy reaches the preset requirement.

[0099] Figure 3 FIG. is a schematic diagram of a model training shown according to an exemplary embodiment. As Figure 3 shown, first, the model is trained respectively using samples corresponding to different low-voltage fault causes. Then, using the samples corresponding to different low-voltage fault causes, mixed training samples and test samples are screened out. Next, training is performed using the mixed training samples, and the model is continuously optimized based on the test samples.

[0100] Through the above embodiments, the generalization ability of the model can be improved, making it applicable to fault location in different situations.

[0101] Further, the emergency repair decision-making unit can implement an active emergency repair function, which can be configured to: determine a first active emergency repair level according to the low-voltage fault type; determine a second active emergency repair level according to the distribution network equipment indicated by the low-voltage fault location result; and determine an active emergency repair strategy according to the first active emergency repair level, the second active emergency repair level and a preset corresponding relationship, where the preset corresponding relationship includes: a plurality of preset emergency repair levels and the emergency repair strategies respectively corresponding to the plurality of preset emergency repair levels, and the emergency repair strategies include emergency repair personnel information, emergency repair response time and emergency repair reference information.

[0102] In some embodiments, the active emergency repair level may include three levels: low, medium and high.

[0103] In some embodiments, the active emergency repair level of the first fault type is in the middle, the active emergency repair level of the second fault type is the lowest, and the active emergency repair level of the third fault type is the highest.

[0104] In some embodiments, the active emergency repair levels corresponding to different distribution network equipment can be pre-configured. Generally speaking, the higher the importance of the distribution network equipment, the higher the active emergency repair level. Furthermore, based on the current distribution network equipment identifier, the corresponding active emergency repair level can be determined.

[0105] Exemplarily, the active emergency repair level of the central type of distribution network equipment is higher than that of the edge type of distribution network equipment.

[0106] In some embodiments, the emergency repair reference information may be some information used to assist in emergency repair, such as: line verification methods, accessories required for line emergency repair, and other information.

[0107] In some embodiments, the higher active emergency repair level between the first active emergency repair level and the second active emergency repair level is determined as the final active emergency repair level. Then, through a preset corresponding relationship, the emergency repair strategy corresponding to the final active emergency repair level is determined.

[0108] In some embodiments, for different emergency repair levels, the complexity, professionalism, etc. of the corresponding emergency repair strategies are different. Exemplarily, for a low active emergency repair level, the professionalism of the emergency repair personnel is average, the emergency repair response time may be long, and there is more emergency repair reference information to assist the emergency repair personnel in emergency repair. For a high active emergency repair level, the professionalism of the emergency repair personnel is high, the emergency repair response time may be short, and there is less emergency repair reference information to moderately assist the emergency repair personnel in emergency repair.

[0109] In some embodiments, the preset corresponding relationship can be configured according to the historical emergency repair data, and it can be correspondingly updated as the emergency repair record data is updated.

[0110] Furthermore, after determining the active emergency repair strategy, the active emergency repair strategy can be fed back to the corresponding emergency repair personnel so that the emergency repair personnel can perform active emergency repair.

[0111] Figure 4 is a block diagram of another portable distribution intelligent gateway operation and maintenance device shown according to an exemplary embodiment. On the basis of Figure 4 shown, the device further includes: a visualization front end.

[0112] The visualization front end is respectively connected to the intelligent gateway unit, the fault location unit, and the emergency repair decision-making unit. It can be a visualization device integrated on the device or a remote visualization device, such as: a mobile device, which is not limited herein.

[0113] Furthermore, the visualization front end is configured to visually display the distribution network data, the low-voltage fault location result, and the emergency repair strategy.

[0114] It can be understood that the visualization front end can display any one of the distribution network data, the low-voltage fault location result, and the emergency repair strategy according to the visualization display requirements.

[0115] Thus, the device also has a visualization display function to facilitate understanding of the operation and maintenance data of the distribution network.

[0116] Through the above technical solutions, the intelligent gateway unit is equivalent to a first-level operation and maintenance unit, which can preliminarily determine the low-voltage fault type and fault data; the fault location unit is equivalent to a second-level operation and maintenance unit, which can perform low-voltage fault location; the emergency repair decision-making unit is equivalent to a third-level operation and maintenance unit, which can formulate an active emergency repair strategy. Thus, through hierarchical distribution network monitoring, the device has the functions of low-voltage fault location and active emergency repair. Moreover, since the three units are respectively used to implement different functions, it can be regarded as an integrated portable distribution intelligent gateway operation and maintenance device. Therefore, the portable distribution intelligent gateway operation and maintenance device can achieve accurate low-voltage fault location and formulate a reasonable active emergency repair strategy, thereby improving the reliability, stability and safety of the distribution network.

[0117] Figure 5 is a flowchart of a method for operating and maintaining a distribution intelligent gateway according to an exemplary embodiment, as Figure 5 shown, the method includes the following steps:

[0118] Step S51, obtain distribution network data, and determine the low-voltage fault type and fault data according to the distribution network data, where the low-voltage fault type is used to characterize the cause of the low-voltage fault in the distribution network.

[0119] Step S52, determine the low-voltage fault location result according to the low-voltage fault type and the fault data, where the low-voltage fault location result is used to characterize the location where the low-voltage fault in the distribution network occurs, and the location where the low-voltage fault occurs is indicated by distribution network equipment.

[0120] Step S53, determine an active emergency repair strategy according to the low-voltage fault location result and the low-voltage fault type, and execute the active emergency repair strategy.

[0121] It can be understood that this method can be understood as a method executed by taking the portable distribution intelligent gateway operation and maintenance device as a whole.

[0122] Of course, this method can also be applied to other devices, such as distribution network monitoring devices, which are not limited herein.

[0123] Figure 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. As Figure 6 shown, the electronic device 600 may include: a processor 601, a memory 602. The electronic device 600 may further include one or more of a multimedia component 603, an input / output (I / O) interface 604, and a communication component 605.

[0124] Among them, the processor 601 is used to control the overall operation of the electronic device 600 to complete all or part of the steps in the above-mentioned power distribution intelligent gateway operation and maintenance method. The memory 602 is used to store various types of data to support the operation of the electronic device 600. These data may include, for example, instructions for any application or method operating on the electronic device 600, as well as application-related data, such as contact data, received and sent messages, pictures, audio, video, and so on. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc. The multimedia component 603 may include a screen and an audio component. Among them, the screen can be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals. The received audio signals can be further stored in the memory 602 or sent through the communication component 605. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 604 provides an interface between the processor 601 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 605 is used for wired or wireless communication between the electronic device 600 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them. Therefore, the corresponding communication component 605 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0125] In one exemplary embodiment, the electronic device 600 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above XXXX method.

[0126] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When the program instructions are executed by a processor, the steps of the above power distribution intelligent gateway operation and maintenance method are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 602 including program instructions, and the above program instructions may be executed by the processor 601 of the electronic device 600 to complete the above power distribution intelligent gateway operation and maintenance method.

[0127] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a processor. When the computer program is executed by the processor, the steps of the above power distribution intelligent gateway operation and maintenance method are implemented.

[0128] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0129] In addition, it should be noted that, in the above specific embodiments, the various specific technical features described can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure will not separately describe various possible combination methods.

[0130] In addition, any combination can be made between various different embodiments of the present disclosure as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

Claims

1. A portable power distribution intelligent gateway operation and maintenance device with low-voltage fault location and active repair functions, characterized in that: include: An intelligent gateway unit is connected to the distribution network and is configured to obtain distribution network data and determine a low voltage fault type and fault data according to the distribution network data, wherein the low voltage fault type is used to characterize a cause of a low voltage fault in the distribution network; A fault location unit connected to the intelligent gateway unit and configured to determine a low-voltage fault location result according to the low-voltage fault type and the fault data, wherein the low-voltage fault location result is used to characterize a location where a low-voltage fault occurs in the distribution network, and the location where the low-voltage fault occurs is indicated by a distribution network device; A repair decision unit, connected to the intelligent gateway unit and the fault location unit respectively, configured to determine an active repair strategy according to the low voltage fault location result and the low voltage fault type, and execute the active repair strategy; The low voltage fault type includes: a first fault type, which is used to characterize that a low voltage fault is caused by a line fault in the distribution network; the distribution network data includes: line data and external environment impact data; and the intelligent gateway unit is further configured as follows: Comparing the line data with first preset abnormal line data, the first preset abnormal line data is used to determine whether there is a low voltage fault caused by a single line; If the line data matches the first preset abnormal line data, the low voltage fault type is determined to be the first fault type, and the line data is determined to be the fault data; If the line data does not match the first preset abnormal line data, the line data is compared with the second preset abnormal line data, and the low voltage fault type and fault data are determined based on the comparison result. The second preset abnormal line data is used to determine whether there is a low voltage fault caused by non-single line reasons.

2. The portable power distribution intelligent gateway operation and maintenance device according to claim 1 is characterized in that: The low voltage fault type also includes: a second fault type and a third fault type, wherein the second fault type is used to characterize that the distribution network has a low voltage fault due to external reasons, and the third fault type is used to characterize that the distribution network has a low voltage fault due to line faults and external reasons; Correspondingly, when the low-voltage fault type is the first fault type, the fault data includes line data; when the low-voltage fault type is the second fault type, the fault data includes external environment impact data; when the low-voltage fault type is the third fault type, the fault data includes line data, external environment impact data, the corresponding impact weight of the line data and the corresponding impact weight of the external environment impact data.

3. The portable power distribution intelligent gateway operation and maintenance device according to claim 2 is characterized in that: The intelligent gateway unit is further configured as: If the line data matches the second preset abnormal line data, the low voltage fault type is determined to be the third fault type, the line data and the external environment impact data are determined to be the fault data, and the corresponding impact weight of the line data and the corresponding impact weight of the external environment impact data are determined according to the mismatch between the line data and the first preset abnormal line data and the match between the line data and the second preset abnormal line data; If the line data does not match the second preset abnormal line data, comparing the external environment impact data with the preset abnormal external environment impact data; If the external environment impact data matches the preset abnormal external environment impact data, the low voltage fault type is determined to be the second fault type, and the external environment impact data is determined to be the fault data.

4. The portable power distribution intelligent gateway operation and maintenance device according to claim 2, characterized in that: The fault location unit is further configured to: Extracting a fault feature from the fault data according to the low voltage fault type, wherein the low voltage fault type is used to indicate a method for extracting the fault feature; A low voltage fault location result is determined according to the fault characteristics and a pre-trained low voltage fault location model.

5. The portable power distribution intelligent gateway operation and maintenance device according to claim 4 is characterized in that: The fault location unit is further configured to: If the low voltage fault type is the first fault type, extracting abnormal line data and line data related to the abnormal line data from the line data as the fault feature; If the low voltage fault type is the second fault type, extracting abnormal environment impact data from the external environment impact data as the fault feature; If the low-voltage fault type is the third fault type, abnormal line data and line data related to the abnormal line data are extracted from the line data as the first fault feature, and abnormal environmental impact data is extracted from the external environmental impact data as the second fault feature. According to the corresponding impact weight of the line data and the corresponding impact weight of the external environmental impact data, the first fault feature and the second fault feature are combined to obtain the final fault feature.

6. The portable power distribution intelligent gateway operation and maintenance device according to claim 4, characterized in that: The fault location unit is further configured to: Acquire a training data set, the training data set comprising a plurality of first training samples and a plurality of second training samples, each first training sample comprising a first sample fault feature and a first sample label, each second training sample comprising a second sample fault feature and a second sample label, the first sample fault feature being a fault feature extracted based on line data, the second sample feature being a fault feature extracted based on external environment impact data, the first sample label and the second sample label respectively indicating a location where a low voltage fault occurs through a distribution network equipment identifier; The low-voltage fault location model to be trained is trained according to the training data set to obtain the pre-trained low-voltage fault model.

7. The portable power distribution intelligent gateway operation and maintenance device according to claim 6, characterized in that: The fault location unit is further configured to: Performing initial training on the low-voltage fault location model to be trained according to the multiple first training samples to obtain an initially trained low-voltage fault location model; According to the plurality of second training samples, performing secondary training on the initially trained low-voltage fault location model to obtain a secondary trained low-voltage fault location model; Obtaining a third training sample and a test sample according to the plurality of first training samples and the plurality of second training samples; According to the third training sample, the low-voltage fault location model trained twice is trained three times to obtain a low-voltage fault location model trained three times; According to the test samples, the three trained low-voltage fault location models are optimized and trained to obtain the pre-trained low-voltage fault location model.

8. The portable power distribution intelligent gateway operation and maintenance device according to claim 1, characterized in that: The emergency repair decision unit is further configured to: Determining a first proactive emergency repair level according to the low voltage fault type; Determining a second active emergency repair level according to the distribution network equipment indicated by the low-voltage fault locating result; An active emergency repair strategy is determined according to the first active emergency repair level, the second active emergency repair level and a preset correspondence, wherein the preset correspondence includes: multiple preset emergency repair levels and emergency repair strategies corresponding to the multiple preset emergency repair levels, and the emergency repair strategy includes emergency repair personnel information, emergency repair response time and emergency repair reference information.

9. The portable power distribution intelligent gateway operation and maintenance device according to claim 1, characterized in that: The portable power distribution intelligent gateway operation and maintenance device also includes: A visualization front end, wherein the visualization front end is connected to the intelligent gateway unit, the fault location unit and the emergency repair decision unit respectively, and the visualization front end is configured to visualize the distribution network data, the low-voltage fault location result and the emergency repair strategy.

Images