Power distribution network fault location and restoration system, electronic device, and computer readable medium

Abstract

This disclosure discloses a power distribution network fault location and repair system, electronic equipment, and a computer-readable medium. One specific implementation of the method includes: various intelligent terminals and a control center. Each intelligent terminal is configured to: collect operating parameters of the power distribution network based on a preset time interval; perform wavelet transform on the operating parameters to obtain wavelet transform features; perform fault detection on the wavelet transform features to obtain fault detection results; and transmit the operating parameters, wavelet transform features, and fault detection results to the control center based on the fault detection results. The control center is configured to: determine fault location information in response to determining that a fault state corresponding to a fault detection result exists among the received fault detection results; and send a fault isolation command to the intelligent terminal corresponding to the fault location information. This implementation can reduce the downtime of faulty circuit systems.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of power system technology, and more specifically to distribution network fault location and repair systems, electronic devices, and computer-readable media. Background Technology

[0002] With the application of distributed generation in distribution networks, the multi-source and multi-type power supply characteristics have changed the current distribution logic of traditional power grids. This diversity of power sources makes fault analysis in distribution networks more difficult. Currently, the common approach for fault location and repair operations in distribution networks is to implement zoned management to locate fault sections. For example, directional longitudinal protection is used in the upstream section of the distribution network, while time-limited overcurrent protection is used in the downstream section.

[0003] However, when using the above method, a common technical problem is that the fault current of inverter distributed power sources is different from that of traditional grid power sources. The short-circuit current is irregular, which leads to a decrease in the accuracy of fault detection. As a result, it is difficult to locate and isolate the fault in a timely manner based on the fault current, thus prolonging the shutdown time of the circuit system.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide a power distribution network fault location and repair system, electronic equipment, and computer-readable medium to address the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a power distribution network fault location and repair system, comprising: various intelligent terminals and a control center. Each of the aforementioned intelligent terminals is configured to: collect operating parameters of the power distribution network based on a preset time interval, wherein the operating parameters include voltage and current; perform wavelet transform on the operating parameters to obtain wavelet transform features; perform fault detection on the wavelet transform features to obtain fault detection results; and transmit the operating parameters, the wavelet transform features, and the fault detection results to the control center based on the fault detection results. The control center is configured to: determine fault location information in response to determining that a fault state corresponding to a fault detection result exists among the received fault detection results; and send a fault isolation command to the intelligent terminal corresponding to the fault location information.

[0008] Secondly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the system described in any implementation of the first aspect above.

[0009] Thirdly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the system described in any of the implementations of the first aspect above.

[0010] The above-described embodiments of this disclosure have the following beneficial effects: the distribution network fault location and repair system of some embodiments of this disclosure can improve the accuracy of fault detection and reduce the downtime of the circuit system. Specifically, the reason why the segmentation results of the relevant segmentation model are not accurate enough is that the fault current of the inverter distributed power source is different from that of the traditional grid power source, and the short-circuit current is irregular. Based on this, in the distribution network fault location and repair system of some embodiments of this disclosure, each intelligent terminal is configured to: first, collect the operating parameters of the distribution network based on a preset time interval. The operating parameters include voltage and current. Since each intelligent terminal is distributed at a key node of the distribution network, the state of the grid can be continuously monitored by collecting the operating parameters of the distribution network. Next, wavelet transform is performed on the operating parameters to obtain wavelet transform features. Thus, key features in the signal can be effectively extracted, and transient changes in the short term can be captured, thereby improving the sensitivity and accuracy of fault detection. Second, fault detection is performed on the wavelet transform features to obtain fault detection results. By performing fault detection on the wavelet transform features, faults existing in the grid can be identified more quickly and accurately. Subsequently, based on the aforementioned fault detection results, the aforementioned operating parameters, wavelet transform features, and fault detection results are transmitted to the aforementioned control center. The control center is configured to determine the fault location information in response to the determination that a fault state corresponding to a fault detection result exists among the received fault detection results. Automated fault location helps to quickly and accurately pinpoint the fault area, thereby reducing the search time for maintenance personnel. Finally, a fault isolation command is sent to the intelligent terminal corresponding to the aforementioned fault location information. This allows for the rapid disconnection of the fault area from the normal operating area, minimizing the overall impact on the power system and significantly reducing system downtime. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1 These are schematic diagrams of some embodiments of the power distribution network fault location and repair system disclosed herein;

[0013] Figure 2 These are timing diagrams of some embodiments of the power distribution network fault location and repair system disclosed herein;

[0014] Figure 3 These are schematic diagrams of distribution networks for some embodiments of the distribution network fault location and repair system disclosed herein;

[0015] Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0018] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0019] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0020] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0021] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] Figure 1 A schematic diagram of the structure of some embodiments of the power distribution network fault location and repair system according to the present disclosure is shown. Figure 1The system includes various intelligent terminals 1 and a control center 2. Each intelligent terminal can be a Smart Terminal Unit (STU). Each intelligent terminal can include components such as sensors and microprocessors. The sensors may include, but are not limited to, voltage sensors, current sensors, and zero-sequence current transformers. Each intelligent terminal can be deployed at key nodes in the distribution network. These key nodes can be distributed generation grid connection points, feeder heads, sectionalizing switches, etc. The control center can be a distribution automation master station. Each intelligent terminal can communicate with the control center. The intelligent terminals can also communicate with each other. Some timing diagrams of the distribution network fault location and repair system disclosed herein are as follows: Figure 2 As shown.

[0023] In some embodiments, each of the smart terminals 1 described above can be configured as follows:

[0024] First, the operating parameters of the power distribution network are collected based on preset time intervals.

[0025] In some embodiments, the aforementioned smart terminal can collect operating parameters of the distribution network based on a preset time interval. The value of the aforementioned time interval is not specifically limited here. For example, the time interval can be 1 second. The aforementioned distribution network can be a network supplying power to a load area. The aforementioned distribution network may include, but is not limited to, at least one of the following: main substations, switches, smart terminals, circuit breakers, etc. A schematic diagram of the aforementioned distribution network is shown below. Figure 3 As shown. Figure 3 In this diagram, Main Transformer 1 and Main Transformer 2 represent the main substations, CB1 and CB2 represent circuit breakers, S1 to S5 represent switches, and STU0 to STU6 represent intelligent terminals. Each of these intelligent terminals can be connected via a point-to-point communication network. The operating parameters mentioned above may include, but are not limited to, voltage, current, zero-sequence voltage, and zero-sequence current. In practice, these intelligent terminals can collect operating parameters from the distribution network lines they are connected to using their equipped sensors.

[0026] Second, wavelet transform is performed on the operating parameters to obtain wavelet transform features.

[0027] In some embodiments, the aforementioned smart terminal can perform wavelet transform on the aforementioned operating parameters to obtain wavelet transform features. In practice, a preset wavelet transform algorithm can be used to perform wavelet transform on the aforementioned operating parameters to obtain wavelet transform features.

[0028] As an example, the wavelet transform algorithm mentioned above may include, but is not limited to, at least one of the following: wavelet transform algorithm, empirical wavelet transform algorithm, etc.

[0029] Third, fault detection is performed on the wavelet transform features to obtain fault detection results.

[0030] In some embodiments, the aforementioned smart terminal can perform fault detection on the aforementioned wavelet transform features to obtain fault detection results. In practice, a preset fault detection algorithm can be used to perform fault detection on the aforementioned wavelet transform features to obtain fault detection results.

[0031] As an example, the above fault detection algorithm may include, but is not limited to, at least one of the following: threshold comparison method and pattern recognition method.

[0032] In some optional implementations of certain embodiments, the intelligent terminal performs fault detection on the wavelet transform features to obtain fault detection results, which may include the following steps:

[0033] Based on a pre-defined fault detection student model, the fault detection results corresponding to the aforementioned wavelet transform features are determined. These fault detection results include: normal state, warning state, and fault state. The aforementioned fault detection student model can be a pre-trained artificial intelligence model used to obtain fault detection results based on the input wavelet transform features.

[0034] Optionally, the above-mentioned fault detection student model is trained by the following steps:

[0035] The first step involves the control center transmitting a pre-set initial fault detection model to each of the aforementioned intelligent terminals. This initial fault detection model can be a machine learning model or a neural network model. For example, it could be a support vector machine or a long short-term memory network.

[0036] The second step involves each of the aforementioned smart terminals training the received initial fault detection model using local data to obtain trained model parameters, and then transmitting these trained model parameters to the control center. Each smart terminal can collect local data, which may include a sample wavelet transform feature set. Each sample wavelet transform feature in the sample wavelet transform feature set may correspond to a sample fault label. These sample fault labels can be normal, warning, or fault labels. In practice, firstly, for each smart terminal, the sample wavelet transform feature set contained in the local data can be used as input data, and the corresponding sample fault label can be used as the desired output to train the initial fault detection model, resulting in a trained fault detection model. Secondly, the smart terminal can determine the parameters corresponding to the trained fault detection model as the trained model parameters. Finally, the smart terminal can transmit the trained model parameters to the control center.

[0037] Third, the control center performs weighted aggregation on the received trained model parameters to obtain aggregated parameters. In practice, firstly, for each of the aforementioned smart terminals, the control center can determine the weight of that smart terminal as the ratio between its local data capacity and total data capacity. The local data capacity can be the memory size occupied by the local data of the smart terminal. The smart terminal can transmit its corresponding local data capacity to the control center. The total data capacity can be the sum of the local data capacities of all smart terminals. Then, the control center can perform weighted aggregation on the received trained model parameters according to the weight of each smart terminal to obtain aggregated parameters.

[0038] Fourth, the control center obtains a fault detection teacher model based on the aggregated parameters and the initial fault detection model. The structure of the fault detection teacher model can be the same as the initial fault detection model, and the parameters of the fault detection teacher model can be the aggregated parameters.

[0039] Fifth, the control center transmits the fault detection teacher model to each of the aforementioned smart terminals.

[0040] Step 6: For each of the aforementioned smart terminals, the fault detection teacher model is trained using distillation technology to obtain the fault detection student model. In practice, for each of the aforementioned smart terminals, the fault detection teacher model can be trained using pre-set knowledge distillation techniques and the corresponding local data to obtain the fault detection student model.

[0041] Fourth, based on the fault detection results, the operating parameters, wavelet transform features, and fault detection results are transmitted to the control center.

[0042] In some embodiments, the aforementioned smart terminal may transmit the aforementioned operating parameters, the aforementioned wavelet transform features, and the aforementioned fault detection results to the aforementioned control center based on the aforementioned fault detection results.

[0043] In some optional implementations of certain embodiments, the intelligent terminal transmitting the operating parameters, wavelet transform features, and fault detection results to the control center based on the fault detection results may include the following steps:

[0044] The first step, in response to determining that the fault detection result is in a normal state, is to transmit the operating parameters, wavelet transform features, and fault detection result to the control center based on a preset normal time interval. The normal time interval can be 5 minutes.

[0045] As an example, when the above fault detection result is normal, the collected operating parameters, corresponding wavelet transform features and fault detection results will be transmitted to the above control center every 5 minutes.

[0046] The second step involves, in response to determining that the fault detection result is in an early warning state, transmitting the aforementioned operating parameters, wavelet transform features, and fault detection result to the control center based on a preset early warning time interval. The early warning time interval can be 30 seconds.

[0047] Third, in response to determining that the above fault detection result indicates a fault state, the above operating parameters, the above wavelet transform features, and the above fault detection result are transmitted to the above control center. In practice, when the above fault detection result indicates a fault state, the above operating parameters, the above wavelet transform features, and the above fault detection result are immediately transmitted to the above control center.

[0048] In some embodiments, the control center 2 described above can be configured as follows:

[0049] First, in response to determining that there is a fault state corresponding to the fault detection result among the various received fault detection results, the fault location information is determined.

[0050] In some embodiments, the control center 2 may determine the fault location information in response to determining that there is a fault state corresponding to the fault detection result among the received fault detection results.

[0051] In practice, a common technical problem in fault location is that impedance-based methods are often insufficient to pinpoint the exact location of a fault. While traveling wave-based fault location offers higher accuracy, it often requires traveling wave analysis of the entire distribution network, leading to high computational complexity and lengthy fault location time. Therefore, the following solution is proposed.

[0052] In some optional implementations of certain embodiments, the control center 2, in response to determining that there is a fault state corresponding to a fault detection result among the received fault detection results, determines the fault location information, which may include the following steps:

[0053] The first step is to determine the received operating parameters, wavelet transform features, and fault detection results from the aforementioned smart terminals as the operating parameter set, wavelet transform feature set, and fault detection result set.

[0054] The second step is to perform the following steps for each fault detection result corresponding to the fault state in the above fault detection result set:

[0055] The first sub-step involves generating the impedance value at fault time based on the operating parameters corresponding to the fault detection results. In practice, the ratio between voltage and current included in the operating parameters can be used to determine the impedance value at fault time.

[0056] The second sub-step involves generating an impedance change rate based on the aforementioned impedance value during a fault and a preset normal impedance value. The preset normal impedance value can be the impedance value of the corresponding smart terminal in its normal state. Here, each of the aforementioned smart terminals can determine the ratio between voltage and current as its normal impedance value when the fault detection result corresponds to a normal state. In practice, firstly, the difference between the aforementioned impedance value during a fault and the aforementioned normal impedance value can be determined. Then, the percentage between the aforementioned difference and the aforementioned normal impedance value can be determined as the impedance change rate.

[0057] The third step involves identifying the smart terminals corresponding to each impedance change rate greater than or equal to a preset impedance change threshold as impedance-abnormal smart terminals, thus obtaining a set of impedance-abnormal smart terminals. The impedance change threshold can be a preset percentage and is not specifically limited here. For example, the impedance change threshold could be 60%.

[0058] The fourth step involves obtaining the fault section smart terminal set based on the spatial distribution of the distribution network and the aforementioned set of impedance anomaly smart terminals. The aforementioned spatial distribution of the distribution network can be represented as a table characterizing the location of each smart terminal in the distribution network and the distribution relationships between the connecting lines. In practice, distribution network faults are regional; a fault point will cause adjacent smart terminals upstream and downstream to detect impedance anomalies, while smart terminals far from the fault point will not show significant impedance changes. As an example, based on the aforementioned spatial distribution of the distribution network, each impedance anomaly smart terminal located on the same feeder in the aforementioned set of impedance anomaly smart terminals can be identified as a fault section smart terminal, thus obtaining the fault section smart terminal set.

[0059] The fifth step involves obtaining the traveling wave features corresponding to each intelligent terminal in the aforementioned faulty segment intelligent terminal set, thus obtaining a traveling wave feature set. Each traveling wave feature in the set corresponds to a traveling wave timestamp. In practice, firstly, for each intelligent terminal in the aforementioned faulty segment intelligent terminal set, traveling wave features can be extracted from the wavelet transform features corresponding to the intelligent terminal, obtaining the traveling wave timestamp and traveling wave polarity as traveling wave features. Then, the intelligent terminal in the faulty segment can transmit these traveling wave features to the control center. Finally, the control center can determine the received traveling wave features as a traveling wave feature set.

[0060] The sixth step is to determine the spacing between every two connected smart terminals in the aforementioned faulty section smart terminal set, thus obtaining the spacing set. In practice, the spacing can be determined by the length of the line between every two connected smart terminals in the aforementioned faulty section smart terminal set, based on the spatial distribution of the distribution network described above.

[0061] Step 7: Determine the fault location information based on the aforementioned spacing set, traveling wave feature set, and preset traveling wave velocity. In practice, the fault location information can be determined based on the traveling wave ranging principle, according to the aforementioned spacing set, traveling wave feature set, and preset traveling wave velocity. The fault location information can be represented by the line segment to which the fault belongs and the distance of the fault to the nearest smart terminal on that line segment. For example, the fault location information could be: "The fault is located in section 2 of Line 1, 250m away from smart terminal 3."

[0062] Steps one through seven and related content in the above-mentioned optional solutions constitute an inventive point of this disclosure, solving the aforementioned technical problem: "long fault location time." The reason for the long fault location time is often that impedance-based methods are usually insufficient to pinpoint the specific location of the fault. While traveling wave fault location has higher accuracy, it often requires traveling wave analysis of the entire distribution network, resulting in high computational load. Solving these factors can reduce fault location time. To achieve this, firstly, the impedance of each intelligent terminal whose fault detection result indicates a fault state is determined by the voltage and current ratio. This avoids determining the impedance of all intelligent terminals in the entire distribution network, reducing computational load. Then, the impedance change rate is generated based on the impedance during the fault and the normal impedance. This eliminates the influence of impedance differences between different terminals, improving the accuracy of fault location. Next, intelligent terminals with impedance change rates greater than a preset threshold are identified as impedance-abnormal intelligent terminals. Secondly, based on the spatial distribution of the distribution network, the fault section corresponding to each impedance-abnormal intelligent terminal is determined. This allows direct identification of the faulty line section, improving the efficiency of subsequent traveling wave ranging. Then, the traveling wave characteristics corresponding to each intelligent terminal within the fault section are determined. This allows for the accurate extraction of the arrival time and propagation direction of the traveling waves, providing crucial data for subsequent ranging. Finally, based on the segment length, traveling wave characteristics, and traveling wave velocity, the fault location is determined using the traveling wave ranging principle. By determining the section through impedance and then using traveling waves to pinpoint the specific location, the computational load and time can be significantly reduced, improving fault location efficiency and shortening fault location time.

[0063] Second, send a fault isolation command to the smart terminal corresponding to the fault location information.

[0064] In some embodiments, the control center 2 can send a fault isolation command to the smart terminal corresponding to the fault location information. In practice, the control center can determine the smart terminals at both ends of the fault location information based on the spatial distribution of the power distribution network, and send a fault isolation command to each of the smart terminals at both ends.

[0065] In some embodiments, each of the smart terminals 1 described above can also be configured to:

[0066] In response to receiving a fault isolation command from the control center, the corresponding switch is disconnected. The aforementioned smart terminal can control the corresponding switch to close or open.

[0067] Optionally, the control center 2 may also adjust the capacitor banks in the distribution network according to the received operating parameters in response to determining that there is a fault detection result corresponding to an early warning state among the received fault detection results.

[0068] In practice, when the control center determines that none of the received fault detection results correspond to a fault state, and that some fault detection results correspond to a warning state, adjustments can be made to the capacitor banks in the distribution network. This can compensate for reactive power and stabilize the voltage in the distribution network.

[0069] In practice, a common technical challenge in fault restoration is the lengthy power supply recovery time due to the complexity of power flow calculations in distribution networks and the time-consuming manual analysis of feeder load conditions. Therefore, the following solution is proposed.

[0070] In some embodiments, each of the aforementioned smart terminals 1 can also be configured to repair the power distribution network, which may include the following steps:

[0071] The first step, in response to determining that the smart terminal is the downstream smart terminal corresponding to the fault location information, is to perform the following steps:

[0072] The first sub-step involves determining the differential smart terminal set and tie switch set corresponding to the downstream smart terminal. In practice, firstly, based on the aforementioned distribution network spatial distribution, the downstream smart terminal among the smart terminals at both ends of the fault location information can be identified as the downstream smart terminal. Secondly, based on the aforementioned distribution network spatial distribution, each smart terminal located in the same differential protection area as the downstream smart terminal is identified as the differential smart terminal set. The aforementioned differential protection area can be a logical protection area formed by two or more switches equipped with smart terminals and the connecting lines between them. Here, Kirchhoff's current law can be used to determine the differential protection area corresponding to the downstream smart terminal. Afterwards, the tie switch corresponding to each of the aforementioned differential smart terminals can be determined, resulting in the tie switch set.

[0073] The second sub-step involves determining the feeders connected to the downstream intelligent terminals based on the spatial distribution of the distribution network, thus obtaining the feeder set. In practice, the feeder set can be obtained by determining the feeders connected to the downstream intelligent terminals based on the spatial distribution of the distribution network.

[0074] The third sub-step involves determining the terminal voltage of each tie switch in the tie switch set based on the operating parameters of each differential intelligent terminal in the aforementioned differential intelligent terminal set, thus obtaining the tie switch terminal voltage set; and determining the current of each feeder in the aforementioned feeder set, thus obtaining the feeder current set. In practice, for each differential intelligent terminal in the differential intelligent terminal set, firstly, the voltages included in the operating parameters collected by the differential intelligent terminal can be determined as the tie switch terminal voltages. Then, the currents included in the operating parameters can be determined as the feeder currents.

[0075] The fourth sub-step involves generating a connection switch sequence based on the order of the voltage values ​​at each connection switch terminal in the aforementioned connection switch terminal voltage set. Specifically, each connection switch in the connection switch sequence is ordered from largest to smallest according to its corresponding connection switch terminal voltage.

[0076] The fifth sub-step involves performing the following steps for each tie switch in the tie switch sequence:

[0077] Sub-step one: Based on the above distribution network spatial distribution, determine the feeders that are connected to the above tie switch in the above feeder concentration, and obtain the connected feeders.

[0078] Sub-step two: Based on the preset normal current value and the preset maximum allowable current set for substations, determine the load current change rate corresponding to the aforementioned connected feeders. The aforementioned normal current value can be the current value collected by the intelligent terminal corresponding to the aforementioned tie switch under normal conditions. Each maximum allowable current in the aforementioned maximum allowable current set for substations can correspond to one substation. The aforementioned maximum allowable current for substations can be a preset current value, without specific limitations. In practice, firstly, based on the aforementioned distribution network spatial distribution, determine the substations connected to the aforementioned connected feeders, and determine the maximum allowable current corresponding to the aforementioned substations. Then, the sum of the aforementioned normal current value and the feeder current corresponding to the aforementioned connected feeder can be determined as the variable feeder current. Next, the ratio between the aforementioned variable feeder current and the aforementioned maximum allowable current for substations can be determined as the load current change rate.

[0079] Sub-step three involves determining each load current change rate in the aforementioned load current change rate set that satisfies a preset current change condition as the initial load current change rate, thus obtaining the initial load current change rate set. The aforementioned current change condition can be that the load current change rate is less than 1.

[0080] Sub-step four: In response to determining that the load current change rate meets a preset current change condition, the aforementioned interconnecting switch is controlled to close. The aforementioned current change condition can be that the load current change rate is less than or equal to 1. In practice, when the load current change rate is less than or equal to 1, the smart terminal can control the interconnecting switch it is connected to to close.

[0081] In sub-step five, in response to the determination that the aforementioned load current change rate does not meet the preset current change condition, a centralized control command is sent to the aforementioned control center. Here, after receiving the centralized control command, the aforementioned control center can repair the fault location according to the distribution network self-healing control technology.

[0082] Steps one through five of the above-mentioned optional solutions and their related contents constitute an inventive point of this disclosure, solving the aforementioned technical problem: "long power restoration time." The long power restoration time is often caused by the complexity of power flow calculations in the distribution network and the time-consuming manual analysis of feeder load status. Solving these factors can reduce the power restoration time. To achieve this, firstly, the power outage location is determined based on the downstream intelligent terminal of the fault point, and the differential intelligent terminals within the same differential protection area are identified. This allows it to determine which terminals can participate in power restoration. Next, based on the power grid structure, all feeders connected to the aforementioned downstream intelligent terminals are identified. This allows for the preliminary determination of possible power restoration paths. Secondly, the voltage at the corresponding tie switch is determined based on the differential intelligent terminal. Power restoration paths corresponding to higher voltages are prioritized according to a voltage ranking from high to low. This allows for prioritizing closing the circuit from lines with higher voltage and more stable power supply, improving the speed and stability of circuit restoration. Finally, based on the current of the feeders connected to the tie switch, the load current change rate is generated, and it is determined whether the load current change rate meets the conditions. Therefore, by using the ratio between the load that needs to be transferred after the circuit breaker is closed and the maximum allowable current of the substation, the stability of the distribution line after the circuit breaker is closed can be ensured, secondary faults can be avoided, and the time consumption caused by manual intervention can be reduced.

[0083] The following is for reference. Figure 4 It shows a schematic diagram of the structure of an electronic device (such as a computing device) suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0084] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0085] In one embodiment, the processor is configured to run a computer program stored in a memory to perform the following steps: each of the aforementioned smart terminals is configured to: collect operating parameters of the power distribution network based on a preset time interval, wherein the operating parameters include voltage and current; perform wavelet transform on the operating parameters to obtain wavelet transform features; perform fault detection on the wavelet transform features to obtain fault detection results; and transmit the operating parameters, the wavelet transform features, and the fault detection results to the control center based on the fault detection results; the control center is configured to: determine fault location information in response to determining that there is a fault state corresponding to the fault detection results among the received fault detection results; and send a fault isolation command to the smart terminal corresponding to the fault location information.

[0086] This disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to the various embodiments of the methods described above.

[0087] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0088] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0089] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A power distribution network fault location and repair system, wherein, The power distribution network fault location and repair system includes: various intelligent terminals and a control center, characterized in that it includes: Each of the various smart terminals is configured to: Based on a preset time interval, the operating parameters of the distribution network are collected, wherein the operating parameters include voltage and current; Wavelet transform is applied to the operating parameters to obtain wavelet transform features; Fault detection is performed on the wavelet transform features to obtain fault detection results; Based on the fault detection results, the operating parameters, the wavelet transform features, and the fault detection results are transmitted to the control center. The control center is configured to: In response to determining that there is a fault state corresponding to the fault detection result among the received fault detection results, the fault location information is determined; Send a fault isolation command to the smart terminal corresponding to the fault location information.

2. The power distribution network fault location and repair system according to claim 1, characterized in that, Each of the various smart terminals is further configured to: In response to receiving a fault isolation command from the control center, the corresponding switch is disconnected.

3. The power distribution network fault location and repair system according to claim 1, characterized in that, Each of the various smart terminals is further configured to: Based on a preset fault detection student model, the fault detection results corresponding to the wavelet transform features are determined, wherein the fault detection results include: normal state, warning state, and fault state.

4. The power distribution network fault location and repair system according to claim 3, characterized in that, The fault detection student model is trained using the following steps: The control center transmits the preset initial fault detection model to each of the various intelligent terminals. For each of the aforementioned smart terminals, the smart terminal uses local data to train the received initial fault detection model, obtains the trained model parameters, and transmits the trained model parameters to the control center. The control center performs weighted aggregation on the received parameters of each trained model to obtain aggregated parameters; The control center obtains the fault detection teacher model based on the aggregated parameters and the initial fault detection model; The control center transmits the fault detection teacher model to each smart terminal; For each of the aforementioned smart terminals, the fault detection teacher model is distilled and trained through the smart terminal to obtain the fault detection student model.

5. The power distribution network fault location and repair system according to claim 1, characterized in that, Each of the various smart terminals is further configured to: In response to determining that the fault detection result is in a normal state, the operating parameters, the wavelet transform features, and the fault detection result are transmitted to the control center based on a preset normal time interval. In response to determining that the fault detection result is in an early warning state, the operating parameters, the wavelet transform features, and the fault detection result are transmitted to the control center based on a preset early warning time interval. In response to determining that the fault detection result is a fault state, the operating parameters, the wavelet transform features, and the fault detection result are transmitted to the control center.

6. The power distribution network fault location and repair system according to claim 1, characterized in that, The control center is further configured to: In response to the determination that one of the received fault detection results corresponds to a warning state, the capacitor banks in the distribution network are adjusted according to the received operating parameters.

7. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the power distribution network fault location and repair system as described in any one of claims 1 to 7.

8. A computer-readable medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, implements the power distribution network fault location and repair system as described in any one of claims 1 to 7.

Images