Power grid-based fault detection method, device, equipment and storage medium

Abstract

This application provides a power grid-based fault detection method, apparatus, device, and storage medium. Applied to current protection devices installed in power grid lines, the method includes: acquiring a first voltage and a predicted load; the first voltage characterizes the minimum voltage of the protected line during operation; the predicted load characterizes the predicted load of the line downstream of the current protection device; determining a first threshold based on a preset voltage and the first voltage; the preset voltage characterizes the rated voltage of the power grid; the first threshold characterizes a voltage criterion value for a current fault occurring in the line downstream of the current protection device; determining a second threshold based on the preset voltage and the predicted load; the second threshold characterizes a current criterion value for a current fault occurring in the line downstream of the current protection device; and determining fault information based on the first and second thresholds. This method aims to improve the accuracy of power grid fault detection.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a fault detection method, device, equipment and storage medium based on power grids. Background Technology

[0002] With the large-scale integration of distributed power sources into the power grid, fault currents in the power grid no longer follow the fault response patterns of traditional induction motors.

[0003] In related technologies, a current fault is determined by comparing the fault current to a fixed threshold. However, using a fixed threshold cannot accommodate the randomness and volatility introduced by distributed generation. For example, when the fault current is close to the grid's load current, misjudgments are prone to occur, resulting in low accuracy in grid fault detection. Therefore, improving the accuracy of grid fault detection has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a power grid-based fault detection method, apparatus, device, and storage medium to improve the accuracy of power grid fault detection.

[0005] In a first aspect, embodiments of this application provide a power grid-based fault detection method, applied to a current protection device installed in a line within the power grid, the method comprising:

[0006] Obtain a first voltage and a predicted load; the first voltage represents the minimum voltage of the protected line of the current protection device during operation; the predicted load represents the predicted load of the line after the current protection device;

[0007] A first threshold is determined based on a preset voltage and the first voltage; the preset voltage represents the rated voltage of the power grid; the first threshold represents the voltage criterion value for a current fault occurring in the line downstream of the current protection device.

[0008] A second threshold is determined based on the preset voltage and the predicted load; the second threshold represents the current criterion value for a current fault occurring in the line downstream of the current protection device.

[0009] Based on the first threshold and the second threshold, fault information is determined; the fault information indicates whether a current fault has occurred in the line after the current protection device.

[0010] In one possible implementation, determining the second threshold based on the preset voltage and the predicted load includes:

[0011] Based on the predicted load, the apparent power is determined; the apparent power represents the apparent power of the line after the current protection device.

[0012] A first current is determined based on the apparent power and the preset voltage; the first current represents the maximum load current of the power grid operation.

[0013] The second threshold is determined based on the first current.

[0014] In one possible implementation, determining fault information based on the first threshold and the second threshold includes:

[0015] Obtain the second voltage and second current in the circuit where the current protection device is installed at the current moment;

[0016] If the second voltage is less than the first threshold and the second current is greater than the second threshold, then it is determined that a current fault has occurred in the line after the current protection device.

[0017] In one possible implementation, obtaining the predicted load includes:

[0018] Acquire meteorological information and operational information; the meteorological information represents the weather conditions within a first preset time period, which is after the current time; the operational information includes the load of the line after the current protection device within a second preset time period, which is before the current time.

[0019] Based on the meteorological information and the operational information, load information at a preset time is determined; the preset time is within a first preset time period; the load information represents the load of the line after the current protection device at the preset time as predicted.

[0020] Based on the current time, the predicted load is selected from the load information at all preset times.

[0021] In one possible implementation, determining the load information at a preset time based on the meteorological information and the operational information includes:

[0022] The meteorological information and the operational information are input into a preset prediction model to obtain load information at a preset time. The preset prediction model is a trained neural network model used to perform data reasoning on the input meteorological information and operational information to obtain load information at a preset time.

[0023] In one possible implementation, the operational information further includes the power of each distributed power source connected in the line after the current protection device, and the method further includes:

[0024] Based on the meteorological information and the operational information, the power information at a preset time is determined; the power information represents the power of each distributed power source connected to the line after the current protection device at the preset time as predicted.

[0025] Based on the current time, the predicted power is selected from the power information at all preset times;

[0026] A third threshold is determined based on the predicted power; the third threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0027] In one possible implementation, determining the third threshold based on the predicted power includes:

[0028] For a distributed power source connected at a first preset position in the line after the current protection device, the first residual voltage of the distributed power source is detected; the first residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the protection line at the maximum impedance of the power grid.

[0029] Based on the power of the distributed power source in the first residual voltage and the predicted power, a third current of the distributed power source is determined; the third current represents the current generated by the distributed power source flowing to the end of the protection line.

[0030] A fourth current is determined based on the preset voltage; the fourth current represents the current generated by the power source of the power grid flowing to the end of the protection line.

[0031] A third threshold is determined based on each of the third currents and the fourth currents.

[0032] In one possible implementation, it also includes:

[0033] The fifth current is determined based on the preset voltage; the fifth current represents the current generated by the power source of the power grid that flows to the end of the backup line of the protection line.

[0034] For the distributed power source connected at the second preset position in the line after the current protection device, the second residual voltage of the distributed power source is detected; the second residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the backup line of the protection line at the maximum impedance of the grid.

[0035] The sixth current of the distributed power source is determined based on the power of the distributed power source in the second residual voltage and the predicted power; the sixth current represents the current generated by the distributed power source flowing to the end of the backup line of the protection line.

[0036] A fourth threshold is determined based on the fifth current and each of the sixth currents; the fourth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0037] In one possible implementation, it also includes:

[0038] A fifth threshold is determined based on the apparent power; the fifth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0039] Secondly, embodiments of this application provide a power grid-based fault detection device, applied to a current protection device installed in a power grid line, the device comprising:

[0040] The detection module is used to detect a first voltage and a predicted load; the first voltage represents the minimum voltage of the protected circuit of the current protection device during operation; the predicted load represents the predicted load of the circuit after the current protection device.

[0041] The first determining module is used to determine a first threshold based on a preset voltage and the first voltage; the preset voltage represents the rated voltage of the power grid; the first threshold represents the voltage criterion value for a current fault to occur in the line after the current protection device.

[0042] The second determining module is used to determine a second threshold based on the preset voltage and the predicted load; the second threshold characterizes the current criterion value for a current fault occurring in the line after the current protection device.

[0043] The third determining module is used to determine fault information based on the first threshold and the second threshold; the fault information indicates whether a current fault has occurred in the line after the current protection device.

[0044] Thirdly, embodiments of this application provide a power grid-based fault detection device, including: a memory and a processor;

[0045] The memory stores computer-executed instructions;

[0046] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0047] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0048] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0049] The power grid-based fault detection method, apparatus, equipment, and storage medium provided in this application acquire a first voltage and a predicted load in real time. The first voltage represents the minimum voltage of the protected line of the current protection device during operation, and the predicted load represents the predicted load of the line after the current protection device. This provides a data basis for dynamically updating the I-stage setting value of the current protection device, avoiding the use of fixed thresholds to analyze current faults. This achieves compatibility with the technical effect of strong power grid fluctuations caused by distributed power sources connecting to the distribution network and poor adaptability of fixed thresholds. By introducing a second threshold based on the predicted load, the action threshold of the current protection device is lowered, enabling the effective capture of weak fault currents that were originally submerged in the load current, fundamentally avoiding protection failure due to unclear fault characteristics. At the same time, by combining the voltage comparison load criterion corresponding to the first threshold, further judgment of fault identification is achieved. Even if the second current falls within the load fluctuation range, as long as the second voltage does not drop, the current protection device can reliably block. This effectively avoids protection maloperation caused by sudden load increases or current prediction errors, ensuring the continuity of power supply. Attached Figure Description

[0050] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0051] Figure 1 A flowchart illustrating the power grid-based fault detection method provided in this application. Figure 1 ;

[0052] Figure 2 A schematic diagram of the distribution network topology including distributed generation provided for this application;

[0053] Figure 3 A flowchart illustrating the power grid-based fault detection method provided in this application. Figure 2 ;

[0054] Figure 4 A schematic diagram of the structure of the power grid-based fault detection device provided in this application;

[0055] Figure 5 This is a schematic diagram of the structure of the power grid-based fault detection device provided in this application.

[0056] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0057] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0058] First, let me explain the terms used in this application:

[0059] Maximum operating mode: refers to the operating state in which the system has the most power input, the strongest grid connection, and the lowest impedance. It occurs during the high water season (all hydropower is on), the high load season (all thermal power is on), and when the grid is in closed-loop operation.

[0060] Maximum operating mode: refers to the operating state of the system with the least power input, the weakest grid connection, and the highest impedance. It occurs during the dry season, light load season, equipment maintenance, and open-loop operation of the power grid.

[0061] Three-phase short circuit: refers to a metallic connection occurring between three phase conductors.

[0062] Two-phase short circuit: refers to a metallic connection occurring between any two phase conductors.

[0063] Three-stage protection: This refers to configuring the protection of a line into three protection stages with different characteristics, each undertaking a different protection task, together forming a complete line protection scheme. The three protection stages are Stage I, Stage II, and Stage III. Stage I is instantaneous overcurrent protection, the primary protection, with instantaneous operation. Stage II is backup protection for the primary protection, with short-delay operation. Stage III is remote backup protection, with a longer-delay operation.

[0064] Boosting current: This refers to the phenomenon where, when a line fault occurs, a portion of the total current flowing through the fault point comes from these branch power sources (such as distributed power sources), resulting in the current flowing through the line protection being less than the total current flowing through the fault point.

[0065] Weak feeder fault: refers to a fault state in which the short-circuit current provided by the power source is very small (much smaller than the traditional short-circuit current level) when a short-circuit fault occurs in the power system, making it difficult for current protection equipment to accurately detect and identify it.

[0066] In the context of new power systems, the high penetration rate of large-scale distributed power sources (such as photovoltaic and wind power) is profoundly changing the operating characteristics of traditional distribution networks. Distribution networks are gradually evolving from a single-source radial structure to a multi-source heterogeneous active distribution network, and the system's operating status exhibits significant dynamism and uncertainty.

[0067] The output power of distributed power sources is significantly affected by meteorological conditions (such as light intensity, temperature, and wind speed), exhibiting strong intermittency and time-varying characteristics. For example, photovoltaic output may fluctuate by more than 50% within minutes during the transition between sunny and cloudy weather.

[0068] Meanwhile, the fault current characteristics of distributed power supply access points no longer follow the fault response rules of traditional induction motors. Under the low voltage ride-through control strategy, the fault current output of inverter-type power supplies is subject to the dual constraints of control logic and pre-fault operating state, exhibiting "weak feedback" characteristics.

[0069] Traditional distribution network line protection generally adopts the conventional three-stage current protection, which includes Stage I instantaneous overcurrent protection, Stage II time-limited instantaneous overcurrent protection, and Stage III overcurrent protection. Its setting relies on an "offline calculation, online fixing" mode. Maintenance personnel perform offline calculations based on the maximum and minimum operating modes of the power grid, combined with historical load data, and then embed the results into the protection equipment.

[0070] The implementation process of this method includes: 1) calculating the protection setting value through historical load data and system impedance parameters; 2) writing the setting value into the protection device, which will not be adjusted in subsequent operation.

[0071] Under complex operating conditions, traditional relay protection equipment based on fixed settings faces severe challenges: on the one hand, the protection equipment cannot sense the real-time output and fault response characteristics of distributed power sources, resulting in a serious mismatch between the protection settings and the actual operating state of the system; on the other hand, the access of distributed power sources changes the distribution pattern of fault current in the distribution network, causing the traditional protection differential coordination logic to fail, which may lead to protection maloperation or failure to operate, threatening the safety of the power grid.

[0072] The fault detection method, apparatus, equipment, and storage medium based on the power grid provided in this application are intended to solve the above-mentioned technical problems.

[0073] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0074] Figure 1 A flowchart illustrating the power grid-based fault detection method provided in this application. Figure 1,like Figure 1 As shown, this method is applied to current protection devices installed in lines within a power grid. The method includes:

[0075] S101. Obtain the first voltage and the predicted load; the first voltage represents the minimum voltage of the protected line of the current protection device during operation; the predicted load represents the predicted load of the line after the current protection device.

[0076] Among them, current protection devices are used to detect abnormal changes in line current (such as short circuits and overloads) and automatically disconnect the circuit when a fault occurs. Circuit protection devices can be installed at line switches (such as circuit breakers) in the power grid to ensure the safe operation of the power grid and equipment.

[0077] Figure 2 The schematic diagram of the distribution network topology including distributed generation provided in this application is as follows: Figure 2 As shown, this power distribution network is a 10 kV radial power supply network, mainly consisting of the following components:

[0078] Equivalent power source of power grid system This represents the power supply or equivalent voltage source provided by the superior substation.

[0079] Equivalent impedance of power grid system It reflects the impedance changes of the power grid system under different operating modes, including the maximum and minimum operating modes;

[0080] Point P is the outgoing line point of the substation, used to connect the power grid system side with the main power grid line;

[0081] Points Q and M are used to define the line. Point Q is an intermediate node connecting the main line and branch lines; point M is a terminal node. The line is divided into PQ segment and QM segment using points P, Q, and M.

[0082] Switch 1 is located after point P. A current protection device is installed at switch 1 to protect the PQ section line. That is, the current protection device at switch 1 protects the PQ section line and is the main incoming line protection switch of the power grid system.

[0083] Switch 2 is located after point Q. A current protection device is installed at switch 2 to protect the QM section line. That is, the protected line of the current protection device at switch 2 is the QM section line. At the same time, the QM section line is also the downstream feeder of the current protection device at switch 1. That is, the backup line of the current protection device at switch 1 is the QM section line.

[0084] Point T is the terminal load node, which connects to the distribution transformer and load.

[0085] IIDG (Inverter Interfaced Distributed Generation) is a distributed generation system. IIDG connects to the distribution network through a grid connection point Q and has low-voltage ride-through capability.

[0086] Fault point This indicates the typical location of a fault in the PQ line segment, used to analyze the protection operation characteristics of switch 1;

[0087] Fault point This indicates the typical location of a fault in the QM line section, used to analyze the protection coordination relationship between switch 1 and switch 2;

[0088] On the load side, various user loads are connected through distribution transformers, and the load size changes dynamically with factors such as season, time of day, and temperature.

[0089] The current protection device is a three-stage current protection device. It can dynamically update the setting values ​​of stage I, stage II, and stage III by processing the real-time collected data at fixed intervals. This allows the current protection device to dynamically update the setting values ​​used to determine current faults in real time. For example, the setting value can be updated every 15 minutes.

[0090] The technical solution of this application will be described in detail below, taking the current protection device at switch 1 as an example.

[0091] In a protected line, when the fault point is far from the distributed power source or the capacity of the distributed power source is small, the fault current output at the fault point may be less than or close to the maximum load current of the line. For example, the fault current is 1.2 times the rated voltage of the power grid system, and the maximum load current of the line is 1.0 times the rated voltage of the power grid system.

[0092] If the current amplitude setting is used alone to determine whether a current fault has occurred, the setting value must be high to avoid load current, such as 1.3 times the rated voltage of the power grid system. In this case, the weak fault current provided by the distributed generation cannot be detected, resulting in failure to operate.

[0093] To address the aforementioned technical issues, a first voltage is acquired during each update of the current protection device. This first voltage represents the minimum voltage of the protected circuit during operation; for example, it is the lowest voltage that may occur at the grid connection point under the most unfavorable fault conditions for protection operation.

[0094] For switch 1, the first voltage is: the minimum residual voltage of all distributed power sources connected to the grid at the grid connection point when a two-phase short circuit occurs at the end Q point of the protection line under the minimum operating mode of the power grid system (maximum equivalent impedance of the power grid system).

[0095] For example, for any distributed power source connected in the protection line, the minimum residual voltage at the grid connection point of the distributed power source can be calculated using the following formula (1):

[0096] (1);

[0097] In the formula, This represents the minimum residual voltage at the grid connection point of the i-th distributed power source; Indicates the rated voltage of the power grid system; This represents the impedance from the grid connection point of the i-th distributed power source to the fault point. This indicates the impedance of the power grid system under maximum operating conditions. It represents the total impedance from the power source to the fault point in the power grid system.

[0098] According to formula (1), the residual voltage at the grid connection point of a distributed generation source is equal to the rated voltage of the power grid system multiplied by a coefficient, which can be determined based on... , , The calculation shows that since the location of the fault point remains unchanged when the residual voltage at the grid connection point of the distributed power source is at its minimum, this coefficient remains unchanged. Since the rated voltage of the power grid system remains unchanged, the first voltage remains unchanged.

[0099] Therefore, for all distributed power sources connected to the protection line, a simulation system can be used to calculate the residual voltage at the grid connection point of each distributed power source when a two-phase short circuit occurs at the end of the protection line under the minimum operating mode of the power grid system. The minimum residual voltage is then selected as the first voltage from all the residual voltages of the distributed power sources. In subsequent calculations, the first voltage is obtained using the saved data.

[0100] Simultaneously with obtaining the first voltage, the predicted load is also obtained. The predicted load is the load of the line downstream of the current protection device, as predicted. The line downstream of the current protection device refers to the line from the installation point of the current protection device to the end of the line, i.e., the line under the jurisdiction of the current protection device. For example, for switch 1, the predicted load is the load of the line downstream of point P, as predicted. For instance, the predicted load can be obtained by analyzing the historical load of the line downstream of point P to understand the load fluctuation pattern.

[0101] S102. Determine the first threshold based on the preset voltage and the first voltage; the preset voltage represents the rated voltage of the power grid; the first threshold represents the voltage criterion value for a current fault occurring in the line after the current protection device.

[0102] For example, when fault current and normal load current are close, a low voltage threshold can be set to distinguish between normal load current fluctuations and true fault currents. This voltage threshold can then be used as the low voltage blocking value. Current protection devices can detect whether the real-time voltage is below this voltage threshold to differentiate between normal load current fluctuations and true fault currents.

[0103] Specifically, a first threshold can be determined based on a preset voltage and a first voltage. This first threshold is the low voltage threshold value, where the first threshold represents the voltage criterion value for a current fault occurring in the line downstream of the current protection device. For example, the first threshold can be calculated using the following formula (2):

[0104] (2);

[0105] In the formula, The first threshold is represented by "min"; the minimum function is represented by "min". This represents the first voltage. That is, the first threshold is the minimum value between the preset voltage multiplied by 0.7 and the first voltage.

[0106] In the formula, This is used to ensure that the voltage drops to a sufficiently low level during a fault, and that it is not mistakenly blocked during normal operation or minor fluctuations in the power grid system. This considers the residual voltage value that the distributed power source may have at the grid connection point under the most unfavorable fault conditions. By taking the minimum value between the two, both scenarios are taken into account.

[0107] S103. Determine the second threshold based on the preset voltage and predicted load; the second threshold represents the current criterion value for a current fault occurring in the line downstream of the current protection device.

[0108] For example, since the predicted load is the predicted load of the line after the current protection device, the power of the line after the current protection device can be obtained based on the electrical quantity relationship and the predicted load. Therefore, a current value is obtained based on the power of the line after the current protection device. This current value is used as a second threshold, which characterizes the current criterion value for a current fault occurring in the line after the current protection device. That is, the second threshold is used to determine whether the current detected in real time exceeds the fault current.

[0109] In some specific implementations of this embodiment, determining the second threshold based on the preset voltage and predicted load includes:

[0110] Based on the predicted load, the apparent power is determined; the apparent power represents the apparent power of the line after the current protection device; based on the apparent power and the preset voltage, the first current is determined; the first current represents the maximum load current of the power grid; based on the first current, the second threshold is determined.

[0111] For example, based on electrical quantity relationships and predicted load, the apparent power is determined. The apparent power is the apparent power of the line after the current protection device. For example, the apparent power can be calculated according to the following formula (3):

[0112] (3);

[0113] In the formula, Indicates apparent power; Indicates predicted power; This represents the power factor.

[0114] Then, based on the electrical quantity relationships, the first current is determined according to the apparent power and the preset voltage. The first current is the maximum load current of the power grid operation. For example, the first current can be calculated according to the following formula (4):

[0115] (4);

[0116] In the formula, Indicates the first current; This represents the load fluctuation coefficient, with a value ranging from 1.05 to 1.1.

[0117] After obtaining the first current, the second threshold is determined based on the first current. For example, the second threshold can be calculated according to the following formula (5):

[0118] (5);

[0119] in, This represents the second threshold, i.e., the low current threshold setting value; This represents the low-set reliability coefficient, used to ensure that the low-set value of section I reliably avoids the maximum load current. It can be set to 1.1.

[0120] The beneficial effects of this approach are as follows: by converting the predicted load into apparent power, and then using the apparent power and preset voltage to determine the first current, which is the maximum load current of the power grid, a second threshold can be determined based on the first current. This second threshold can then be used as the current criterion value for current faults in the lines downstream of the current protection device. This ensures that the second threshold is greater than the maximum possible load current while preventing the current protection device from malfunctioning during normal load fluctuations, thereby improving the accuracy of fault detection in the power grid.

[0121] S104. Determine the fault information based on the first threshold and the second threshold; the fault information indicates whether a current fault has occurred in the line after the current protection device.

[0122] The first threshold serves as a benchmark comparison value for determining whether a voltage anomaly has occurred, and the second threshold serves as a benchmark comparison value for determining whether a current anomaly has occurred. By comparing the real-time detected voltage with the first threshold and the real-time detected current with the second threshold, fault information is determined based on the comparison results. The fault information indicates whether a current fault has occurred in the line downstream of the current protection device; that is, the fault information can indicate either a current fault has occurred in the line downstream of the current protection device or not.

[0123] In some specific implementations of this embodiment, determining the fault information based on the first threshold and the second threshold includes:

[0124] Obtain the second voltage and second current in the line where the current protection device is installed at the current moment; if the second voltage is less than the first threshold and the second current is greater than the second threshold, then it is determined that a current fault has occurred in the line after the current protection device.

[0125] For example, by using the current sensor and voltage sensor installed inside the current protection device, the current and voltage at the installation location of the current protection device can be collected in real time, thereby obtaining the second voltage and second current in the line where the current protection device is installed at the current moment.

[0126] The second voltage is compared with the first threshold, and the second current is compared with the second threshold. If the second voltage is less than the first threshold and the second current is greater than the second threshold, it is determined that a current fault has occurred in the line after the current protection device, thereby triggering the protection action of the current protection device. At this time, the current fault is a weak feeder fault, that is, the fault current is close to the maximum load current but the voltage drops significantly.

[0127] If the second voltage is greater than or equal to the first threshold, or the second current is less than or equal to the second threshold, then it is determined that no weak feeder fault has occurred in the line after the current protection device.

[0128] It should be noted that the above fault judgment belongs to the first stage protection of the current protection device. The second and third stage protection can be performed based on the judgment process of the traditional three-stage protection.

[0129] The beneficial effects of this approach are as follows: by comparing the real-time acquired second voltage with the first threshold and the real-time acquired second current with the second threshold, when the current approaches the load current to the point that a weak feeder fault may occur, the voltage comparison results can be further used to determine whether a weak feeder fault has occurred. This realizes the implementation of weak feeder fault judgment, thereby reducing rejections and improving the accuracy of the power grid in detecting weak feeder faults.

[0130] The grid-based fault detection method provided in this application acquires a first voltage and a predicted load in real time. The first voltage represents the minimum voltage of the protected line of the current protection device during operation, and the predicted load represents the predicted load of the line after the current protection device. This provides a data basis for dynamically updating the I-stage setting value of the current protection device, avoiding the use of fixed thresholds to analyze current faults. This ensures compatibility with the technical effect of strong grid fluctuations caused by distributed power sources connecting to the distribution network, where fixed thresholds have poor adaptability. By introducing a second threshold based on the predicted load, the action threshold of the current protection device is lowered, enabling the effective capture of weak fault currents that were originally submerged in the load current. This fundamentally avoids protection failure due to unclear fault characteristics. Simultaneously, by combining the voltage comparison load criterion corresponding to the first threshold, further judgment of fault identification is achieved. Even if the second current falls within the load fluctuation range, as long as the second voltage does not drop, the current protection device can reliably lock out. This effectively avoids protection maloperation caused by sudden load increases or current prediction errors, ensuring the continuity of power supply.

[0131] Figure 3 A flowchart illustrating the power grid-based fault detection method provided in this application. Figure 2 ,like Figure 3 As shown, Figure 3 The embodiment illustrates the complete process of generating the current setting values ​​for stage I, stage II, and stage III protection of the current protection device. The above-mentioned acquisition of predicted load includes:

[0132] Acquire meteorological and operational information; the meteorological information represents the weather conditions within a first preset time period, which is after the current time; the operational information includes the load of the lines after the current protection device within a second preset time period, which is before the current time; determine the load information at a preset time based on the meteorological and operational information; the preset time is within the first preset time period; the load information represents the load of the lines after the current protection device at the predicted preset time; based on the current time, filter out the predicted load from the load information at all preset times.

[0133] The method includes:

[0134] S301. Obtain the first voltage, and obtain meteorological information and operational information; the meteorological information represents the weather conditions within a first preset time period, which is after the current time; the operational information includes the load of the line after the current protection device within a second preset time period, which is before the current time.

[0135] For example, the first voltage is obtained, and at the same time, the operation information can be obtained from the data collected in real time by the SCADA (Supervisory Control and Data Acquisition) system of the distribution network. The operation information includes the load of the line after the current protection device within a second preset time period.

[0136] For example, if the setting value is updated every 15 minutes, then the load curve of the line after the current protection device is obtained from the SCADA system of the distribution network for the hour before the current time every 15 minutes. That is, the second preset time period is the hour before the current time.

[0137] Simultaneously, meteorological information for the distributed power source area is obtained from the micro-weather station. This meteorological information characterizes the weather conditions within a first preset time period, which is located after the current time. For example, the meteorological information includes light intensity, wind speed, and temperature. The first preset time period is 4 hours after the current time.

[0138] When updating the settings for the first time, static parameters of the power grid can also be obtained, including line impedance, equivalent impedance of the main power source of the power grid system, rated capacity of distributed power sources, and low voltage ride-through control strategy parameters of the inverters of distributed power sources. The obtained static parameters are stored so that the stored data can be used directly for data processing in the future.

[0139] After acquiring the initial voltage, meteorological information, and operational information, the acquired data undergoes preprocessing (such as noise reduction, normalization, and outlier removal) to obtain preprocessed data. Subsequent data processing uses this preprocessed data for all calculations.

[0140] S302. Based on meteorological and operational information, determine the load information at a preset time; the preset time is within the first preset time period; the load information represents the load of the line after the current protection device at the preset time obtained through prediction.

[0141] For example, since meteorological information is information for a future period of time, and operational information is information for a historical period of time, the load fluctuation of the line after the current protection device can be predicted for a future period of time based on the operational information and the meteorological information.

[0142] For example, based on the analysis results of the fluctuation relationship between historical meteorological information and historical operational information, and according to the meteorological and operational information obtained at the current moment, the load information at a preset moment is determined. The preset moment is located within a first preset time period. For example, the first preset time period is 4 hours after the current moment. By dividing the first preset time period into 15-minute intervals, the load information at 16 preset moments within the first preset time period is obtained, thus forming the load fluctuation information for the next 4 hours.

[0143] In some specific implementations of this embodiment, determining the load information at a preset time based on meteorological and operational information includes:

[0144] Meteorological and operational information is input into a preset prediction model to obtain load information at a preset time. The preset prediction model is a trained neural network model used to perform data reasoning on the input meteorological and operational information to obtain load information at a preset time.

[0145] The preset prediction model can be a trained long short-term memory neural network model. The training data for the preset prediction model can be historical meteorological information and historical operational information from the past 1 to 3 years. By using historical meteorological data and historical operational information to train the long short-term memory neural network model to be trained, the preset prediction model is obtained. This allows the preset prediction model to learn the variation pattern of load information in the operational information with meteorological information, thereby enabling data inference on the input meteorological and operational information to obtain the load information at the preset time.

[0146] To ensure more accurate output load information, a probabilistic model can be embedded within the preset prediction model. This probabilistic model uses probability density prediction methods to generate the probability density distribution of the load at a preset time. Based on the mathematical expectation (i.e., average value) of the load's probability density distribution, the load information at the preset time is generated. In other words, the load information is the mathematical expectation of the predicted load's probability density distribution.

[0147] The beneficial effects of this approach are: by using a long short-term memory neural network model to perform data reasoning on meteorological data and operational information, load information at a preset time can be obtained, achieving refined processing of time-series data. Because long short-term memory neural networks have better data processing capabilities for time-series data, they can more accurately predict load information at future times.

[0148] S303. Based on the current time, filter out the predicted load from the load information at all preset times.

[0149] For example, load information at the nearest preset time to the current time can be used as the filtered predicted load. For instance, load information corresponding to the nearest 15 minutes after the current time can be used as the filtered predicted load. That is, every 15 minutes, the setting value is updated using the load information corresponding to the next 15 minutes, and the updated setting value is used as the benchmark value for current fault judgment in the following 15 minutes.

[0150] In some specific implementations of this embodiment, the preset prediction model internally utilizes a first reinforcement learning agent to process data to obtain load information at a preset time. After each preset time interval, the first measured load data at the current time is acquired. This first measured data is compared with the load information at the preset time obtained from the previous prediction, and the deviation between the two is calculated. This deviation is then converted into a reward / penalty signal for the first reinforcement learning agent, and the first weight information of the preset prediction model is updated online to obtain an updated model. During the next tuning value update, the updated model is used to infer the load information at the preset time, thereby correcting the load information at the preset time and obtaining more accurate load information.

[0151] In some specific implementations of this embodiment, the operating information also includes the power of each distributed power source connected in the line after the current protection device, and the above method further includes:

[0152] Based on meteorological and operational information, the power information at a preset time is determined; the power information represents the power of each distributed power source connected to the line after the current protection device at the preset time, as predicted; based on the current time, the predicted power is selected from the power information at all preset times; based on the predicted power, a third threshold is determined; the third threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0153] For example, the operational information also includes the power of each distributed power source connected to the line after the current protection device, and the power of the distributed power source is related to the load of the power grid. Therefore, the power information at a preset time can be determined based on meteorological information and operational information, that is, the correlation between changes in meteorological information, load information, and power information can be analyzed simultaneously.

[0154] For example, based on meteorological and operational information, power information is obtained at six preset times within a first preset time period. This power information represents the power of each distributed power source connected to the line downstream of the current protection device at the predicted preset times; that is, each power information includes the power of each of the distributed power sources connected to the line downstream of the current protection device.

[0155] Specifically, meteorological and operational information is input into a preset prediction model to obtain load and power information at a preset time. The training data for the preset prediction model also includes historical power information from the past 1 to 3 years, which includes the historical power of each distributed power source connected to the line after the current protection device.

[0156] Through model training, the pre-set prediction model not only learns the variation pattern of load information in operational information with meteorological data, but also learns the interconnected variation pattern of load information, power information, and meteorological information within the operational information. This enables data inference from the input meteorological and operational information to obtain load and power information at a preset time. The load and power information output by the pre-set prediction model at the preset time is stored for subsequent predictions.

[0157] After obtaining the power information at a preset time, the power information most recent at the preset time is used as the selected predicted power. For example, the power information corresponding to the nearest 15 minutes after the current time is used as the selected predicted power. That is, every 15 minutes, the setting value is updated using the power information corresponding to the next 15 minutes, and the updated setting value is used as the benchmark value for current fault judgment in the following 15 minutes.

[0158] Similarly, the preset prediction model internally utilizes a second reinforcement learning agent to process the data and obtain power information at a preset time. After each preset time, the second measured power data for the current time is acquired. This second measured data is compared with the previously predicted power information for the same preset time, and the deviation between the two is calculated. This deviation is then converted into a reward / penalty signal for the second reinforcement learning agent, updating the second weight information of the preset prediction model online to obtain an updated model. During the next tuning update, the updated model is used to infer the power information at the preset time, thereby correcting the power information and obtaining more accurate power information.

[0159] After obtaining the predicted power, a third threshold is determined based on the predicted power. This third threshold is used to determine whether a current fault has occurred in the line downstream of the current protection device. This current fault is a high-current fault, meaning the fault current is much greater than the load current, causing a severe voltage drop. The third threshold is used for the first-stage protection of the current protection device. For example, when the second current detected by the current protection device in real time exceeds the third threshold, a current fault is determined to have occurred, and the current protection device activates instantaneously.

[0160] It should be noted that, based on the inverter control strategy of distributed power sources, the output current of the distributed power source is related to the voltage at the grid connection point and the predicted power. Specifically, the fault current response model of the distributed power source can be represented by the following formula (6):

[0161] (6);

[0162] In the formula, This represents the output power of the distributed power source at a preset time t; This represents the power of distributed power sources in the predicted power at a preset time. This indicates the voltage at the grid connection point of the distributed power source. Indicates the maximum current multiple; Indicates the rated current of the distributed power source; Indicates the reactive power support coefficient; This represents the active power maintained by the distributed generation during low-voltage ride-through. This indicates the confined current of the distributed power source under deep voltage drop, which is a value of 1.8 to 2 times the rated current of the distributed power source.

[0163] Therefore, based on the inverter control strategy of distributed power sources, the current situation of the power grid system and the current situation of each distributed power source when a three-phase short circuit occurs under the maximum operating mode can be analyzed according to the predicted power to set a third threshold, thereby using the third threshold to detect high current faults.

[0164] Specifically, the third threshold is determined based on the predicted power, including:

[0165] For a distributed power source connected at a first preset position in the line after the current protection device, the first residual voltage of the distributed power source is detected; the first residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the protection line at the maximum impedance of the grid; based on the first residual voltage and the power of the distributed power source in the predicted power, the third current of the distributed power source is determined; the third current represents the current generated by the distributed power source flowing to the end of the protection line; based on the preset voltage, the fourth current is determined; the fourth current represents the current generated by the power source of the grid flowing to the end of the protection line; based on each third current and the fourth current, the third threshold is determined.

[0166] For example, the voltage at the grid connection point of distributed generation (DG) can be estimated under different operating modes and fault types in the power grid system. This voltage can then be substituted into the fault current response model of the DG to calculate the short-circuit current contribution value of the DG under different operating conditions and extract the maximum load. The operating modes include maximum and minimum operating modes, and the fault types include three-phase short-circuit faults and two-phase short-circuit faults.

[0167] For a distributed power source connected at a first preset position in the line after the current protection device, where the first preset position is the location of the current protection device that affects the fault current at the fault point when the fault point is the end of the protection line, the first residual voltage of the distributed power source is detected. The first residual voltage is the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the protection line at the maximum impedance of the power grid. For example, the first residual voltage of the distributed power source can be obtained by analyzing a preset simulation model.

[0168] The first residual voltage of the distributed power source is used as Substituting the predicted power of the distributed power source into the above formula (6), we obtain the power of the distributed power source. The distributed power source As the third current of this distributed power source The third current is the current generated by the distributed power source flowing to the end of the protection line when a three-phase short circuit occurs at the end of the protection line.

[0169] In addition to analyzing the third current of each distributed power source, it is also necessary to analyze the impact of the current generated on the fault point by the power grid system. The fourth current can be determined based on the preset voltage. The fourth current is the current generated by the power source of the power grid flowing to the end of the protection line. For example, the equivalent power source voltage can be determined based on the preset voltage. The equivalent power source voltage is 1.05 to 1.1 times the preset voltage. Then, the fourth current can be calculated according to the following formula (7):

[0170] (7);

[0171] In the formula, Indicates the fourth current; Indicates the equivalent power supply voltage; Indicates the minimum impedance of the power grid system; This indicates the line impedance from the installation point of the current protection device to the fault point.

[0172] After obtaining the fourth current and the third current of each distributed power source, the third threshold is determined based on the fourth current and the third currents. For example, the third threshold can be calculated using the following formulas (8)-(9):

[0173] (8);

[0174] (9);

[0175] In the formula, Indicates the maximum short-circuit current; This indicates the third threshold, which is set according to avoid the maximum short-circuit current at the end of the protected line; This represents the preset return coefficient, which is the coefficient of the return capability after the reaction current relay operates; m represents the total number of distributed power sources.

[0176] Based on this, for the first stage protection of the current protection device, the operating logic of the current protection device can be expressed by the following formula (10):

[0177] (10);

[0178] In the formula, Action represents the instantaneous action of the current protection device, such as tripping to disconnect the problematic line; This indicates the second current acquired in real time; This indicates the second voltage acquired in real time; Indicates the third threshold; This indicates "AND", meaning that the second current is greater than the second threshold and the second voltage is less than the first preset threshold. The term "or" indicates that the current protection device can be triggered to operate instantaneously if the second current is greater than the third preset threshold or if the second current is greater than the second threshold and the second voltage is less than the first preset threshold.

[0179] In the above execution steps, the future power of each distributed power source is predicted by acquiring real-time meteorological and operational information. This predicted power provides a data foundation for subsequent inverter control strategies based on distributed power sources and analysis of the third current of the distributed power sources. The third current is the current generated by the distributed power sources flowing to the end of the protection line. Based on the preset voltage (the rated voltage of the power grid system), the fourth current is determined. This fourth current is the current generated by the power sources of the power grid flowing to the end of the protection line. Combining the third current of each distributed power source, the maximum short-circuit current at the end of the protection line under maximum operating conditions can be analyzed. Based on the maximum short-circuit current, a third threshold is set, thereby enabling the current protection device to trigger protection actions in a timely manner when the current may exceed the maximum short-circuit current at the end of the protection line, ensuring line safety.

[0180] In some specific implementations of this embodiment, the sensitivity of the current protection device can also be verified. Specifically, the minimum short-circuit current flowing through the installation point of the current protection device is first calculated under the most unfavorable condition for protection operation. The most unfavorable condition for protection operation is: the power grid system is operating in the minimum operating mode, and a two-phase short circuit occurs at the end of the protection range of the current protection device (the line farthest from the protection installation point, where the short-circuit current is the smallest). For example, the minimum short-circuit current can be calculated using the following formula (11):

[0181] (11);

[0182] in, Indicates the minimum short-circuit current; This refers to the current generated on the power grid side when a two-phase short circuit occurs at the end of the protection range of the current protection device; This refers to the current generated by the distributed power source when a two-phase short circuit occurs at the end of the protection range of the current protection device.

[0183] The following formula (12) can be used to calculate it. :

[0184] (12);

[0185] In the formula, This represents the maximum impedance of the power grid system.

[0186] When a two-phase short circuit occurs at the end of the protection range of the current protection device in minimum operating mode, the voltage at the connection point of the distributed power source can be detected. Distributed power sources Substituting the predicted power of the distributed power source into the above formula (6), we obtain the power of the distributed power source. The distributed power source As the third current of this distributed power source .

[0187] During the process of updating the protection setting value, it is possible to utilize This is to verify the sensitivity coefficient of each protection segment, making the sensitivity coefficient of each protection segment more accurate, so that the current protection device can still operate reliably under the most unfavorable fault conditions.

[0188] S304. Determine the first threshold based on the preset voltage and the first voltage.

[0189] S305. Determine the second threshold based on the preset voltage and predicted load.

[0190] S306. Determine the fault information based on the first threshold and the second threshold.

[0191] S307. Determine the fifth current based on the preset voltage; the fifth current represents the current generated by the power source of the power grid that flows to the end of the backup line of the protection line.

[0192] The setting values ​​for the second-stage protection of the current protection device are continuously updated. Given that the technical solution in this application uses high-precision real-time predictive data for adaptive adjustment, the setting values ​​can closely follow changes in the operating status of the power grid system. Therefore, the technical solution in this application weakens the strict time gradient coordination requirements between traditional three-stage protection. Selectivity is ensured through precise dynamic adjustment of the setting values, thereby allowing for appropriate compression of the operating delay of each protection stage to adapt to the complex and variable fault current characteristics after the integration of distributed power sources.

[0193] For Stage II protection, time-limited instantaneous overcurrent protection based on real-time branch coefficients can be used. Stage II protection needs to coordinate with Stage I protection of the backup line of the protected line, i.e., the adjacent next-level line of the protected line. Considering that the access of distributed power sources will generate additional current at the fault point, causing the traditional fixed branch coefficient to fail, a real-time branch coefficient can be used for correction.

[0194] Specifically, based on formula (7), the fifth current can be calculated according to the preset voltage. The fifth current is the current generated by the power supply of the grid flowing to the end of the backup line of the protected line. For example, for switch 1, its protected line is the PQ section line, and its backup line is the QM line. The fifth current is the current generated by the power supply of the grid flowing to the end of the QM line when a three-phase short circuit occurs at the end of the QM line under the maximum operating mode. .

[0195] S308. For a distributed power source connected at a second preset position in the line after the current protection device, detect the second residual voltage of the distributed power source; the second residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the backup line of the protection line at the maximum impedance of the power grid.

[0196] The second preset position refers to the location of the current protection device that affects the fault current at the fault point when the fault point is at the end of the backup line. For each distributed power source connected at the second preset position in the line after the current protection device, the second residual voltage of the distributed power source is detected. The second residual voltage is the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the backup line of the protection line at the maximum impedance of the grid.

[0197] S309. Determine the sixth current of the distributed power source based on the power of the distributed power source in the second residual voltage and the predicted power; the sixth current represents the current generated by the distributed power source flowing to the end of the backup line of the protection line.

[0198] For each distributed power source, substitute the second residual voltage and the predicted power of the distributed power source into the above formula (6) to obtain the power of the distributed power source. The distributed power source As the sixth current of this distributed power source .

[0199] S310. Determine the fourth threshold based on the fifth current and each of the sixth currents; the fourth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0200] For example, a fourth threshold is determined based on the fifth current and each of the sixth currents, and the fourth threshold is the setting value for the stage II protection. For instance, the fourth threshold can be calculated according to the following formulas (13)-(14):

[0201] (13);

[0202] (14);

[0203] In the formula, Indicates the branch coefficient; This represents the fourth threshold; This represents the reliability coefficient of the second-stage protection (with a value ranging from 1.1 to 1.2). This indicates the real-time setting value for detecting high-current faults in the I-stage protection of the backup line.

[0204] The operating logic of the second-stage protection is as follows: when the real-time detected second current is greater than the fourth threshold and the duration is greater than the first time threshold (within the range of 0.3 seconds to 0.5 seconds), a current fault is determined to have occurred, and the protection action is triggered.

[0205] In the above execution steps, based on the predicted data, the fifth current is determined in real time. This fifth current represents the current generated by the power source of the grid flowing to the end of the backup line of the protection line, and is a dynamically calculated current value in real time. Furthermore, the second residual voltage of the distributed generation is detected in real time. This second residual voltage represents the voltage at the grid connection point of the distributed generation when a three-phase short circuit occurs at the end of the backup line of the protection line at the maximum impedance of the grid. Based on the second residual voltage and the power of the distributed generation in the predicted power, the sixth current of the distributed generation is determined. This sixth current represents the current generated by the distributed generation flowing to the end of the backup line of the protection line, and is also a dynamically calculated current value in real time. The fourth threshold obtained from the fifth and sixth currents is used to determine whether a current fault has occurred in the line downstream of the current protection device. This ensures that regardless of fluctuations in the output of the distributed generation, the fourth threshold can maintain precise coordination with the first-stage protection of the downstream line, thereby improving the accuracy of fault detection.

[0206] S311. Determine the fifth threshold based on the apparent power; the fifth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0207] Continue updating the settings for the third-stage protection of the current protection device. The third-stage protection serves as a remote backup protection and also handles overload clearing. It employs time-definite overcurrent logic. The operating current only needs to avoid exceeding the maximum load current of the protected circuit.

[0208] For example, the fifth threshold can be determined based on the actual power, and the fifth threshold is the setting value of the III-stage protection. Specifically, the fifth threshold can be calculated according to the following formula (15):

[0209] (15);

[0210] In the formula, This represents the fifth threshold; it represents the reliability coefficient of the III-stage protection, with a value ranging from 1.15 to 1.2. This represents the return coefficient of the current protection device, with a value ranging from 0.85 to 0.9.

[0211] The operating logic of the third-stage protection is as follows: when the real-time monitored second current is greater than the fifth threshold and the duration is greater than the second time threshold (the value range is 0.5 seconds to 1.0 seconds), the protection action is triggered.

[0212] In the above execution steps, a fifth threshold is determined based on the apparent power. This fifth threshold is used to determine whether a current fault has occurred in the line downstream of the current protection device. Since the apparent power is a real-time predicted power value, compared to using a fixed setting value for the III-stage protection judgment, the fifth threshold fluctuates in real time with the load prediction, thereby ensuring that the setting value of the III-stage protection can accurately fall at the optimal position that just avoids the current maximum load. This makes the protection setting value highly matched with the actual operating state, thereby improving the accuracy of fault detection.

[0213] To verify the effectiveness of the technical solution of this application in distribution networks with large-scale distributed generation integration, based on Figure 2 A simulation model of the power distribution network topology was built to further illustrate the technical solution of this application.

[0214] The simulation scenario time was set as follows: the observation window was selected during the summer when the photovoltaic output fluctuated greatly and was at its peak (e.g., 12:00-12:15).

[0215] The simulation object is: In this embodiment, we will analyze switch 1. The rated voltage of the distribution network is 10 kV.

[0216] Meteorological and operational information is collected through the SCADA system and micro-weather stations. After outlier removal and normalization, the processed meteorological and operational information is used in subsequent data processing.

[0217] Based on meteorological and operational information, a 12:15 predicted power and predicted load are generated using a pre-set prediction model. The predicted power is then rolled back based on the latest measured power deviation, and the predicted power is rolled back based on the latest measured load deviation. Subsequent data processing uses the corrected predicted power and predicted load.

[0218] Based on the predicted power and load, and combined with the grid operation mode and the general calculation model for distributed generation fault current of the inverter, the fault current of each distributed generation is calculated. and .

[0219] Selecting a load fluctuation coefficient of 1.1, calculate the first current:

[0220] (16);

[0221] Given a maximum impedance of 1.0 ohm for the power grid system, and a two-phase metallic short circuit occurring at point Q, calculate... :

[0222] (17);

[0223] For a two-phase short circuit, the voltage at the grid connection point of the distributed generation is approximately half of the voltage before the fault, i.e. .

[0224] Based on the inverter's low voltage ride-through characteristics, when At this time, the inverter is in the deep drop zone, and the output current is limited but will increase (assuming the multiple is 1.5 times the rated current).

[0225] (18);

[0226] Set the minimum impedance of the power grid system to 0.5 ohms, and consider three-phase short circuits occurring at points Q and M respectively.

[0227] When a three-phase short circuit occurs at point Q, calculate Record it as :

[0228] (19);

[0229] When a three-phase short circuit occurs at point M, i.e., when a three-phase short circuit occurs in the backup line, the line impedance increases by 1.7 ohms. Calculate... Record it as :

[0230] (20);

[0231] At this point, the residual voltage at the grid connection point Q is determined by the voltage drop of the fault current on the QM line segment:

[0232] (twenty one);

[0233] because ,therefore It is 1.5 times the rated current of the distributed power source:

[0234] (twenty two);

[0235] Total current at the fault point for:

[0236] (twenty three);

[0237] For segment I protection:

[0238] Set according to the maximum short-circuit current at the end of the protected line. :

[0239] (twenty three);

[0240] set up :

[0241] (twenty four);

[0242] Pick 0.7 times:

[0243] (25);

[0244] When the real-time detected current is between 160A and 900A, and the real-time detected voltage is below 7000V, a weak feeder fault is identified, triggering the protection operation. Alternatively, when the real-time detected current is greater than 900A, a high-current fault is identified, triggering the protection operation.

[0245] For segment II protection:

[0246] Due to the boosting effect of distributed power sources, computing :

[0247] (26);

[0248] calculate :

[0249] (27);

[0250] The action time is set to 0.3 seconds. When the real-time detected current is greater than 690A and the current duration is greater than 0.3 seconds, a current fault is determined to have occurred, and the protection action is triggered.

[0251] For III-stage protection:

[0252] calculate :

[0253] (28);

[0254] The action time is set to 0.6 seconds. When the real-time detected current is greater than 205A and the current duration is greater than 0.6 seconds, a current fault is determined to have occurred, and the protection action is triggered.

[0255] The final setting value is as follows:

[0256] Stage I protection: High setting 900A, low setting 160A (blocking voltage 7000V), time limit 0 seconds.

[0257] Stage II protection: setting value 690A, time limit 0.3 seconds.

[0258] Stage III protection: setting value 205A, time limit 0.6 seconds.

[0259] Figure 4 The schematic diagram of the power grid-based fault detection device provided in this application is as follows: Figure 4 As shown, the fault detection device 40 based on the power grid provided in this embodiment is applied to current protection devices installed in lines of the power grid.

[0260] The acquisition module 401 is used to acquire a first voltage and a predicted load; the first voltage represents the minimum voltage of the protected line of the current protection device during operation; the predicted load represents the predicted load of the line after the current protection device.

[0261] The first determining module 402 is used to determine a first threshold based on a preset voltage and a first voltage; the preset voltage represents the rated voltage of the power grid; the first threshold represents the voltage criterion value for a current fault to occur in the line after the current protection device.

[0262] The second determining module 403 is used to determine a second threshold based on a preset voltage and a predicted load; the second threshold represents the current criterion value for a current fault occurring in the line downstream of the current protection device.

[0263] The third determining module 404 is used to determine fault information based on the first threshold and the second threshold; the fault information indicates whether a current fault has occurred in the line after the current protection device.

[0264] In one possible implementation, the second determining module 403 is further configured to:

[0265] Based on the predicted load, the apparent power is determined; the apparent power characterizes the apparent power of the line after the current protection device.

[0266] The first current is determined based on the apparent power and the preset voltage; the first current represents the maximum load current of the power grid operation.

[0267] The second threshold is determined based on the first current.

[0268] In one possible implementation, the third determining module 404 is further configured to:

[0269] Obtain the second voltage and second current in the circuit where the current protection device is installed at the current moment;

[0270] If the second voltage is less than the first threshold and the second current is greater than the second threshold, then it is determined that a current fault has occurred in the line after the current protection device.

[0271] In one possible implementation, module 401 is also used for:

[0272] Acquire meteorological and operational information; the meteorological information represents the weather conditions within a first preset time period, which is after the current time; the operational information includes the load of the line after the current protection device within a second preset time period, which is before the current time.

[0273] Based on meteorological and operational information, the load information at a preset time is determined; the preset time is within the first preset time period; the load information represents the load of the line downstream of the current protection device at the preset time as predicted.

[0274] Based on the current time, the predicted load is selected from the load information at all preset times.

[0275] In one possible implementation, module 401 is also used for:

[0276] Meteorological and operational information is input into a preset prediction model to obtain load information at a preset time. The preset prediction model is a trained neural network model used to perform data reasoning on the input meteorological and operational information to obtain load information at a preset time.

[0277] In one possible implementation, the operational information also includes the power of each distributed power source connected in the line downstream of the current protection device, and the grid-based fault detection device 40 further includes a fourth determining module for:

[0278] Based on meteorological and operational information, the power information at a preset time is determined; the power information represents the power of each distributed power source connected to the line after the current protection device at the preset time as predicted.

[0279] Based on the current time, the predicted power is selected from the power information at all preset times;

[0280] A third threshold is determined based on the predicted power; the third threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0281] In one possible implementation, the fourth determining module is also used for:

[0282] For the distributed power source connected at the first preset position in the line after the current protection device, the first residual voltage of the distributed power source is detected; the first residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the protection line at the maximum impedance of the power grid.

[0283] The third current of the distributed power source is determined based on the power of the distributed power source in the first residual voltage and the predicted power; the third current represents the current generated by the distributed power source flowing to the end of the protection line.

[0284] The fourth current is determined based on the preset voltage; the fourth current represents the current generated by the power source of the power grid and flowing to the end of the protected line.

[0285] The third threshold is determined based on the third and fourth currents.

[0286] In one possible implementation, the power grid-based fault detection device 40 further includes a fifth determining module, used for:

[0287] The fifth current is determined based on the preset voltage; the fifth current represents the current generated by the power source of the power grid that flows to the end of the backup line of the protection line.

[0288] For the distributed power source connected at the second preset position in the line after the current protection device, the second residual voltage of the distributed power source is detected; the second residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the backup line of the protection line at the maximum impedance of the grid.

[0289] The sixth current of the distributed power source is determined based on the power of the distributed power source in the second residual voltage and the predicted power; the sixth current characterizes the current generated by the distributed power source flowing to the end of the backup line of the protection line.

[0290] The fourth threshold is determined based on the fifth current and each of the sixth currents; the fourth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0291] In one possible implementation, the fifth determining module is also used for:

[0292] The fifth threshold is determined based on the apparent power; the fifth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

[0293] The power grid-based fault detection device provided in this embodiment can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0294] Figure 5 This is a schematic diagram of the structure of the power grid-based fault detection device provided in this application. Figure 5 As shown, the power grid-based fault detection device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the power grid-based fault detection device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus.

[0295] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0296] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0297] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0298] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0299] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0300] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0301] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0302] The aforementioned readable storage medium 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 storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0303] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0304] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0305] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0306] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0307] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0308] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0309] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A fault detection method based on power grids, characterized in that, The method, applied to current protection devices installed in power grid lines, includes: Obtain a first voltage and a predicted load; the first voltage represents the minimum voltage of the protected line of the current protection device during operation; the predicted load represents the predicted load of the line after the current protection device. A first threshold is determined based on a preset voltage and the first voltage; the preset voltage represents the rated voltage of the power grid; the first threshold represents the voltage criterion value for a current fault to occur in the line downstream of the current protection device. A second threshold is determined based on the preset voltage and the predicted load; the second threshold represents the current criterion value for a current fault occurring in the line downstream of the current protection device. Based on the first threshold and the second threshold, fault information is determined; the fault information indicates whether a current fault has occurred in the line after the current protection device.

2. The method according to claim 1, characterized in that, Determining a second threshold based on the preset voltage and the predicted load includes: Based on the predicted load, the apparent power is determined; the apparent power represents the apparent power of the line after the current protection device. A first current is determined based on the apparent power and the preset voltage; the first current represents the maximum load current of the power grid operation. The second threshold is determined based on the first current.

3. The method according to claim 1, characterized in that, Based on the first threshold and the second threshold, fault information is determined, including: Obtain the second voltage and second current in the circuit where the current protection device is installed at the current moment; If the second voltage is less than the first threshold and the second current is greater than the second threshold, then it is determined that a current fault has occurred in the line after the current protection device.

4. The method according to claim 1, characterized in that, Obtaining the forecast load includes: Acquire meteorological information and operational information; the meteorological information represents the weather conditions within a first preset time period, which is after the current time; the operational information includes the load of the line after the current protection device within a second preset time period, which is before the current time. Based on the meteorological information and the operational information, load information at a preset time is determined; the preset time is within a first preset time period; the load information represents the load of the line downstream of the current protection device at the preset time as predicted. Based on the current time, the predicted load is selected from the load information at all preset times.

5. The method according to claim 4, characterized in that, Based on the meteorological information and the operational information, determine the load information at a preset time, including: The meteorological information and the operational information are input into a preset prediction model to obtain load information at a preset time. The preset prediction model is a trained neural network model used to perform data reasoning on the input meteorological information and operational information to obtain load information at a preset time.

6. The method according to claim 4, characterized in that, The operational information also includes the power of each distributed power source connected in the line after the current protection device, and the method further includes: Based on the meteorological information and the operational information, the power information at a preset time is determined; the power information represents the power of each distributed power source connected to the line after the current protection device at the preset time as predicted. Based on the current time, the predicted power is selected from the power information at all preset times; A third threshold is determined based on the predicted power; the third threshold is used to determine whether a current fault has occurred in the line after the current protection device.

7. The method according to claim 6, characterized in that, Based on the predicted power, a third threshold is determined, including: For a distributed power source connected at a first preset position in the line after the current protection device, the first residual voltage of the distributed power source is detected; the first residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the protection line at the maximum impedance of the power grid. Based on the power of the distributed power source in the first residual voltage and the predicted power, a third current of the distributed power source is determined; the third current represents the current generated by the distributed power source flowing to the end of the protection line. A fourth current is determined based on the preset voltage; the fourth current represents the current generated by the power source of the power grid flowing to the end of the protection line. A third threshold is determined based on each of the third currents and the fourth currents.

8. The method according to claim 6, characterized in that, Also includes: The fifth current is determined based on the preset voltage; The fifth current characterizes the current generated by the power source of the power grid that flows to the end of the backup line of the protection line. For the distributed power source connected at the second preset position in the line after the current protection device, the second residual voltage of the distributed power source is detected; the second residual voltage represents the voltage at the grid connection point of the distributed power source when a three-phase short circuit occurs at the end of the backup line of the protection line at the maximum impedance of the grid. The sixth current of the distributed power source is determined based on the power of the distributed power source in the second residual voltage and the predicted power; The sixth current characterizes the current generated by the distributed power source flowing to the end of the backup line of the protection line. The fourth threshold is determined based on the fifth current and each of the sixth currents; The fourth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

9. The method according to claim 2, characterized in that, Also includes: A fifth threshold is determined based on the apparent power; The fifth threshold is used to determine whether a current fault has occurred in the line after the current protection device.

10. A fault detection device based on a power grid, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-9.

Images