Intelligent fusion method and system for multi-scene fault research and judgment of 10kV power distribution network

Abstract

The invention discloses a 10kV power distribution network multi-scene fault research and judgment intelligent fusion method and system, and belongs to the technical field of power distribution network fault analysis, and the method comprises the steps: judging whether a starting condition is satisfied or not based on the change of zero-sequence voltage, and executing a feature extraction step when the starting condition is satisfied; extracting characteristic data related to the fault, wherein the characteristic data comprises a characteristic reflecting a voltage and current phase relation, a characteristic reflecting an energy characteristic and a characteristic reflecting a current energy ratio; according to a preset feature selection rule, determining features used for fault judgment from the feature data; determining whether the fault is located in the monitoring section based on the features for fault determination; and updating starting parameters for subsequent judgment based on the voltage and current data during the fault period. According to the method, the fault judgment result is given through the judgment result of one of the three algorithms selected through feature quantity self-recognition and self-judgment, the algorithms are selected in a targeted mode for multiple complex scenes on site, and the fault judgment accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault analysis, and in particular to a 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion method and system. Background Art

[0002] 10kV distribution lines operate in a harsh environment, making them prone to frequent faults, including short circuits, line breaks, and single-phase grounding faults. Single-phase grounding faults account for 80% of all faults. While single-phase grounding faults do not affect normal power supply, if not promptly and reliably addressed, they can cause wildfires, overvoltage on the line, and subsequent faults, resulting in loss of life and property. Currently, transient fault signal methods are used to address grounding faults. These methods use the fault signal generated by a single-phase grounding event to select and locate the line. There are two types: steady-state fault signal methods and transient fault signal methods. Steady-state fault signal methods include the zero-sequence current amplitude and phase ratio method, the zero-sequence current active component method, and the zero-sequence current reactive component method. Steady-state signal methods are affected by the neutral point grounding method and require high sampling accuracy for the device's steady-state parameters. Transient fault signal methods include the first half-wave method, wavelet analysis, transient direction method, and phase asymmetry method. These methods are not affected by arc suppression coils, but are affected by the short duration, unstable frequency band, and small amplitude of transient signals. Because transient signal characteristics are far more pronounced than steady-state characteristics during a fault, transient methods outperform steady-state methods, especially for high-resistance grounding and low-current grounding scenarios. Both steady-state and transient signal methods have their own advantages and disadvantages, and their judgment capabilities vary in different scenarios. When designing a ground fault analysis algorithm, the applicability of a single algorithm and the accuracy of fault diagnosis must also be considered. Summary of the Invention

[0003] To solve the above technical problems, an intelligent fusion method for multi-scenario fault analysis and judgment of 10kV distribution network is proposed, which includes collecting three-phase voltage, three-phase current, zero-sequence voltage and zero-sequence current data of distribution lines;

[0004] determining whether a start-up condition is satisfied based on the change of the zero-sequence voltage, and executing a feature extraction step if the condition is satisfied;

[0005] Extracting characteristic data related to the fault, the characteristic data including a characteristic reflecting the phase relationship between the voltage and the current, a characteristic reflecting the energy characteristic, and a characteristic reflecting the current-energy ratio;

[0006] Determining features for fault diagnosis from the feature data according to preset feature selection rules;

[0007] Based on the features used for fault judgment, determining whether the fault is located within the monitoring section;

[0008] Based on the voltage and current data during the fault period, startup parameters used for subsequent judgment are updated.

[0009] As an optimal solution of the intelligent fusion method for multi-scenario fault analysis of a 10kV distribution network described in the present invention, the characteristic reflecting the phase relationship between the voltage and current includes an impedance phase characteristic calculated based on the phase difference between the zero-sequence voltage and the zero-sequence current, and the impedance phase characteristic is used to indicate whether the phase difference between the zero-sequence voltage and the zero-sequence current is within a preset quadrant range.

[0010] As an optimal solution of the intelligent fusion method for multi-scenario fault analysis of a 10kV distribution network described in the present invention, the quadrant range includes a phase range in which the zero-sequence voltage leads the zero-sequence current by more than 90 degrees, and the impedance phase characteristic is determined by real-time calculation of the cosine value of the phase difference.

[0011] As an optimal solution of the intelligent fusion method for multi-scenario fault analysis of a 10kV distribution network described in the present invention, the feature reflecting the energy characteristics includes an energy integral value obtained by integrating the point-by-point product of the zero-sequence voltage and the zero-sequence current within a preset time window after the fault occurs.

[0012] As a preferred solution of the intelligent fusion method for multi-scenario fault analysis of a 10kV distribution network described in the present invention, the energy integral value is used to judge the polarity relationship between the zero-sequence voltage and the zero-sequence current to distinguish between fault lines and sound lines.

[0013] As a preferred solution of the intelligent fusion method for multi-scenario fault analysis of a 10kV distribution network described in the present invention, the characteristics reflecting the current energy ratio include filtering the three-phase current data within two cycles before and after the fault occurs, eliminating frequency components below 150Hz, calculating the energy of each phase current after filtering, and determining the current energy ratio by the ratio of the maximum value to the minimum value.

[0014] As a preferred solution of the intelligent fusion method for multi-scenario fault analysis of a 10kV distribution network described in the present invention, when the current energy ratio is greater than or equal to a preset threshold, it is determined that the fault is located within the monitoring section.

[0015] As a preferred solution of the 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion system described in the present invention, it is characterized by comprising: a starting judgment module for collecting three-phase voltage, three-phase current, zero-sequence voltage and zero-sequence current data of the distribution line;

[0016] a feature extraction module, configured to determine whether a start-up condition is satisfied based on a change in the zero-sequence voltage, and to perform a feature extraction step if the condition is satisfied;

[0017] a feature selection module configured to extract feature data related to the fault, the feature data including features reflecting the phase relationship between the voltage and current, features reflecting energy characteristics, and features reflecting the current-energy ratio; and determine features for fault diagnosis from the feature data according to preset feature selection rules;

[0018] a fault judgment module, configured to judge whether the fault is located within the monitoring section based on the features used for fault judgment;

[0019] The parameter updating module is used to update the starting parameters used for subsequent judgment based on the voltage and current data during the fault period.

[0020] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the intelligent fusion method for multi-scenario fault analysis and judgment of a 10kV distribution network.

[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion method.

[0022] The present invention has the following beneficial effects: By collecting voltage and current information on the line in real time and monitoring voltage and current changes, it initiates characteristic calculation when the zero-sequence voltage reaches a fixed value. Based on this characteristic value, it intelligently selects a low-current grounding detection algorithm, which can accommodate different neutral point grounding schemes and accurately detect single-phase grounding faults. After each determination, the starting fixed value is optimized based on the fault characteristics, achieving adaptive fixed value detection and further improving the accuracy of single-phase grounding faults.

[0023] A variety of algorithms are used to judge single-phase grounding faults. The fault judgment result is given by selecting one of the three algorithms through self-identification and self-judgment of characteristic quantities. For various complex scenarios on site, the algorithm is selected in a targeted manner to improve the accuracy of fault judgment.

[0024] This invention also features a zero-sequence voltage startup value self-calibration function. By using the characteristics of historical metallic faults, the system calculates the zero-sequence voltage during a ground fault across a fixed transition resistor. This zero-sequence voltage is then used to set the zero-sequence voltage startup value. This resolves the issue of missed faults caused by inaccurately setting the zero-sequence voltage startup value on site. This improves the accuracy of fault diagnosis and enhances the reliability of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 This is an overall flow chart of an intelligent fusion method for multi-scenario fault analysis and judgment in a 10kV distribution network provided by one embodiment of the present invention.

[0027] Figure 2 This is a simulation line topology diagram of an intelligent fusion method for multi-scenario fault analysis and judgment in a 10kV distribution network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0029] Example 1, with reference to Figure 1 , which is the first embodiment of the present invention, provides a 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion method, including:

[0030] Step 1:

[0031] S1.1 After a single-phase ground fault occurs, the three-phase voltages, three-phase currents, zero-sequence voltage, and zero-sequence current all change. The algorithm uses the zero-sequence voltage as the ground fault triggering criterion. When a sudden change in the zero-sequence voltage is detected that exceeds the trigger value U0zd, feature extraction is performed based on the unique variation patterns of the fault. The present invention extracts three features in total.

[0032] S1.2 Zero-sequence impedance cosine:

[0033] In an ungrounded neutral system, after a single-phase ground fault occurs, the zero-sequence current in the faulted line is opposite to that in the intact line. The zero-sequence current in the faulted line flows from the line to the busbar, while the zero-sequence current in the intact line flows from the busbar to the line. Because the zero-sequence impedance loop still has a certain resistive component, the zero-sequence voltage generally leads the zero-sequence current by at least 90°.

[0034] In a neutral-point arc suppression coil-grounded system, after a single-phase ground fault occurs, the arc suppression coil's inductive current compensates, causing the zero-sequence current in the faulted line to flow in the same direction as the non-faulted line, flowing from the busbar to the line. However, due to the arc suppression coil's internal resistance and the losses in other zero-sequence impedance loops on the line, a resistive current flows. The zero-sequence current typically leads the zero-sequence voltage by more than 90°.

[0035] Therefore, we can know that the phase difference between the zero-sequence voltage and the zero-sequence current falls in the second and third quadrants, and the zero-sequence impedance cosine value is negative. Therefore, the fault can be judged based on this feature. If the zero-sequence impedance cosine value is negative, it is an in-zone fault, otherwise it is an out-of-zone fault.

[0036] Calculate the zero-sequence angle difference of zero-sequence voltage and zero-sequence current in real time, and calculate the cosine value. Calculation method:

[0037]

[0038] Among them D P is the cosine value of the zero-sequence impedance, is the zero-sequence voltage phase, is the zero-sequence current phase.

[0039] S1.3 Zero-sequence energy integral:

[0040] A small current grounding event exhibits a distinct transient process. The transient current can reach hundreds of amperes, with a primary resonant frequency of approximately 200 to 2000 Hz and a duration typically less than 2 milliseconds. Transients frequently occur in unstable faults, such as arc grounding or intermittent grounding. The high frequency of transient signals is unaffected by arc suppression coils.

[0041] Therefore, whether it is an ungrounded system or a grounded system with arc suppression coils, the transient zero-sequence voltage u0(t) and the zero-sequence current i0(t) of the fault line have opposite polarities, and the energy integral is negative. Correspondingly, u0(t) and the transient zero-sequence current i0(t) of the intact line have the same polarity, and the energy integral is positive.

[0042] Therefore, we multiply the zero-sequence voltage sampling point and the zero-sequence current sampling point within one cycle after the fault, and add them up to get the zero-sequence energy integral. The calculation formula is as follows:

[0043]

[0044] Where u0(i) is the transient zero-sequence voltage sampling point, i0(i) is the transient zero-sequence voltage sampling point, and n is the number of sampling points in one cycle. i = 1, 2, ... n.

[0045] S1.4 Three-phase current high-frequency energy ratio:

[0046] The current on the line is divided into two parts: the first part is the capacitive current of the line to the ground, and the second part is the load current.

[0047] After a single-phase ground fault occurs, the voltage of the single-phase ground fault line remains unchanged, so the load current remains unchanged. However, the neutral point offset produces a zero-sequence voltage, and under the action of the zero-sequence voltage, the capacitance current of each phase to ground changes. For the fault line, a fault current i will flow before the fault point f. f Therefore, the change of fault phase current is not only the change of capacitance current, but also the fault current. The sudden change of three-phase current of the fault line non-fault phase and the sound line is the change of capacitance current to ground. However, the fault current i f It will be affected by the compensation of arc suppression coil. Therefore, the current sudden change at the moment of fault transient should be selected for calculation.

[0048] Based on the above analysis, the three-phase current mutation on the same line is the ground capacitance current, with equal amplitude and consistent waveform. However, before the fault point of the fault line, only the two healthy phases have the same sudden current. The sudden current of the fault phase also includes the fault current, so it does not have the above characteristics.

[0049] The characteristic calculation uses sampling data from two cycles before and after the fault. The three-phase current sampling data is digitally filtered, with a filter band selected above 150 Hz. After filtering, the load current in the three-phase current is removed, leaving only the high-frequency component generated by the ground fault. The remaining high-frequency component energy is calculated using the following formula:

[0050]

[0051] where i A (i) B (i) C (i) is the sampling point data after three-phase current filtering.

[0052] The E calculated above A 、E B 、E C . Select the maximum and minimum values, and make a ratio between the maximum and minimum values. The ratio K e If ≥2.5, it is an internal fault, otherwise it is an external fault.

[0053] Step 2:

[0054] The above three features can all be used to judge single-phase grounding faults, but different features have different applicability in different grounding scenarios. For stable grounding with medium and high resistance, the zero-sequence impedance cosine feature is more reliable. For unstable grounding and arc grounding, the transient process is more obvious, and the zero-sequence energy integral feature is more reliable. For lines with large system current capacity or lines with many outgoing lines, the fault phase current has obvious mutations, and the three-phase current high-frequency energy feature is more reliable. For other fault scenarios not covered, the more adaptable zero-sequence energy integral judgment result can be selected. Therefore, based on the calculation and analysis of the characteristics after the fault, the features can be adaptively selected for fault judgment. The specific method is as follows:

[0055] S2.1 If the fault phase voltage U p If the ratio of the zero-sequence current I0 to the post-fault current is greater than 3000, it is considered to be a medium-high resistance ground fault, and the zero-sequence impedance cosine characteristic judgment result in step S1.2 is used.

[0056] If the transient zero-sequence current after the fault in step S2.2 is greater than or equal to 10A, it is considered that the current mutation is obvious, and the three-phase high-frequency energy judgment result in step S1.4 is selected.

[0057] S2.3 In other cases, select the zero-sequence energy integral judgment result in step S1.3.

[0058] Step 3:

[0059] For single-phase ground faults on different lines, the magnitude of the zero-sequence voltage and current after the fault is affected by the grounding resistance, system capacitance and current, and arc suppression coil compensation. Even on the same line, modifications can affect these three parameters, causing changes in the zero-sequence voltage and current. Therefore, the startup settings of the single-phase ground fault detection algorithm must be continuously adjusted based on the line conditions to improve the fault detection rate.

[0060] S3.1 First record the zero-sequence current I when the maximum value of the zero-sequence voltage (3U0) is greater than 17kV and the fault phase voltage is less than or equal to 200V. max , this value is consistent with the historical record of I max For comparison, the maximum value is selected to consider the fault current I when the line is metallically grounded. 0n , the zero sequence voltage at this time is U 0n .

[0061] S3.2 Select appropriate transition resistor R f , R fThe choice of transition resistor depends on the actual application. For example, a higher resistance value, such as 10kΩ, can be selected for lines used to prevent wildfires in forests and grasslands. For general overhead lines, 3kΩ-5kΩ can be selected. The choice of transition resistor varies depending on local conditions, and grid management personnel should make the selection based on the actual power supply requirements and operating experience of the line.

[0062] S3.3 Record the fault phase voltage U before the fault p , and estimate the corresponding transition resistance R f The zero sequence current I f , the formula is as follows:

[0063]

[0064] S3.4 Calculate the zero-sequence voltage U0 under the transition resistance corresponding to the zero-sequence voltage using the following formula and multiply it by the coefficient k. The value of k takes into account calculation errors and other factors that make the zero-sequence voltage pickup value smaller than the actual zero-sequence voltage at the time of the fault. k is generally set to 0.8 or less. After obtaining the new zero-sequence voltage pickup value, modify U0zd in S1.1.

[0065] U 0zd =kU 0n I f / I 0n

[0066] Example 2, reference Figure 2 , which is the second embodiment of the present invention, provides an intelligent fusion method for multi-scenario fault analysis and judgment in a 10kV distribution network. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0067] Use PSCAD to build the topology diagram shown below. Figure 2 As shown, there are four outgoing lines with different lengths. Centralized parameters are used to simulate different line lengths and types. The fault is set on line 1. The fault types are transition resistance 10Ω, transition resistance 5000Ω, transition resistance 10000Ω, unstable grounding (slight arcing), and severe arcing grounding.

[0068] In a neutral point ungrounded system, the total capacitive current is 4.699 A. Through the arc suppression coil system at the neutral point, the total capacitive current is 99.835 A. The overcompensation is set to 10% and the damping rate is 0.05.

[0069] The initial zero-sequence voltage starting value of the algorithm is 2500V. The waveform data of measurement point 1# (internal fault) is selected for analysis. The results are shown in Table 1.

[0070] Table 1 Experimental data analysis table

[0071]

[0072] Table 1 shows the applicability of the three algorithms:

[0073] 1) Zero-sequence impedance cosine may misjudge a grounding event with severe arcing, but can accurately judge a grounding event with medium or high resistance and stability.

[0074] 2) When the fault zero-sequence current is large, the high-frequency energy ratio of the three-phase current can be accurately judged.

[0075] 3) When the fault occurs in unstable grounding or severe arc grounding, the zero-sequence energy integral can be used to accurately judge the fault.

[0076] In both grounding systems, the zero-sequence voltage does not meet the pickup value. The zero-sequence voltage pickup value of a 10000Ω grounding fault can be estimated based on the zero-sequence current characteristics of a metallic fault, that is, a 10Ω grounding fault.

[0077] The U0zd of the ungrounded system is 2388V, which is sufficient for fault starting. The U0zd of the arc suppression coil system is 501V, which is sufficient for fault starting.

[0078] Example 3 is the third embodiment of the present invention, which differs from the first two embodiments in that:

[0079] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0080] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0081] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0082] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, it can be implemented using a combination of any of the following technologies known in the art: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0083] Example 4, the fourth embodiment of the present invention, provides a 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion system, including:

[0084] Start the judgment module to collect the three-phase voltage, three-phase current, zero-sequence voltage and zero-sequence current data of the distribution line;

[0085] a feature extraction module, configured to determine whether a start-up condition is satisfied based on a change in the zero-sequence voltage, and to perform a feature extraction step if the condition is satisfied;

[0086] a feature selection module configured to extract feature data related to the fault, the feature data including features reflecting the phase relationship between the voltage and current, features reflecting energy characteristics, and features reflecting the current-energy ratio; and determine features for fault diagnosis from the feature data according to preset feature selection rules;

[0087] a fault judgment module, configured to judge whether the fault is located within the monitoring section based on the features used for fault judgment;

[0088] The parameter updating module is used to update the starting parameters used for subsequent judgment based on the voltage and current data during the fault period.

[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent fusion method for multi-scenario fault analysis and judgment in a 10kV distribution network, characterized by: include, Collect three-phase voltage, three-phase current, zero-sequence voltage and zero-sequence current data of distribution lines; determining whether a start-up condition is satisfied based on the change of the zero-sequence voltage, and executing a feature extraction step if the condition is satisfied; Extracting characteristic data related to the fault, the characteristic data including a characteristic reflecting the phase relationship between the voltage and the current, a characteristic reflecting the energy characteristic, and a characteristic reflecting the current-energy ratio; Determining features for fault diagnosis from the feature data according to preset feature selection rules; Based on the features used for fault judgment, determining whether the fault is located within the monitoring section; Based on the voltage and current data during the fault period, startup parameters used for subsequent judgment are updated.

2. The intelligent fusion method for multi-scenario fault analysis and judgment of a 10kV distribution network according to claim 1 is characterized by: The characteristic reflecting the phase relationship between the voltage and current includes an impedance phase characteristic calculated based on the phase difference between the zero-sequence voltage and the zero-sequence current, and the impedance phase characteristic is used to indicate whether the phase difference between the zero-sequence voltage and the zero-sequence current is within a preset quadrant range.

3. The intelligent fusion method for multi-scenario fault analysis and judgment of a 10kV distribution network according to claim 2 is characterized by: The quadrant range includes a phase range in which the zero-sequence voltage leads the zero-sequence current by more than 90 degrees, and the impedance phase characteristic is determined by calculating the cosine value of the phase difference in real time.

4. The intelligent fusion method for multi-scenario fault analysis and judgment in a 10kV distribution network according to claim 3 is characterized by: The feature reflecting the energy characteristic includes an energy integral value obtained by integrating the point-by-point product of the zero-sequence voltage and the zero-sequence current within a preset time window after the fault occurs.

5. The intelligent fusion method for multi-scenario fault analysis and judgment of a 10kV distribution network according to claim 4 is characterized by: The energy integral value is used to determine the polarity relationship between the zero-sequence voltage and the zero-sequence current, so as to distinguish a fault line from a sound line.

6. The intelligent fusion method for multi-scenario fault analysis and judgment in a 10kV distribution network according to claim 5, characterized in that: The characteristics reflecting the current energy ratio include filtering the three-phase current data within two cycles before and after the fault occurs, eliminating the frequency components below 150Hz, calculating the energy of each phase current after filtering, and determining the current energy ratio by the ratio of the maximum value to the minimum value.

7. The intelligent fusion method for multi-scenario fault analysis and judgment of a 10kV distribution network according to claim 6 is characterized by: When the current-energy ratio is greater than or equal to a preset threshold, it is determined that the fault is located within the monitoring section.

8. A 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion system, applying a 10kV distribution network multi-scenario fault analysis and judgment intelligent fusion method according to any one of claims 1 to 7, characterized in that: include: Start the judgment module to collect the three-phase voltage, three-phase current, zero-sequence voltage and zero-sequence current data of the distribution line; a feature extraction module, configured to determine whether a start-up condition is satisfied based on a change in the zero-sequence voltage, and to perform a feature extraction step if the condition is satisfied; a feature selection module configured to extract feature data related to the fault, the feature data including features reflecting the phase relationship between the voltage and current, features reflecting energy characteristics, and features reflecting the current-energy ratio; and determine features for fault diagnosis from the feature data according to preset feature selection rules; a fault judgment module, configured to judge whether the fault is located within the monitoring section based on the features used for fault judgment; The parameter updating module is used to update the starting parameters used for subsequent judgment based on the voltage and current data during the fault period.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent fusion method for multi-scenario fault analysis and judgment of a 10kV distribution network described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a 10kV distribution network multi-scenario fault analysis and intelligent fusion method according to any one of claims 1 to 7 are implemented.

Images