Intelligent detection method and system for power distribution fault
By sending current traveling waves in the distribution network, calculating equipment addresses and analyzing signal waveforms, and identifying fault categories and equipment in the distribution network, the problems of fault location and identification in the existing technology are solved, and accurate fault detection and equipment identification are achieved. .
Patent Information
- Application Number
- CN202310855185.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-12
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2043-07-12
AI Technical Summary
The prior art is difficult to accurately locate fault points and identify the types of equipment that have failed in the distribution network, especially in the event of short circuit faults, and the current waveforms of different fault types are different but cannot be distinguished.
By sending the first current traveling wave and the second current traveling wave in the distribution network, calculating the device address, analyzing the mutation threshold and distortion values of the current signal waveform, identifying the mutation waveform, and combining the normal waveform to identify the fault category and equipment, determine the final fault Test results.
It realizes accurate positioning of fault points and identification of fault equipment types, ensures the accuracy of fault detection, can predict the address of fault equipment when a short-circuit fault, and identifies fault equipment categories through resistance value comparison, removes erroneous fault equipment, and filters the fault source. .
Smart Images

Figure CN116879679B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power distribution networks, and in particular to a method and system for intelligent detection of power distribution faults. Background Art
[0002] The method of fault location in the prior art is to inject an initial traveling wave signal into the line from the starting position of the line in the topological structure of the distribution network, and establish an initial traveling wave time difference analysis table based on the time when the initial traveling wave arrives at the node of the line, that is, each distribution network measurement system. On this basis, the topological relationship of the distribution network is identified through the initial traveling wave time difference relationship, and the location of the equipment in the distribution network can be determined. When a short circuit fault occurs in the equipment in the line, the traveling wave cannot pass through the line. In this case, it is impossible to locate the equipment using the initial traveling wave. Secondly, due to the different current waveforms under different fault types, the prior art detects the fault type through the mutation characteristics of the current waveform, but this method cannot identify the faulty equipment. According to the above-mentioned problems existing in the prior art, there is still a need for a solution that can smoothly locate the fault point and identify the type of equipment that has failed to ensure the accuracy of fault detection. Summary of the invention
[0003] In order to solve the above problems, the present invention provides a method and system for intelligent detection of power distribution faults, which can smoothly locate the fault point and identify the type of equipment where the fault occurs, so as to ensure the accuracy of fault detection.
[0004] In a first aspect, the present invention provides a method for intelligent detection of power distribution faults, comprising:
[0005] Acquire a sending substation and a receiving substation of a distribution network, send a first current traveling wave from the sending substation to the distribution network, and send a second current traveling wave from the receiving substation to the distribution network;
[0006] Calculating a first device address of a device in the distribution network based on the first current traveling wave, calculating a second device address of a device in the distribution network based on the second current traveling wave, and identifying a fault address of the distribution network using the first device address and the second device address;
[0007] Collecting the current signal of the fault address, constructing a signal waveform of the current signal, analyzing a mutation threshold of the signal waveform, calculating a distortion value of the signal waveform, and judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value;
[0008] When the mutation waveform exists in the signal waveform, the mutation waveform is used to identify the fault type of the distribution network, and a normal waveform other than the mutation waveform is extracted from the signal waveform, and the faulty device of the distribution network is identified using the normal waveform;
[0009] Based on the fault address, the fault type and the faulty device, a final fault detection result of the distribution network is determined.
[0010] In a possible implementation manner of the first aspect, calculating a first device address of a device in the distribution network based on the first current traveling wave includes:
[0011] The distance between every two devices when the first current traveling wave passes through the distribution network is calculated using the following formula:
[0012] G=[G 1 -G 0 ,G 2 -G 1 ,G 3 -G 2 ,…,G m -G m-1 ]
[0013] S=[G 1 ×V,(G 2 -G 1 )×V,…,(G m -G m-1 )×V]
[0014] Wherein, S represents the distance between every two devices when the first current traveling wave passes through the distribution network, G 1 represents the wave head time when the first current wave passes through the first device in the distribution network, G 2 represents the wave head time when the first current wave passes through the second device in the distribution network, G 3 represents the wave head time when the first current wave passes through the third device in the distribution network, G m-1 represents the wave head time when the first current wave passes through the distribution network to the m-1th device, G m represents the wave head time when the first current wave passes through the mth device in the distribution network, G 0 represents the wave head time of the first current traveling wave when it departs from the sending substation in the distribution network, that is, the value is 0, G represents the difference in the wave head time of every two devices, and V represents the transmission rate of the first current traveling wave;
[0015] A line image of the distribution network is collected, and based on the line angle in the line image and the distance between every two devices when the first current traveling wave passes through the distribution network, the first device address is calculated using the following formula:
[0016]
[0017]
[0018] (u,v)=((u 0 ,v 0 ) 0 ,(u 0 +S 2 cosθ,v 0 +S 2 sinθ) 1 ,......,(u 0 ′,v 0 ′) m )
[0019] Wherein, (u,v) represents the first device address, (u 0 ,v 0 ) 0 represents the address of the sending substation, (u 0 +S 2 cosθ,v 0 +S 2 sinθ) 1 Indicates the address of the first device in the distribution network, (u 0 ′,v 0 ′) m represents the address of the mth device in the distribution network, S 2 represents the distance between every two devices when the first current wave passes through the distribution network, that is, the distance from the sending substation to the first device, θ represents the line angle, K 1 represents the horizontal distance from the transmitting substation to the first device, K 3 Indicates the vertical distance from the transmitting substation to the first device.
[0020] In a possible implementation manner of the first aspect, the identifying a fault address of the distribution network by using the first device address and the second device address includes:
[0021] Extracting a connection line and a shortest line segment between the first device address and the second device address;
[0022] identifying a faulty line in the connection lines;
[0023] Based on the first angle between the fault line at the first device address and the shortest line segment, and the second angle between the fault line at the second device address and the shortest line segment, the shortest distance between the fault point in the fault line and the shortest line segment is calculated using the following formula:
[0024]
[0025]
[0026]
[0027] Wherein, h represents the shortest distance between the fault point and the shortest line segment, x 2 ,y 2 The horizontal and vertical coordinates representing the second device address, x 1 ,y 1 The horizontal and vertical coordinates of the first device address, θ 1 represents the first angle, θ 2 The second angle, l 1 indicates the distance between the first device address and the intersection of a straight line perpendicular to the shortest line segment through the fault point and the shortest line segment, l 2 represents the distance between the obtained intersection point and the second device address, represents the length of the shortest line segment between the first device address and the second device address;
[0028] Based on the shortest distance, the fault address corresponding to the fault point is calculated using the following formula:
[0029]
[0030]
[0031]
[0032]
[0033]
[0034] Wherein, (x′, y′) represents the fault address, h represents the shortest distance between the fault point and the shortest line segment, and x 2 ,y 2 The horizontal and vertical coordinates representing the second device address, x 1 ,y 1 The horizontal and vertical coordinates of the first device address, θ 1 represents the first angle, θ2 The second angle, l 1 indicates the distance between the first device address and the intersection of a straight line perpendicular to the shortest line segment through the fault point and the shortest line segment, l 2 represents the distance between the obtained intersection point and the second device address, represents the distance between the fault address and the first device address, represents the distance between the fault address and the obtained intersection point, L represents the distance between the fault address and the first device address, x 0 ,y 0 Indicates the horizontal and vertical coordinates of the obtained intersection point.
[0035] In a possible implementation manner of the first aspect, analyzing the mutation threshold of the signal waveform includes:
[0036] Get historical signal waveform;
[0037] Calculating a current mutation value of the historical signal waveform;
[0038] A minimum current mutation value is selected from the current mutation values, and the minimum current mutation value is used as the mutation threshold.
[0039] In a possible implementation manner of the first aspect, calculating the current mutation value of the historical signal waveform includes:
[0040] The current mutation value of the historical signal waveform is calculated using the following formula, including:
[0041]
[0042] Wherein, ΔI represents the current mutation value, i(t) represents the current value at the tth moment, represents the current value of the first half cycle from the tth moment, i(tn) represents the current value of the first half cycle from the tth moment, and n represents the total duration of each cycle.
[0043] In a possible implementation manner of the first aspect, the determining whether there is a sudden change waveform in the signal waveform based on the sudden change threshold and the distortion value includes:
[0044] When the distortion value is less than the mutation threshold, determining that the mutation waveform does not exist in the signal waveform;
[0045] When the distortion value is not less than the mutation threshold, it is determined that the mutation waveform exists in the signal waveform.
[0046] In a possible implementation manner of the first aspect, the identifying a fault type of the distribution network by using the mutation waveform includes:
[0047] The waveform weight of the sudden change waveform is calculated using the following formula:
[0048]
[0049] in, represents the waveform weight of the mutation waveform, f represents the activation function, N represents the normalization process, ε t represents the distortion value at the tth moment in the mutation waveform, t 0 The time period of ~T is the time period length of a unit cycle in the mutation waveform;
[0050] Based on the waveform weight and the sudden change waveform, the fault category probability of the distribution network is calculated using the following formula:
[0051]
[0052]
[0053] Where P represents the probability of the fault category, w 1 represents the waveform weight of the sudden waveform. Since the sudden waveform contains multiple unit cycles, w 1 is composed of multiple unit cycles The vector formed, p I represents the fault category probability predicted based on the current value contained in the signal waveform, p U represents the fault category probability predicted based on the voltage signal of the fault address, w o represents the weight of the hidden layer, h j represents the output data of the hidden layer receiving the signal waveform, σ represents the activation function, w 2 represents the waveform weight of the normal waveform in the signal waveform except the mutation waveform, j represents the time sequence number of the mutation waveform, and 0 to T′ represents the total duration of the mutation waveform;
[0054] A fault category corresponding to a maximum fault category probability among the fault category probabilities is queried, and the fault category corresponding to the maximum fault category probability is used as the fault category of the distribution network.
[0055] In a possible implementation manner of the first aspect, the identifying a faulty device of the distribution network by using the normal waveform includes:
[0056] Extracting a current value of the distribution network from the normal waveform;
[0057] Based on the current value, the resistance value of the equipment in the distribution network is calculated using the following formula:
[0058]
[0059] Wherein, R represents the resistance value, U represents the voltage value extracted from the voltage waveform of the fault address, and I represents the current value;
[0060] When the resistance value is consistent with the resistance value in the preset device-resistance table, the preset device-resistance table is queried for a faulty device corresponding to the resistance value.
[0061] In a possible implementation manner of the first aspect, determining a final fault detection result of the distribution network based on the fault address, the fault type, and the faulty device includes:
[0062] Selecting a target faulty device that meets the fault category from the faulty devices;
[0063] Identify whether the device at the fault address matches the target fault device;
[0064] When the device at the fault address matches the target fault device, taking the fault address as the target fault address;
[0065] The fault type, the target fault device and the target fault address are used as the final fault detection result.
[0066] In a second aspect, the present invention provides a power distribution fault intelligent detection system, the system comprising:
[0067] A current sending module, used for acquiring a sending substation and a receiving substation of a distribution network, sending a first current traveling wave from the sending substation to the distribution network, and sending a second current traveling wave from the receiving substation to the distribution network;
[0068] an address identification module, configured to calculate a first device address of a device in the distribution network based on the first current traveling wave, calculate a second device address of a device in the distribution network based on the second current traveling wave, and identify a fault address of the distribution network using the first device address and the second device address;
[0069] a mutation discrimination module, used for collecting the current signal of the fault address, constructing a signal waveform of the current signal, analyzing a mutation threshold of the signal waveform, calculating a distortion value of the signal waveform, and judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value;
[0070] A device identification module, used for identifying the fault type of the distribution network by using the mutation waveform when the mutation waveform exists in the signal waveform, extracting a normal waveform other than the mutation waveform from the signal waveform, and identifying the faulty device of the distribution network by using the normal waveform;
[0071] The result determination module is used to determine the final fault detection result of the distribution network based on the fault address, the fault type and the faulty device.
[0072] Compared with the prior art, the technical principle and beneficial effects of this solution are:
[0073] The embodiment of the present invention calculates the first device address of the device in the distribution network based on the first current wave, so as to determine the address of the device in the distribution network that has not suffered a short-circuit fault. Furthermore, the embodiment of the present invention calculates the second device address of the device in the distribution network based on the second current wave, so as to be used for, when a short-circuit fault occurs in the distribution network and causes the first current wave to be unable to continue to pass forward, starting from the destination of the second current wave to pass in the reverse direction through the line that the first current wave cannot pass. Furthermore, the embodiment of the present invention identifies the fault address of the distribution network by using the first device address and the second device address, so as to predict the address of the device that has suffered a short-circuit fault based on the detected address of the device that has not suffered a short-circuit fault. The embodiment of the invention constructs the signal waveform of the current signal to detect the fault type based on the abnormal change of the signal waveform. Furthermore, the embodiment of the invention identifies the faulty equipment of the distribution network by using the normal waveform to calculate the resistance value of the location where the fault occurs based on the current value and the voltage value, so that the resistance value can be compared with the factory resistance value of each device, and finally the type of equipment where the fault occurs can be identified. The embodiment of the invention uses the fault address, the fault type and the faulty equipment to further remove the erroneous faulty equipment based on the resistance value when redundant erroneous faulty equipment is identified, and screens the fault points when the fault spreads and causes some fault points that are not the fault source to also fail. Therefore, the intelligent detection method and system for power distribution faults proposed in the embodiment of the invention can smoothly locate the fault point and identify the type of equipment where the fault occurs, so as to ensure the accuracy of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0074] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0075] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0076] Figure 1 A schematic diagram of a flow chart of a method for intelligent detection of power distribution faults provided by an embodiment of the present invention;
[0077] Figure 2 In one embodiment of the present invention Figure 1 A schematic diagram of a first device address of a power distribution fault intelligent detection method provided;
[0078] Figure 3 In one embodiment of the present invention Figure 1 A schematic diagram of a fault address of a power distribution fault intelligent detection method is provided;
[0079] Figure 4 A schematic diagram of a module of an intelligent detection system for power distribution faults provided by an embodiment of the present invention;
[0080] Figure 5 A schematic diagram of the internal structure of an electronic device for implementing an intelligent detection method for power distribution faults provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0081] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0082] An embodiment of the present invention provides an intelligent detection method for power distribution faults, and the execution subject of the intelligent detection method for power distribution faults includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the intelligent detection method for power distribution faults can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.
[0083] See also Figure 1 FIG. 1 is a flow chart of a method for intelligent detection of power distribution faults provided by an embodiment of the present invention. Figure 1The intelligent detection method for power distribution faults described in the invention includes:
[0084] S1. Acquire a sending substation and a receiving substation of a distribution network, send a first current traveling wave from the sending substation to the distribution network, and send a second current traveling wave from the receiving substation to the distribution network.
[0085] In an embodiment of the present invention, the distribution network refers to a power grid that receives electric energy from a transmission network or a regional power plant, and distributes the received electric energy locally or step by step according to voltage to various types of users through distribution facilities. The distribution network is composed of overhead lines, poles and towers, distribution transformers, switchgear, reactive compensation capacitors, lightning arresters, transformer flexible cables, transformer elbow heads and other distribution equipment and ancillary facilities. It should be noted that the overall structure of the distribution network is a mesh topology structure, the overhead lines constitute the edges in the mesh topology structure, and the poles and towers, distribution transformers, switchgear, reactive compensation capacitors, lightning arresters, transformer flexible cables, transformer elbow heads and other distribution equipment constitute the nodes between the edges in the mesh topology structure.
[0086] Furthermore, the sending substation refers to a place where voltage and current are transformed and electric energy is distributed; the receiving substation refers to a place where voltage and current are transformed and electric energy is received.
[0087] It should be noted that in the process of sending the first current wave from the sending substation, passing through multiple device nodes in the distribution network, and finally arriving at the receiving substation, if a short circuit fault occurs in the mesh topology structure of the distribution network, it will cause the line to be blocked. Therefore, when the first current wave sent from the sending substation encounters the location of the short circuit fault, it cannot continue to communicate forward.
[0088] Therefore, the embodiment of the present invention sends a second current wave from the receiving substation to the distribution network, so as to use the second current wave to probe the position of the node device in the line where the first current wave cannot continue to communicate after encountering a short circuit fault.
[0089] Among them, the transmission directions of the first current traveling wave and the second current traveling wave are opposite, but the sizes are the same. The current traveling wave is relative to the current standing wave. The current standing wave can be regarded as a stationary wave that does not move forward and the phase does not change, while the traveling wave is a moving wave with a linearly lagging phase. The current traveling wave refers to a transmission state of a plane wave on a transmission line. In the transmission line, the current traveling wave is propagated in the form of an electromagnetic wave.
[0090] S2. Calculate a first device address of a device in the distribution network based on the first current wave, calculate a second device address of a device in the distribution network based on the second current wave, and use the first device address and the second device address to identify a fault address of the distribution network.
[0091] The embodiment of the present invention calculates the first device address of the device in the distribution network based on the first current traveling wave, so as to determine the address of the device in the distribution network that has not suffered a short circuit fault.
[0092] In one embodiment of the present invention, the calculating the first device address of the device in the distribution network based on the first current traveling wave includes: calculating the distance between every two devices when the first current traveling wave passes through the distribution network using the following formula:
[0093] G=[G 1 -G 0 ,G 2 -G 1 ,G 3 -G 2 ,…,G m -G m-1 ]
[0094] S=[G 1 ×V,(G 2 -G 1 )×V,…,(G m -G m-1 )×V]
[0095] Wherein, S represents the distance between every two devices when the first current traveling wave passes through the distribution network, G 1 represents the wave head time when the first current wave passes through the first device in the distribution network, G 2 represents the wave head time when the first current wave passes through the second device in the distribution network, G 3 represents the wave head time when the first current wave passes through the third device in the distribution network, G m-1 represents the wave head time when the first current wave passes through the distribution network to the m-1th device, G m represents the wave head time when the first current wave passes through the mth device in the distribution network, G 0 represents the wave head time of the first current traveling wave when it departs from the sending substation in the distribution network, that is, the value is 0, G represents the difference in the wave head time of every two devices, and V represents the transmission rate of the first current traveling wave;
[0096] A line image of the distribution network is collected, and based on the line angle in the line image and the distance between every two devices when the first current traveling wave passes through the distribution network, the first device address is calculated using the following formula:
[0097]
[0098]
[0099] (u,v)=((u 0 ,v 0 ) 0 ,(u 0 +S 2 cosθ,v 0 +S 2 sinθ) 1 ,......,(u 0 ′,v 0 ′) m )
[0100] Wherein, (u,v) represents the first device address, (u 0 ,v 0 ) 0 represents the address of the sending substation, (u 0 +S 2 cosθ,v 0 +S 2 sinθ) 1 Indicates the address of the first device in the distribution network, (u 0 ′,v 0 ′) m represents the address of the mth device in the distribution network, S 2 represents the distance between every two devices when the first current wave passes through the distribution network, that is, the distance from the sending substation to the first device, θ represents the line angle, K 1 represents the horizontal distance from the transmitting substation to the first device, K 3 Indicates the vertical distance from the transmitting substation to the first device.
[0101] See also Figure 2 As shown, an embodiment of the present invention Figure 1 A schematic diagram of a first device address of a power distribution fault intelligent detection method is provided.
[0102] The wave front time refers to the time it takes for the current to rise to its amplitude.
[0103] Furthermore, an embodiment of the present invention calculates a second device address of a device in the distribution network based on the second current wave, so that when a short circuit occurs in the distribution network and the first current wave cannot continue to pass forward, the second current wave destination starts to pass in the opposite direction through the line that the first current wave cannot pass.
[0104] In one embodiment of the present invention, the process of calculating the second device address of the device in the distribution network based on the second current wave is similar to the principle of calculating the first device address of the device in the distribution network based on the first current wave, and will not be further elaborated here.
[0105] Furthermore, the embodiment of the present invention identifies the fault address of the distribution network by using the first device address and the second device address, so as to predict the address of the device having a short-circuit fault based on the detected address of the device not having a short-circuit fault.
[0106] In one embodiment of the present invention, the use of the first device address and the second device address to identify the fault address of the distribution network includes: extracting the connection line and the shortest line segment between the first device address and the second device address; identifying the fault line in the connection line; based on the first angle between the fault line at the first device address and the shortest line segment, and the second angle between the fault line at the second device address and the shortest line segment, using the following formula to calculate the shortest distance between the fault point in the fault line and the shortest line segment:
[0107]
[0108]
[0109]
[0110] Wherein, h represents the shortest distance between the fault point and the shortest line segment, x 2 ,y 2 The horizontal and vertical coordinates representing the second device address, x 1 ,y 1 The horizontal and vertical coordinates of the first device address, θ 1 represents the first angle, θ 2 The second angle, l 1 indicates the distance between the first device address and the intersection of a straight line perpendicular to the shortest line segment through the fault point and the shortest line segment, l 2 represents the distance between the obtained intersection point and the second device address, represents the length of the shortest line segment between the first device address and the second device address;
[0111] Based on the shortest distance, the fault address corresponding to the fault point is calculated using the following formula:
[0112]
[0113]
[0114]
[0115]
[0116]
[0117] Wherein, (x′, y′) represents the fault address, h represents the shortest distance between the fault point and the shortest line segment, and x 2 ,y 2 The horizontal and vertical coordinates representing the second device address, x 1 ,y 1 The horizontal and vertical coordinates of the first device address, θ 1 represents the first angle, θ 2 The second angle, l 1 indicates the distance between the first device address and the intersection of a straight line perpendicular to the shortest line segment through the fault point and the shortest line segment, l 2 represents the distance between the obtained intersection point and the second device address, represents the distance between the fault address and the first device address, represents the distance between the fault address and the obtained intersection point, L represents the distance between the fault address and the first device address, x 0 ,y 0 Indicates the horizontal and vertical coordinates of the obtained intersection point.
[0118] See also Figure 3 As shown, an embodiment of the present invention Figure 1 A schematic diagram of a fault address of an intelligent detection method for power distribution faults is provided.
[0119] S3. Collect the current signal of the fault address, construct a signal waveform of the current signal, analyze the mutation threshold of the signal waveform, calculate the distortion value of the signal waveform, and determine whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value.
[0120] The embodiment of the present invention constructs a signal waveform of the current signal to detect the fault type based on the abnormal change of the signal waveform.
[0121] In one embodiment of the present invention, the analysis of the mutation threshold of the signal waveform includes: obtaining a historical signal waveform; calculating a current mutation value of the historical signal waveform; selecting a minimum current mutation value from the current mutation values, and using the minimum current mutation value as the mutation threshold.
[0122] The historical signal waveform refers to the signal waveform generated in historical time.
[0123] In another embodiment of the present invention, the current mutation value of the historical signal waveform is calculated using the following formula, including:
[0124]
[0125] Wherein, ΔI represents the current mutation value, i(t) represents the current value at the tth moment, represents the current value of the first half cycle from the tth moment, i(tn) represents the current value of the first half cycle from the tth moment, and n represents the total duration of each cycle.
[0126] In one embodiment of the present invention, the principle of calculating the distortion value of the signal waveform is similar to the principle of calculating the current mutation value of the historical signal waveform, which will not be further elaborated herein.
[0127] In one embodiment of the present invention, judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value includes: when the distortion value is less than the mutation threshold, judging that there is no mutation waveform in the signal waveform; when the distortion value is not less than the mutation threshold, judging that there is a mutation waveform in the signal waveform.
[0128] S4. When the mutation waveform exists in the signal waveform, the mutation waveform is used to identify the fault type of the distribution network, and a normal waveform other than the mutation waveform is extracted from the signal waveform, and the faulty device of the distribution network is identified using the normal waveform.
[0129] In the embodiment of the present invention, the fault categories include lightning strikes causing the arrester body to burst and break down, the upper lead of the arrester touching the crossarm, grounding faults causing the flexible cable of the transformer to burn out, grounding faults causing the insulation breakdown of the transformer elbow head, overhead line-tree line conflicts, etc. It should be noted that the waveform mutations of the current signal under different fault categories are different. Therefore, this principle can be used to train the long short-term memory neural network, so as to use the trained long short-term memory neural network to predict the corresponding fault category according to the waveform of the input current signal.
[0130] In one embodiment of the present invention, the identifying the fault type of the distribution network by using the mutation waveform includes: calculating the waveform weight of the mutation waveform by using the following formula:
[0131]
[0132] in, represents the waveform weight of the mutation waveform, f represents the activation function, N represents the normalization process, ε t represents the distortion value at the tth moment in the mutation waveform, t 0 The time period of ~T is the time period length of a unit cycle in the mutation waveform;
[0133] Based on the waveform weight and the sudden change waveform, the fault category probability of the distribution network is calculated using the following formula:
[0134]
[0135]
[0136] Where P represents the probability of the fault category, w 1 represents the waveform weight of the sudden waveform. Since the sudden waveform contains multiple unit cycles, w 1 is composed of multiple unit cycles The vector formed, p I represents the fault category probability predicted based on the current value contained in the signal waveform, p U represents the fault category probability predicted based on the voltage signal of the fault address, w o represents the weight of the hidden layer, h j represents the output data of the hidden layer receiving the signal waveform, σ represents the activation function, w 2 represents the waveform weight of the normal waveform in the signal waveform except the mutation waveform, j represents the time sequence number of the mutation waveform, and 0 to T′ represents the total duration of the mutation waveform;
[0137] A fault category corresponding to a maximum fault category probability among the fault category probabilities is queried, and the fault category corresponding to the maximum fault category probability is used as the fault category of the distribution network.
[0138] It should be noted that the calculation process of the fault category probability predicted based on the voltage signal of the fault address is the same as the above-mentioned p I The calculation process is similar.
[0139] Furthermore, the embodiment of the present invention utilizes the normal waveform to identify the faulty equipment in the distribution network, so as to calculate the resistance value of the location where the fault occurs based on the current value and the voltage value, so that the resistance value can be compared with the factory resistance value of each equipment, and finally the type of the faulty equipment can be identified.
[0140] In one embodiment of the present invention, the method of identifying a faulty device in the distribution network using the normal waveform includes: extracting a current value of the distribution network from the normal waveform; and calculating a resistance value of a device in the distribution network based on the current value using the following formula:
[0141]
[0142] Wherein, R represents the resistance value, U represents the voltage value extracted from the voltage waveform of the fault address, and I represents the current value;
[0143] When the resistance value is consistent with the resistance value in the preset device-resistance table, the preset device-resistance table is queried for a faulty device corresponding to the resistance value.
[0144] S5. Determine a final fault detection result of the distribution network based on the fault address, the fault type and the faulty device.
[0145] The embodiment of the present invention is based on the fault address, the fault category and the faulty device, so that when redundant erroneous faulty devices are identified based on the resistance value, the fault category is used to further remove the erroneous faulty devices, and when the fault spreads and causes some fault points that are not the fault source to also fail, the fault points are screened.
[0146] In one embodiment of the present invention, determining the final fault detection result of the distribution network based on the fault address, the fault category and the fault device includes: selecting a target fault device that meets the fault category from the fault devices; identifying whether the device at the fault address meets the target fault device; when the device at the fault address meets the target fault device, using the fault address as the target fault address; using the fault category, the target fault device and the target fault address as the final fault detection result.
[0147] Optionally, the process of selecting a target fault device that meets the fault category from the faulty devices is as follows: when the fault category is a ground fault causing the transformer flexible cable to burn, the faulty device should be the transformer flexible cable, and the device that does not meet the transformer flexible cable should be deleted, and the device that meets the transformer flexible cable is used as the target fault device; the process of identifying whether the device at the fault address meets the target fault device is as follows: when the devices at the fault address are A and B, but the target fault device is C, it means that this fault address is not the source of the fault. This is because when a fault occurs somewhere in the line, it will cause faults in other places connected to this place. Since maintenance at this place will cause other places connected to this place to return to normal synchronously, only the fault here needs to be paid attention to.
[0148] It can be seen that the embodiment of the present invention calculates the first device address of the device in the distribution network based on the first current wave, so as to determine the address of the device in the distribution network that has not suffered a short-circuit fault. Further, the embodiment of the present invention calculates the second device address of the device in the distribution network based on the second current wave, so as to be used for, when a short-circuit fault occurs in the distribution network and causes the first current wave to be unable to continue to pass forward, starting from the destination of the second current wave to pass in the opposite direction through the line that the first current wave cannot pass. Further, the embodiment of the present invention identifies the fault address of the distribution network by using the first device address and the second device address, so as to predict the address of the device that has suffered a short-circuit fault based on the detected address of the device that has not suffered a short-circuit fault. , the embodiment of the present invention constructs the signal waveform of the current signal to detect the fault type based on the abnormal change of the signal waveform. Furthermore, the embodiment of the present invention identifies the faulty equipment of the distribution network by using the normal waveform to calculate the resistance value of the location where the fault occurs based on the current value and the voltage value, so that the resistance value can be compared with the factory resistance value of each device, and finally the type of equipment where the fault occurs can be identified. The embodiment of the present invention is based on the fault address, the fault type and the faulty equipment, so that when redundant faulty equipment is identified based on the resistance value, the fault type can be used to further remove the faulty equipment, and when the fault spreads and causes some fault points that are not the fault source to also fail, the fault points can be screened. Therefore, the intelligent detection method for power distribution faults proposed in the embodiment of the present invention can smoothly locate the fault point and identify the type of equipment where the fault occurs, so as to ensure the accuracy of fault detection.
[0149] like Figure 4 The figure shows a functional module diagram of the intelligent detection system for power distribution faults of the present invention.
[0150] The power distribution fault intelligent detection system 400 of the present invention can be installed in an electronic device. According to the functions to be implemented, the power distribution fault intelligent detection system can include a current sending module 401, an address identification module 402, a mutation discrimination module 403, a device identification module 404 and a result determination module 405. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0151] In the embodiment of the present invention, the functions of each module / unit are as follows:
[0152] The current sending module 401 is used to obtain a sending substation and a receiving substation of the distribution network, send a first current traveling wave from the sending substation to the distribution network, and send a second current traveling wave from the receiving substation to the distribution network;
[0153] The address identification module 402 is used to calculate a first device address of a device in the distribution network based on the first current traveling wave, calculate a second device address of the device in the distribution network based on the second current traveling wave, and identify a fault address of the distribution network using the first device address and the second device address;
[0154] The mutation discrimination module 403 is used to collect the current signal of the fault address, construct a signal waveform of the current signal, analyze the mutation threshold of the signal waveform, calculate the distortion value of the signal waveform, and judge whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value;
[0155] The device identification module 404 is used to identify the fault type of the distribution network by using the mutation waveform when the mutation waveform exists in the signal waveform, and extract the normal waveform except the mutation waveform from the signal waveform, and identify the faulty device of the distribution network by using the normal waveform;
[0156] The result determination module 405 is used to determine the final fault detection result of the distribution network based on the fault address, the fault type and the faulty device.
[0157] In detail, each module in the power distribution fault intelligent detection system 400 in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The same technical means are used as the intelligent detection method for power distribution faults described in the invention and can produce the same technical effects, so they will not be repeated here.
[0158] like Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device for realizing the intelligent detection method for power distribution faults according to the present invention.
[0159] The electronic device may include a processor 50, a memory 51, a communication bus 52 and a communication interface 53, and may also include a computer program stored in the memory 51 and executable on the processor 50, such as a power distribution fault intelligent detection program.
[0160] In some embodiments, the processor 50 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 50 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 51 (for example, executing a power distribution fault intelligent detection program, etc.), and calls data stored in the memory 51 to execute various functions of the electronic device and process data.
[0161] The memory 51 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 51 may be an internal storage unit of an electronic device in some embodiments, such as a mobile hard disk of the electronic device. The memory 51 may also be an external storage device of an electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 51 may also include both an internal storage unit of the electronic device and an external storage device. The memory 51 may not only be used to store application software and various types of data installed in the electronic device, such as the code of the database configuration connection program, but also be used to temporarily store data that has been output or is to be output.
[0162] The communication bus 52 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 51 and at least one processor 50, etc.
[0163] The communication interface 53 is used for communication between the above-mentioned electronic device 5 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.
[0164] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0165] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 50 through a power management system, so that functions such as charging management, discharging management, and power consumption management are implemented through the power management device. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described in detail here.
[0166] It should be understood that the embodiment is for illustrative purposes only and the scope of the patent invention is not limited to this structure.
[0167] The database configuration connection program stored in the memory 51 in the electronic device is a combination of multiple computer programs. When running in the processor 50, it can achieve:
[0168] Acquire a sending substation and a receiving substation of a distribution network, send a first current traveling wave from the sending substation to the distribution network, and send a second current traveling wave from the receiving substation to the distribution network;
[0169] Calculating a first device address of a device in the distribution network based on the first current traveling wave, calculating a second device address of a device in the distribution network based on the second current traveling wave, and identifying a fault address of the distribution network using the first device address and the second device address;
[0170] Collecting the current signal of the fault address, constructing a signal waveform of the current signal, analyzing a mutation threshold of the signal waveform, calculating a distortion value of the signal waveform, and judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value;
[0171] When the mutation waveform exists in the signal waveform, the mutation waveform is used to identify the fault type of the distribution network, and a normal waveform other than the mutation waveform is extracted from the signal waveform, and the faulty device of the distribution network is identified using the normal waveform;
[0172] Based on the fault address, the fault type and the faulty device, a final fault detection result of the distribution network is determined.
[0173] Specifically, the specific implementation method of the processor 50 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.
[0174] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).
[0175] The present invention further provides a storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:
[0176] Acquire a sending substation and a receiving substation of a distribution network, send a first current traveling wave from the sending substation to the distribution network, and send a second current traveling wave from the receiving substation to the distribution network;
[0177] Calculating a first device address of a device in the distribution network based on the first current traveling wave, calculating a second device address of a device in the distribution network based on the second current traveling wave, and identifying a fault address of the distribution network using the first device address and the second device address;
[0178] Collecting the current signal of the fault address, constructing a signal waveform of the current signal, analyzing a mutation threshold of the signal waveform, calculating a distortion value of the signal waveform, and judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value;
[0179] When the mutation waveform exists in the signal waveform, the mutation waveform is used to identify the fault type of the distribution network, and a normal waveform other than the mutation waveform is extracted from the signal waveform, and the faulty device of the distribution network is identified using the normal waveform;
[0180] Based on the fault address, the fault type and the faulty device, a final fault detection result of the distribution network is determined.
[0181] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, systems and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.
[0182] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0183] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0184] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0185] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.
[0186] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0187] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A method for intelligent detection of power distribution faults, characterized in that: The method comprises: Acquire a sending substation and a receiving substation of a distribution network, send a first current traveling wave from the sending substation to the distribution network, and send a second current traveling wave from the receiving substation to the distribution network; Calculating a first device address of a device in the distribution network based on the first current traveling wave includes: The distance between every two devices when the first current traveling wave passes through the distribution network is calculated using the following formula: G=[G1-G0,G2-G1,G3-G2,…,G m -G m-1 ] S=[G1×V,(G2-G1)×V,…,(G m -G m-1 )×V] Wherein, S represents the distance between every two devices when the first current wave passes through the distribution network, G1 represents the wave head time when the first current wave passes through the distribution network to the first device, G2 represents the wave head time when the first current wave passes through the distribution network to the second device, G3 represents the wave head time when the first current wave passes through the distribution network to the third device, G m-1 represents the wave head time when the first current wave passes through the distribution network to the m-1th device, G m represents the wave head time when the first current wave passes through the mth device in the distribution network, G0 represents the wave head time when the first current wave starts from the sending substation in the distribution network, that is, the value is 0, G represents the difference in the wave head time of every two devices, and V represents the transmission rate of the first current wave; A line image of the distribution network is collected, and based on the line angle in the line image and the distance between every two devices when the first current traveling wave passes through the distribution network, the first device address is calculated using the following formula: (u, v)=((u0, v0)0, (u0+S2cosθ, v0+S2sinθ)1,......, (u0′, v0′) m ) Wherein, (u, v) represents the first device address, (u0, V0)0 represents the address of the sending substation, (u0+S2cosθ, v0+S2sinθ)1 represents the address of the first device in the distribution network, (u0′, v0′) m represents the address of the mth device in the distribution network, S2 represents the distance between every two devices when the first current wave passes through the distribution network, that is, the distance from the sending substation to the first device, θ represents the line angle, K1 represents the horizontal distance from the sending substation to the first device, and K3 represents the vertical distance from the sending substation to the first device; Calculating a second device address of a device in the distribution network based on the second current traveling wave, and identifying a fault address of the distribution network using the first device address and the second device address; Collecting the current signal of the fault address, constructing a signal waveform of the current signal, analyzing a mutation threshold of the signal waveform, calculating a distortion value of the signal waveform, and judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value; When the mutation waveform exists in the signal waveform, the mutation waveform is used to identify the fault type of the distribution network, and a normal waveform other than the mutation waveform is extracted from the signal waveform, and the faulty device of the distribution network is identified using the normal waveform; Based on the fault address, the fault type and the faulty device, a final fault detection result of the distribution network is determined.
2. The method according to claim 1, characterized in that The identifying a fault address of the distribution network by using the first device address and the second device address includes: Extracting a connection line and a shortest line segment between the first device address and the second device address; identifying a faulty line in the connection lines; Based on the first angle between the fault line at the first device address and the shortest line segment, and the second angle between the fault line at the second device address and the shortest line segment, the shortest distance between the fault point in the fault line and the shortest line segment is calculated using the following formula: Wherein, h represents the shortest distance between the fault point and the shortest line segment, x2, y2 represent the horizontal coordinate and the vertical coordinate of the second device address, x1, y1 represent the horizontal coordinate and the vertical coordinate of the first device address, θ1 represents the first angle, θ2 represents the second angle, l1 represents the distance between the first device address and the intersection point of a straight line perpendicular to the shortest line segment through the fault point, and l2 represents the distance between the second device address and the intersection point. represents the length of the shortest line segment between the first device address and the second device address; Based on the shortest distance, the fault address corresponding to the fault point is calculated using the following formula: Wherein, (x′, y′) represents the fault address, h represents the shortest distance between the fault point and the shortest line segment, x2, y2 represent the horizontal coordinate and the vertical coordinate of the second device address, x1, y1 represent the horizontal coordinate and the vertical coordinate of the first device address, θ1 represents the first angle, θ2 represents the second angle, l1 represents the distance between the first device address and the intersection point of a straight line perpendicular to the shortest line segment through the fault point, and l2 represents the distance between the second device address and the intersection point. represents the distance between the fault address and the first device address, represents the distance between the fault address and the obtained intersection point, L represents the distance between the fault address and the first device address, and x0, y0 represent the horizontal coordinate and the vertical coordinate of the obtained intersection point.
3. The method according to claim 1, characterized in that The analyzing the mutation threshold of the signal waveform includes: Get historical signal waveform; Calculating a current mutation value of the historical signal waveform; A minimum current mutation value is selected from the current mutation values, and the minimum current mutation value is used as the mutation threshold.
4. The method according to claim 3, characterized in that Calculating the current mutation value of the historical signal waveform includes: The current mutation value of the historical signal waveform is calculated using the following formula, including: Wherein, ΔI represents the current mutation value, i(t) represents the current value at the tth moment, represents the current value of the first half cycle from the tth moment, i(tn) represents the current value of the first half cycle from the tth moment, and n represents the total duration of each cycle.
5. The method according to claim 1, characterized in that The step of determining whether there is a sudden change waveform in the signal waveform based on the sudden change threshold and the distortion value includes: When the distortion value is less than the mutation threshold, determining that the mutation waveform does not exist in the signal waveform; When the distortion value is not less than the mutation threshold, it is determined that the mutation waveform exists in the signal waveform.
6. The method according to claim 1, characterized in that The method of identifying the fault type of the distribution network by using the mutation waveform includes: The waveform weight of the sudden change waveform is calculated using the following formula: in, represents the waveform weight of the mutation waveform, f represents the activation function, N represents the normalization process, ε t represents the distortion value at the tth moment in the mutation waveform, and the time period from t0 to T is the time period length of a unit cycle in the mutation waveform; Based on the waveform weight and the sudden change waveform, the fault category probability of the distribution network is calculated using the following formula: Wherein, P represents the fault category probability, w1 represents the waveform weight of the mutation waveform, and since the mutation waveform contains multiple unit cycles, w1 is the waveform weight of multiple unit cycles. The vector formed, p I represents the fault category probability predicted based on the current value contained in the signal waveform, p U represents the fault category probability predicted based on the voltage signal of the fault address, w o represents the weight of the hidden layer, h j represents the output data of the hidden layer receiving the signal waveform, σ represents the activation function, w2 represents the waveform weight of the normal waveform in the signal waveform except the mutation waveform, j represents the time sequence number of the mutation waveform, and 0~T′ represents the total duration of the mutation waveform; A fault category corresponding to a maximum fault category probability among the fault category probabilities is queried, and the fault category corresponding to the maximum fault category probability is used as the fault category of the distribution network.
7. The method according to claim 1, characterized in that The method of using the normal waveform to identify the faulty device of the distribution network includes: Extracting a current value of the distribution network from the normal waveform; Based on the current value, the resistance value of the equipment in the distribution network is calculated using the following formula: Wherein, R represents the resistance value, U represents the voltage value extracted from the voltage waveform of the fault address, and I represents the current value; When the resistance value is consistent with the resistance value in the preset device-resistance table, the preset device-resistance table is queried for a faulty device corresponding to the resistance value.
8. The method according to claim 1, characterized in that The determining, based on the fault address, the fault type and the faulty device, a final fault detection result of the distribution network includes: Selecting a target faulty device that meets the fault category from the faulty devices; Identify whether the device at the fault address matches the target fault device; When the device at the fault address matches the target fault device, taking the fault address as the target fault address; The fault type, the target fault device and the target fault address are used as the final fault detection result.
9. An intelligent detection system for power distribution faults, characterized in that: The system comprises: A current sending module, used for acquiring a sending substation and a receiving substation of a distribution network, sending a first current traveling wave from the sending substation to the distribution network, and sending a second current traveling wave from the receiving substation to the distribution network; An address identification module, used to calculate a first device address of a device in the distribution network based on the first current traveling wave, comprising: The distance between every two devices when the first current traveling wave passes through the distribution network is calculated using the following formula: G=[G1-G0,G2-G1,G3-G2,…,G m -G m-1 ] S=[G1×V,(G2-G1)×V,…,(G m -G m-1 )×V] Wherein, S represents the distance between every two devices when the first current wave passes through the distribution network, G1 represents the wave head time when the first current wave passes through the distribution network to the first device, G2 represents the wave head time when the first current wave passes through the distribution network to the second device, G3 represents the wave head time when the first current wave passes through the distribution network to the third device, G m-1 represents the wave head time when the first current wave passes through the distribution network to the m-1th device, G m represents the wave head time when the first current wave passes through the mth device in the distribution network, G0 represents the wave head time when the first current wave starts from the sending substation in the distribution network, that is, the value is 0, G represents the difference in the wave head time of every two devices, and V represents the transmission rate of the first current wave; A line image of the distribution network is collected, and based on the line angle in the line image and the distance between every two devices when the first current traveling wave passes through the distribution network, the first device address is calculated using the following formula: (u, v)=((u0, V0)0, (u0+S2cosθ, v0+S2sinθ)1,......, (u0′, v0′) m ) Wherein, (u, v) represents the first device address, (u0, V0)0 represents the address of the sending substation, (u0+S2cosθ, v0+S2sinθ)1 represents the address of the first device in the distribution network, (u0′, v0′) m represents the address of the mth device in the distribution network, S2 represents the distance between every two devices when the first current wave passes through the distribution network, that is, the distance from the sending substation to the first device, θ represents the line angle, K1 represents the horizontal distance from the sending substation to the first device, and K3 represents the vertical distance from the sending substation to the first device; Calculating a second device address of a device in the distribution network based on the second current traveling wave, and identifying a fault address of the distribution network using the first device address and the second device address; a mutation discrimination module, used for collecting the current signal of the fault address, constructing a signal waveform of the current signal, analyzing a mutation threshold of the signal waveform, calculating a distortion value of the signal waveform, and judging whether there is a mutation waveform in the signal waveform based on the mutation threshold and the distortion value; A device identification module, used for identifying the fault type of the distribution network by using the mutation waveform when the mutation waveform exists in the signal waveform, extracting a normal waveform other than the mutation waveform from the signal waveform, and identifying the faulty device of the distribution network by using the normal waveform; The result determination module is used to determine the final fault detection result of the distribution network based on the fault address, the fault type and the faulty device.
