Unmanned aerial vehicle fault detection method, device, equipment and medium

Abstract

The invention discloses an unmanned aerial vehicle fault detection method and device, equipment and a medium. The method comprises the following steps: acquiring a to-be-detected wire position, and acquiring at least one wire wiring image acquired by an unmanned aerial vehicle corresponding to the to-be-detected wire position; identifying each wire wiring image corresponding to the position of the to-be-detected wire to obtain a wire wiring mode corresponding to the position of the to-be-detected wire; the position of an unmanned aerial vehicle induction coil is adjusted according to the wire wiring mode, so that the unmanned aerial vehicle induction coil can detect at least one to-be-detected wire corresponding to the position of the to-be-detected wire, and wire detection currents corresponding to the to-be-detected wires are obtained; calculating a fault calculation result according to the wire detection current corresponding to each to-be-detected wire; and determining fault detection information corresponding to the unmanned aerial vehicle according to the position of the to-be-detected lead and the fault calculation result. According to the embodiment of the invention, the accuracy and efficiency of unmanned aerial vehicle fault detection can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data detection technology, and in particular to a method, device, equipment and medium for detecting faults of unmanned aerial vehicles. Background Art

[0002] With the rapid development of science and technology, the types of power equipment are gradually increasing. In order to ensure the normal operation of power equipment, the number of low-voltage overhead lines is gradually increasing. However, due to long-term high-load operation outdoors and other reasons, unsafe accidents may occur in the lines, so it is necessary to detect line safety in a timely manner.

[0003] Currently, line faults are checked section by section by manpower using clamp meters at high altitudes.

[0004] However, there are a large number of low-voltage overhead lines, and manual detection has a low detection accuracy, which can easily lead to unsafe accidents. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for detecting faults of unmanned aerial vehicles (UAVs), so as to improve the accuracy of detecting faults of unmanned aerial vehicles (UAVs).

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting a fault of a drone, the method comprising:

[0007] Acquire the position of the wire to be detected, and acquire at least one wire wiring image collected by a drone corresponding to the position of the wire to be detected;

[0008] Identify each wire wiring image corresponding to the position of the wire to be detected, and obtain the wire wiring mode corresponding to the position of the wire to be detected;

[0009] Adjust the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected;

[0010] The fault calculation result is obtained by calculating the wire detection current corresponding to each wire to be detected;

[0011] According to the position of the wire to be detected and the fault calculation results, the fault detection information corresponding to the UAV is determined.

[0012] In a second aspect, an embodiment of the present invention further provides a drone fault detection device, the device comprising:

[0013] An image acquisition module, used to acquire the position of the wire to be detected, and to acquire at least one wire wiring image acquired by a drone corresponding to the position of the wire to be detected;

[0014] An image recognition module is used to recognize each wire wiring image corresponding to the position of the wire to be detected, and obtain the wire wiring mode corresponding to the position of the wire to be detected;

[0015] A current detection module is used to adjust the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected;

[0016] A current calculation module, used to calculate the fault calculation result according to the wire detection current corresponding to each wire to be detected;

[0017] The information confirmation module is used to determine the fault detection information corresponding to the drone according to the position of the wire to be detected and the fault calculation result.

[0018] In a third aspect, an embodiment of the present invention further provides a drone fault detection device, the drone fault detection device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the drone fault detection method of any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the drone fault detection method of any embodiment of the present invention when executed.

[0023] The technical solution of the embodiment of the present invention obtains the position of the wire to be detected and at least one wire wiring image collected by the drone corresponding to the position of the wire to be detected, identifies each wire wiring image corresponding to the position of the wire to be detected, obtains the wire wiring method corresponding to the position of the wire to be detected, adjusts the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, obtains the wire detection current corresponding to each wire to be detected, calculates the fault calculation result according to the wire detection current corresponding to each wire to be detected, determines the fault detection information corresponding to the drone according to the position of the wire to be detected and the fault calculation result, performs different operations for different wire wiring methods, refines the steps of drone fault detection, and improves the accuracy of drone fault detection.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in 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 creative work.

[0026] Figure 1 is a flow chart of a method for detecting a drone fault according to an embodiment of the present invention;

[0027] Figure 2 is a structural diagram of a conductor installation of a low-voltage overhead line provided in an embodiment of the present invention;

[0028] Figure 3 is a structural diagram of a fault detection drone provided according to an embodiment of the present invention;

[0029] Figure 4 is a structural diagram of a fault detection drone provided according to an embodiment of the present invention;

[0030] Figure 5 is a flow chart of a method for detecting a drone fault according to an embodiment of the present invention;

[0031] Figure 6 is a structural diagram of a UAV fault detection device provided according to an embodiment of the present invention;

[0032] Figure 7 It is a structural diagram of a UAV fault detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of the wire wiring images involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0036] Embodiment 1

[0037] Figure 1 The present invention provides a flowchart of a method for detecting a drone fault. The present invention can be applied to the case of detecting a drone fault. The method can be performed by a drone fault detection device, which can be implemented in the form of hardware and / or software.

[0038] See also Figure 1 The drone fault detection method shown includes:

[0039] S101, obtaining a position of a wire to be detected, and obtaining at least one wire wiring image collected by a drone corresponding to the position of the wire to be detected.

[0040] The position to be detected may be a position in the conductor where current detection is to be performed. The conductor wiring image may be an image of a conductor installation structure of a low-voltage overhead line.

[0041] Specifically, the position of the wire to be detected can be obtained, and the drone can be flown to the position of the wire to be detected. The camera of the drone can be controlled to capture multi-angle wire wiring images at the position to be detected, so that each wire wiring image can be subsequently identified.

[0042] In one example, the drone is flown to position 1 of the wire to be detected, and the camera of the drone is controlled to capture 5 top view wire wiring images and 5 side view images of position 1 to be detected.

[0043] S102 , identifying each wire wiring image corresponding to the position of the wire to be detected, and obtaining the wire wiring mode corresponding to the position of the wire to be detected.

[0044] Among them, the wire wiring method can be a wire installation structure. There are usually two types of wire installation structures. The first is three-phase four-wire (horizontal), such as Figure 2 As shown on the left side of the figure, the other type is three-phase four-wire (vertical), such as Figure 2 Shown on the right.

[0045] Specifically, images of different wire wiring methods can be collected in advance by drones, and neural network training can be performed on these images to obtain a guided wiring method recognition model. The neural network includes but is not limited to: feedforward neural network, recurrent neural network, convolutional neural network, generative adversarial neural network, graph neural network, long short-term memory network and artificial neural network, etc., which are not limited in the embodiments of the present invention. The guided wiring method recognition model can be stored in a drone to identify the wire wiring method, or the wire wiring method recognition model can be stored in a control system. After the wire wiring image is collected by the drone, the wire wiring image is transmitted to the control system, and the control system recognizes the guided wiring method.

[0046] In one example, a drone collects 10 wire wiring images at the position 1 of the wire to be detected and identifies these images to obtain that the guide wiring method at the position 1 of the wire to be detected is three-phase four-wire (horizontal).

[0047] S103, adjusting the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected.

[0048] The drone induction coil position may be the position of the induction coil installed on the drone. The wire detection current may be the current value of the wire to be detected corresponding to the induction coil detected by the drone induction coil.

[0049] Specifically, there are four low-voltage overhead wires, namely, phase A wire, phase B wire, phase C wire, and phase D wire. Different guided wiring methods result in different wire installation structures, so different guided wiring methods correspond to different positions of drone induction coils. The drone is equipped with an adjustable operating lever, and four drone induction coils are installed on the adjustable operating lever, namely, phase A coil, phase B coil, phase C coil, and phase D coil. Different induction coils perform current detection on the corresponding wires. The angle and position of the operating lever are adjusted according to the guided wiring method, so that the drone induction coil is adjusted to a position where it can perform current detection on the corresponding wire to be detected, and the wire detection current corresponding to each wire to be detected is obtained. Figure 2 The left side shows three-phase four-wire (horizontal), so the induction coil needs to be adjusted as follows Figure 3 The operable rod is shown parallel to the plane where the four wires to be tested are located. Figure 2The right side of the diagram shows three-phase four-wire (vertical), so the induction coil needs to be adjusted as follows: Figure 4 The operable rod is shown parallel to the plane where the four wires to be detected are located.

[0050] S104, obtaining a fault calculation result according to the wire detection current corresponding to each wire to be detected.

[0051] The fault calculation result may be a result calculated based on the wire detection current, and may be used to determine the fault type of the wire to be detected.

[0052] Specifically, overhead lines are one of the commonly used transmission methods in power systems, and the power transmission from low-voltage lines to the user side is also mainly based on overhead lines. As low-voltage overhead lines run outdoors for a long time, due to the aging of the line materials themselves, damage from external forces, long-term high-load operation and other reasons, the wires are prone to leakage during use. After leakage occurs, it will not only cause damage to power equipment and power loss, but more seriously, it will cause electric shock accidents to passers-by, resulting in casualties. Therefore, it is necessary to detect the leakage of the wire to be detected, and leakage detection can be performed by detecting the current value of the wire to be detected. In addition, low-voltage lines are often uneven due to uneven power loads of users, and the lines often have three-phase imbalance, which is very easy to cause single-phase line overload operation and joint power accidents. Therefore, it is necessary to detect the three-phase imbalance between the wire detection currents of the wire to be detected. The fault calculation result is calculated based on the wire detection current corresponding to each wire to be detected.

[0053] S105: Determine the fault detection information corresponding to the UAV according to the position of the wire to be detected and the fault calculation result.

[0054] The fault detection information may be descriptive information of the wire fault condition detected at the position of the wire to be detected.

[0055] Specifically, a fault detection is performed on each wire position to be detected to obtain a fault calculation result corresponding to each wire position to be detected, and the fault type corresponding to each wire position to be detected is determined according to the fault calculation result, and the faulty wire position to be detected and the fault type are determined as the fault detection information corresponding to the drone.

[0056] The technical solution of the embodiment of the present invention obtains the position of the wire to be detected and at least one wire wiring image collected by the drone corresponding to the position of the wire to be detected, identifies each wire wiring image corresponding to the position of the wire to be detected, obtains the wire wiring method corresponding to the position of the wire to be detected, adjusts the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, obtains the wire detection current corresponding to each wire to be detected, calculates the fault calculation result according to the wire detection current corresponding to each wire to be detected, determines the fault detection information corresponding to the drone according to the position of the wire to be detected and the fault calculation result, performs different operations for different wire wiring methods, refines the steps of drone fault detection, and improves the accuracy of drone fault detection.

[0057] Embodiment 2

[0058] Figure 5 This is a flow chart of a method for detecting a fault in a UAV provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment of the present invention optimizes and improves the operation of detecting a fault in a UAV.

[0059] Furthermore, "obtaining a fault calculation result based on the wire detection current corresponding to each wire to be detected" is refined into "obtaining at least one fault detection type; calculating the wire detection current corresponding to each wire to be detected according to each fault detection type, and obtaining a fault calculation result" to improve the operation of UAV fault detection.

[0060] It should be noted that for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions of other embodiments.

[0061] See also Figure 5 The drone fault detection method shown includes:

[0062] S501: Acquire a position of a wire to be detected, and acquire at least one wire wiring image collected by a drone corresponding to the position of the wire to be detected.

[0063] S502 , identifying each wire wiring image corresponding to the position of the wire to be detected, and obtaining the wire wiring mode corresponding to the position of the wire to be detected.

[0064] S503, adjusting the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected.

[0065] S504: Obtain at least one fault detection type.

[0066] The fault detection type may be a type of fault detection performed on a wire to be detected.

[0067] Specifically, at least one fault detection type is obtained, and the obtaining method includes but is not limited to: mouse selection or keyboard input, which is not limited in the embodiment of the present invention. The fault detection type includes a leakage detection type and a current balance detection type.

[0068] S505 , calculating the wire detection current corresponding to each wire to be detected according to each fault detection type, and obtaining a fault calculation result.

[0069] Specifically, different fault detection types correspond to different fault calculation methods. Different fault calculation methods are searched according to different fault detection types, and the fault calculation results are obtained by calculating according to the fault calculation methods corresponding to the fault types.

[0070] S506: Determine the fault detection information corresponding to the UAV according to the position of the wire to be detected and the fault calculation result.

[0071] The embodiment of the present invention obtains at least one fault detection type, calculates the wire detection current corresponding to each wire to be detected according to each fault detection type, obtains a fault calculation result, performs different fault calculation operations according to different fault detection types, refines the operation of drone fault detection, and improves the accuracy of drone fault detection.

[0072] Optionally, the fault detection type is a leakage detection type; the wire detection current corresponding to each wire to be detected is calculated according to each fault detection type to obtain a fault calculation result, including: identifying each wire wiring image to obtain at least one wire color; for each wire color, screening each wire to be detected to obtain a target wire corresponding to the wire color and a wire detection current corresponding to the target wire; adding the wire detection currents of the target wires corresponding to each wire color to obtain a total wire current; obtaining a preset current threshold; comparing the total wire current with the preset current threshold to obtain a fault calculation result.

[0073] The target wire may be a wire corresponding to the wire color among the wires to be detected. The total wire current may be the sum of the wire detection currents corresponding to the target wires. The preset current threshold may be a preset threshold of the total wire current.

[0074] Specifically, the colors of low-voltage wires are divided into 4 colors, among which phase A is yellow, phase B is green, phase C is red, and N line (neutral line) is lavender. Identify the wiring images of each wire to obtain at least one wire color. For each wire color, screen the wires to be detected to obtain the target wire corresponding to the wire color and the wire detection current corresponding to the target wire. Add the wire detection currents of the target wires corresponding to each wire color to obtain the total wire current. Obtain the preset current threshold. Generally, the preset current threshold is set to 0. If the sum of the wire detection currents collected in the same area and the same time period is not zero, leakage occurs. Compare the total wire current with the preset current threshold of 0 to obtain the fault calculation result.

[0075] At least one wire color is obtained by identifying the wiring images of each wire. For each wire color, the wires to be detected are screened to obtain the target wire corresponding to the wire color and the wire detection current corresponding to the target wire. The wire detection currents of the target wires corresponding to each wire color are added to obtain the total wire current, and the preset current threshold is obtained. The total wire current is compared with the preset current threshold to obtain the fault calculation result, which can further screen the wires to be detected, ensure the accuracy of the total wire current, and improve the accuracy of UAV fault detection.

[0076] Optionally, the fault detection type is a current balance detection type; the wire detection current corresponding to each wire to be detected is calculated according to each fault detection type to obtain a fault calculation result, including: arranging and combining the wires to be detected to obtain at least one wire group, one wire group including two wires to be detected and wire detection currents corresponding to each wire to be detected; for each wire group, subtracting the wire detection currents corresponding to the two wires to be detected corresponding to the wire group to obtain a wire current difference corresponding to the wire group; obtaining a current difference threshold; for each wire group, subtracting the wire current difference corresponding to the wire group from the current difference threshold to obtain a fault calculation result.

[0077] The wire group may be a set of two wires to be detected and the wire detection currents corresponding to the wires to be detected. The wire current difference may be the difference between the wire detection currents corresponding to the two wires to be detected in a wire group. The current difference threshold may be the threshold of the wire current difference.

[0078] Specifically, each wire to be detected is arranged and combined to obtain at least one wire group, and one wire group includes two wires to be detected and wire detection currents corresponding to each wire to be detected. For each wire group, the larger value of the wire detection current in the wire detection current corresponding to the two wires to be detected corresponding to the wire group is subtracted from the smaller value of the wire detection current to obtain the wire current difference corresponding to the wire group; the current difference threshold is obtained, and for each wire group, the wire current difference corresponding to the wire group is subtracted from the current difference threshold. If the wire current difference corresponding to the wire group is less than the current difference threshold, it indicates that the rated difference between the wire detection currents of the two wires to be detected in the wire group is small, and the current is relatively balanced, and no alarm is given for a fault; if the wire current difference corresponding to the wire group is greater than or equal to the current difference threshold, it indicates that the rated difference between the wire detection currents of the two wires to be detected in the wire group is large, and the current is unbalanced, and an alarm is given for a fault, and the alarm method can be an information alarm, an email alarm, a telephone alarm, a sound alarm, a smoke alarm, or a light alarm.

[0079] By arranging and combining the wires to be detected, at least one wire group is obtained, and one wire group includes two wires to be detected and a wire detection current corresponding to each wire to be detected. For each wire group, the wire detection currents corresponding to the two wires to be detected corresponding to the wire group are subtracted to obtain the wire current difference corresponding to the wire group, and the current difference threshold is obtained; for each wire group, the wire current difference corresponding to the wire group is subtracted from the current difference threshold to obtain a fault calculation result. Fault detection is performed through multi-dimensional data, thereby improving the accuracy of drone fault detection.

[0080] Optionally, obtaining the position of the wire to be detected includes: obtaining the low-voltage wire segment to be detected and the starting position of the wire segment; obtaining a preset acquisition distance; dividing the low-voltage wire segment to be detected starting from the starting position of the wire segment according to the preset acquisition distance to obtain at least one wire position to be detected corresponding to the low-voltage wire segment to be detected.

[0081] The low-voltage wire segment to be detected may be a wire segment for which fault detection is to be performed, and the wire between two electric poles is a low-voltage wire segment to be detected. The starting position of the wire segment may be the position of the electric pole in the low-voltage wire segment to be detected where the drone is prepared to start fault detection from the electric pole in the wire segment.

[0082] Specifically, a low-voltage wire segment to be detected is obtained. A direction for fault detection of the wire segment is obtained. The electric pole at the starting point of the low-voltage wire segment to be detected is determined according to the direction of fault detection, and the position of the electric pole at the starting point of the low-voltage wire segment to be detected is determined as the starting point of the wire segment. The preset collection distance can be the interval between the positions of the drone detecting the wire current each time.

[0083] In one example, a low-voltage wire segment 1 to be detected is obtained, and the position of the low-voltage wire segment 1 is (0, 0) to (2, 5, 0). The starting position of the wire segment is (0, 0). The preset acquisition distance is 1 meter. According to the preset acquisition distance, the low-voltage wire segment to be detected is divided from the starting position of the wire segment into (0, 0) to (1, 0), (1, 0) to (2, 0) and (2, 0) to (2.5, 0) according to the preset acquisition distance. The three wire positions to be detected corresponding to the low-voltage wire segment 1 to be detected are (0.5, 0), (1.5, 0) and (2.25, 0).

[0084] By obtaining the low-voltage wire segment to be detected and the starting position of the wire segment, the preset collection distance is obtained, and the low-voltage wire segment to be detected is divided from the starting position of the wire segment according to the preset collection distance to obtain at least one wire position to be detected corresponding to the low-voltage wire segment to be detected. By detecting the current of the same low-voltage wire segment to be detected multiple times, the randomness of the detection is reduced and the accuracy of UAV fault detection is improved.

[0085] Optionally, at least one wire wiring image captured by a drone corresponding to the position of the wire to be detected is obtained, including: identifying the low-voltage wire segment to be detected and obtaining at least one drone shooting direction; for each drone shooting direction, if the drone shooting direction is a top-down direction, the drone is flown to directly above the low-voltage wire segment to be detected to obtain at least one first wire image; if the drone shooting direction is a side-view direction, the camera deflection angle is obtained, the drone is flown to a shooting position parallel to the low-voltage wire segment to be detected, and at least one second wire image is obtained according to the camera deflection angle; each first wire image and each second wire image is determined as a wire wiring image.

[0086] The shooting direction of the drone may be the direction in which the camera installed on the drone collects images. The first wire image may be an image taken by the camera of the drone looking down at the wire to be detected. The camera deflection angle may be the angle of camera deflection. The second wire image may be an image taken by the camera of the drone in the side view direction of the wire to be detected. The wire wiring image may be an image taken by the drone of the position of the wire to be detected.

[0087] Specifically, an image of the low-voltage wire segment to be detected is obtained, and the image of the low-voltage wire segment to be detected is identified to obtain the position of the low-voltage wire segment to be detected in the top-view direction and the side-view direction. For each drone shooting direction, if the drone shooting direction is a top-view direction, the drone is flown to directly above the low-voltage wire segment to be detected, and the camera is directed to look down at the low-voltage wire segment to be detected, and at least one first wire image is acquired. If the drone shooting direction is a side-view direction, the camera deflection angle is acquired, the drone is flown to a shooting position parallel to the low-voltage wire segment to be detected, the camera is deflected according to the camera deflection angle, and at least one second wire image is acquired; each first wire image and each second wire image are determined as a wire wiring image.

[0088] In one example, a drone shooting direction, a left-view direction, and a right-view direction are identified for the low-voltage wire segment to be detected. For each drone shooting direction, if the drone shooting direction is a top-down direction, the drone is flown to the top of the low-voltage wire segment to be detected to acquire 5 first wire images. If the drone shooting direction is a left-view direction, the camera deflection angle is obtained to be 30°, and the drone is flown to the left side of the low-voltage wire segment to be detected and parallel to the low-voltage wire segment to be detected. The initial angle of the camera is 0°, and 20 second wire images are acquired according to the camera deflection angle, which are deflected upward by 30° and 60°, deflected downward by 30° and 60°, deflected to the left by 30° and 60°, and deflected to the right by 30° and 60°. If the shooting direction of the drone is the right viewing direction, the camera deflection angle is obtained to be 30°, the drone is flown to the shooting position on the right side of the low-voltage wire segment to be detected and parallel to the low-voltage wire segment to be detected, the initial angle of the camera is 0°, and 20 second wire images deflected 30° and 60° upward, 30° and 60° downward, 30° and 60° to the left, and 30° and 60° to the right are collected according to the camera deflection angle. Each first wire image and each second wire image are determined as a wire wiring image.

[0089] At least one drone shooting direction is obtained by identifying the low-voltage wire segment to be detected. For each drone shooting direction, if the drone shooting direction is a top-down direction, the drone is flown to directly above the low-voltage wire segment to be detected to obtain at least one first wire image. If the drone shooting direction is a side-view direction, the camera deflection angle is obtained, and the drone is flown to a shooting position parallel to the low-voltage wire segment to be detected, and at least one second wire image is obtained according to the camera deflection angle; each first wire image and each second wire image are determined as a wire wiring image, and the accuracy of drone fault detection is improved by collecting images of the positions to be detected from multiple angles.

[0090] Optionally, the position of the drone induction coil is adjusted according to the wire wiring method so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected, including: finding the coil rod adjustment method according to the wire wiring method; adjusting the coil rod of the drone according to the coil rod adjustment method so that each induction coil on the coil rod is parallel to each wire to be detected; for each induction coil, detecting the distance between the induction coil and the wire to be detected corresponding to the induction coil to obtain the detection distance; obtaining the detectable distance; for each induction coil, comparing the detection distance with the detectable distance to obtain a distance comparison result; adjusting the position of the induction coil corresponding to the drone according to the distance comparison result corresponding to the induction coil, controlling the opening and closing device corresponding to the induction coil to detect the wire to be detected, and obtaining the wire detection current corresponding to the wire to be detected.

[0091] The coil rod adjustment method may be a method of adjusting the drone induction coil. The detection distance may be the distance between the induction coil and the wire to be detected corresponding to the induction coil, and the detection distance may be detected by a laser rangefinder. The detectable distance may be the distance between the induction coil and the wire to be detected, at which the induction coil can detect the current of the wire to be detected. The distance comparison result may be the result of comparing the detection distance with the detectable distance. The opening and closing device may be a device for the induction coil to clamp the wire to be detected for current detection.

[0092] Specifically, the coil rod adjustment method is searched according to the wire wiring method. If the wire wiring method is three-phase four-wire (vertical), the coil rod adjustment method is to adjust the operable rod to be parallel to the plane where each wire to be detected is located; if the wire wiring method is three-phase four-wire (horizontal), the coil rod adjustment method is to adjust the operable rod to be parallel to the plane where each wire to be detected is located. For each induction coil, the distance between the induction coil and the wire to be detected corresponding to the induction coil is detected to obtain the detection distance and the detectable distance; for each induction coil, the detection distance is compared with the detectable distance to obtain the distance comparison result. If the detection distance is less than or equal to the detectable distance, the opening and closing device clamps the wire to be detected to detect the current. If the detection distance is greater than the detectable distance, the position of the induction coil corresponding to the drone is adjusted according to the distance comparison result corresponding to the induction coil, and the opening and closing device corresponding to the induction coil is controlled to detect the wire to be detected, and the wire detection current corresponding to the wire to be detected is obtained.

[0093] By finding the coil rod adjustment method according to the wire wiring method, the coil rod of the drone is adjusted according to the coil rod adjustment method so that each induction coil on the coil rod is parallel to each wire to be detected, for each induction coil, the distance between the induction coil and the wire to be detected corresponding to the induction coil is detected to obtain the detection distance, and the detectable distance is obtained. For each induction coil, the induction coil is compared with the detectable distance to obtain a distance comparison result; according to the distance comparison result corresponding to the induction coil, the position of the induction coil corresponding to the drone is adjusted, and the opening and closing device corresponding to the induction coil is controlled to detect the wire to be detected, and the wire detection current corresponding to the wire to be detected is obtained. According to different wire wiring methods and different wire positions, the method of collecting current can be analyzed in real time to collect current, which is convenient for fault detection and improves the accuracy of drone fault detection.

[0094] Embodiment 3

[0095] Figure 6 The structure diagram of a UAV fault detection device provided in Embodiment 3 of the present invention is shown. The embodiment of the present invention is applicable to the case of UAV fault detection, the device can execute the UAV fault detection method, and the device can be implemented in the form of hardware and / or software.

[0096] See also Figure 6 The UAV fault detection device shown includes: an image acquisition module 601, an image recognition module 602, a current detection module 603, a current calculation module 604 and an information confirmation module 605, wherein:

[0097] An image acquisition module 601 is used to acquire the position of the wire to be detected, and acquire at least one wire wiring image acquired by a drone corresponding to the position of the wire to be detected;

[0098] An image recognition module 602 is used to recognize each wire wiring image corresponding to the position of the wire to be detected, and obtain the wire wiring mode corresponding to the position of the wire to be detected;

[0099] The current detection module 603 is used to adjust the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected;

[0100] The current calculation module 604 is used to calculate the fault calculation result according to the wire detection current corresponding to each wire to be detected;

[0101] The information confirmation module 605 is used to determine the fault detection information corresponding to the drone according to the position of the wire to be detected and the fault calculation result.

[0102] The technical solution of the embodiment of the present invention obtains the position of the wire to be detected and at least one wire wiring image collected by the drone corresponding to the position of the wire to be detected, identifies each wire wiring image corresponding to the position of the wire to be detected, obtains the wire wiring method corresponding to the position of the wire to be detected, adjusts the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, obtains the wire detection current corresponding to each wire to be detected, calculates the fault calculation result according to the wire detection current corresponding to each wire to be detected, determines the fault detection information corresponding to the drone according to the position of the wire to be detected and the fault calculation result, performs different operations for different wire wiring methods, refines the steps of drone fault detection, and improves the accuracy of drone fault detection.

[0103] Optionally, the current calculation module 604 includes:

[0104] A type acquisition unit, used to acquire at least one fault detection type;

[0105] The fault calculation unit is used to calculate the wire detection current corresponding to each wire to be detected according to each fault detection type to obtain a fault calculation result.

[0106] Optionally, a fault calculation unit is used to:

[0107] The fault detection type is leakage detection type;

[0108] Identify each wire wiring image to obtain at least one wire color;

[0109] For each wire color, screen the wires to be detected to obtain the target wire corresponding to the wire color and the wire detection current corresponding to the target wire;

[0110] Add the wire detection currents of the target wires corresponding to the wire colors to obtain the total wire current;

[0111] Obtaining a preset current threshold;

[0112] The total conductor current is compared with the preset current threshold to obtain the fault calculation result.

[0113] Optionally, a fault calculation unit is used to:

[0114] The fault detection type is a current balance detection type;

[0115] Arrange and combine the wires to be detected to obtain at least one wire group, wherein one wire group includes two wires to be detected and wire detection currents corresponding to the wires to be detected;

[0116] For each wire group, subtract the wire detection currents corresponding to the two wires to be detected corresponding to the wire group to obtain the wire current difference corresponding to the wire group;

[0117] Get the current difference threshold;

[0118] For each wire group, the wire current difference corresponding to the wire group is subtracted from the current difference threshold to obtain a fault calculation result.

[0119] Optionally, the image acquisition module 601 includes:

[0120] A line segment acquisition unit, used to acquire the low-voltage wire segment to be detected and the starting position of the wire segment;

[0121] A distance acquisition unit, used to acquire a preset collection distance;

[0122] The line segment division unit is used to divide the low-voltage wire segment to be detected from the starting position of the wire segment according to the preset collection distance, and obtain at least one wire position to be detected corresponding to the low-voltage wire segment to be detected.

[0123] Optionally, the image acquisition module 601 is specifically used for:

[0124] Identify the low-voltage wire segment to be detected and obtain at least one drone shooting direction;

[0125] For each drone shooting direction, if the drone shooting direction is a downward-looking direction, the drone is flown to directly above the low-voltage wire segment to be detected to acquire at least one first wire image;

[0126] If the shooting direction of the drone is a side view direction, the camera deflection angle is obtained, the drone is flown to a shooting position parallel to the low-voltage wire segment to be detected, and at least one second wire image is acquired according to the camera deflection angle;

[0127] Each of the first conductive wire images and each of the second conductive wire images are determined as conductive wire wiring images.

[0128] Optionally, the current detection module 603 is specifically used for:

[0129] Find the coil rod adjustment method based on the wire routing method;

[0130] Adjust the coil rod of the drone according to the coil rod adjustment method so that each induction coil on the coil rod is parallel to each wire to be detected;

[0131] For each induction coil, detect the distance between the induction coil and the wire to be detected corresponding to the induction coil to obtain a detection distance;

[0132] Get the detectable distance;

[0133] For each induction coil, the detection distance is compared with the detectable distance to obtain a distance comparison result;

[0134] The position of the induction coil corresponding to the UAV is adjusted according to the distance comparison result corresponding to the induction coil, and the opening and closing device corresponding to the induction coil is controlled to detect the wire to be detected, so as to obtain the wire detection current corresponding to the wire to be detected.

[0135] The drone fault detection device provided in the embodiment of the present invention can execute the drone fault detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the drone fault detection method.

[0136] Embodiment 4

[0137] Figure 7 A schematic structural diagram of a UAV fault detection device 700 that can be used to implement an embodiment of the present invention is shown.

[0138] like Figure 7 As shown, the drone fault detection device 700 includes at least one processor 701, and a memory connected to the at least one processor 701, such as a read-only memory (ROM) 702, a random access memory (RAM) 703, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 701 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 702 or the computer program loaded from the storage unit 708 to the random access memory (RAM) 703. In RAM703, various programs and data required for the operation of the drone fault detection device 700 can also be stored. The processor 701, ROM702 and RAM703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0139] Multiple components in the drone fault detection device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the drone fault detection device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0140] The processor 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 701 executes the various methods and processes described above, such as a drone fault detection method.

[0141] In some embodiments, the drone fault detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the drone fault detection device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the processor 701, one or more steps of the drone fault detection method described above may be performed. Alternatively, in other embodiments, the processor 701 may be configured to execute the drone fault detection method in any other appropriate manner (e.g., by means of firmware).

[0142] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0144] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein may be implemented on a drone fault detection device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or trackball), through which a user can provide input to the drone fault detection device. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0146] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0147] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting a drone fault, characterized in that: The method comprises: Acquire the position of the wire to be detected, and acquire at least one wire wiring image collected by a drone corresponding to the position of the wire to be detected; Identify each of the wire wiring images corresponding to the position of the wire to be detected, and obtain the wire wiring mode corresponding to the position of the wire to be detected; Adjust the position of the drone induction coil according to the wire wiring method, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected; Obtaining a fault calculation result according to the wire detection current corresponding to each of the wires to be detected; Fault detection information corresponding to the UAV is determined according to the position of the wire to be detected and the fault calculation result.

2. The method according to claim 1, characterized in that The calculating of the fault calculation result according to the wire detection current corresponding to each of the wires to be detected includes: Get at least one fault detection type; The wire detection current corresponding to each of the wires to be detected is calculated according to each of the fault detection types to obtain a fault calculation result.

3. The method according to claim 2, characterized in that The fault detection type is a leakage detection type; The calculating the wire detection current corresponding to each of the wires to be detected according to each of the fault detection types to obtain a fault calculation result includes: Identifying each of the wire wiring images to obtain at least one wire color; For each of the wire colors, screening is performed among the wires to be detected to obtain a target wire corresponding to the wire color and a wire detection current corresponding to the target wire; Adding the wire detection currents of the target wires corresponding to the wire colors to obtain the total wire current; Obtaining a preset current threshold; The total current of the conductor is compared with the preset current threshold to obtain a fault calculation result.

4. The method according to claim 2, characterized in that: The fault detection type is a current balance detection type; The calculating the wire detection current corresponding to each of the wires to be detected according to each of the fault detection types to obtain a fault calculation result includes: Arrange and combine the wires to be detected to obtain at least one wire group, wherein one wire group includes two wires to be detected and wire detection currents corresponding to the wires to be detected; For each of the wire groups, subtract wire detection currents corresponding to two to-be-detected wires corresponding to the wire group to obtain a wire current difference corresponding to the wire group; Get the current difference threshold; For each of the wire groups, the wire current difference corresponding to the wire group is subtracted from the current difference threshold to obtain a fault calculation result.

5. The method according to claim 1, characterized in that The step of obtaining the position of the wire to be detected includes: Obtain the low-voltage wire segment to be detected and the starting point position of the wire segment; Get the preset collection distance; According to the preset acquisition distance, the low-voltage wire segment to be detected is divided from the starting position of the wire segment according to the preset acquisition distance to obtain at least one wire position to be detected corresponding to the low-voltage wire segment to be detected.

6. The method according to claim 5, characterized in that The step of obtaining at least one wire wiring image collected by a drone corresponding to the position of the wire to be detected includes: Identify the low-voltage wire segment to be detected and obtain at least one drone shooting direction; For each of the drone shooting directions, if the drone shooting direction is a downward-looking direction, the drone is flown to directly above the low-voltage wire segment to be detected to acquire at least one first wire image; If the shooting direction of the drone is a side view direction, the camera deflection angle is obtained, the drone is flown to a shooting position parallel to the low-voltage wire segment to be detected, and at least one second wire image is acquired according to the camera deflection angle; Each of the first conductive line images and each of the second conductive line images are determined as a conductive line wiring image.

7. The method according to claim 1, characterized in that The method of adjusting the position of the drone induction coil according to the wire wiring method so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtaining the wire detection current corresponding to each wire to be detected, includes: Find the coil rod adjustment method according to the wire routing method; The coil rod of the drone is adjusted according to the coil rod adjustment method, so that each of the induction coils on the coil rod is parallel to each of the wires to be detected; For each of the induction coils, detecting the distance between the induction coil and the wire to be detected corresponding to the induction coil to obtain the detection distance; Get the detectable distance; For each of the induction coils, the detection distance is compared with the detectable distance to obtain a distance comparison result; The position of the induction coil corresponding to the drone is adjusted according to the distance comparison result corresponding to the induction coil, and the opening and closing device corresponding to the induction coil is controlled to detect the wire to be detected, so as to obtain the wire detection current corresponding to the wire to be detected.

8. A drone fault detection device, characterized in that: The device comprises: An image acquisition module, used to acquire the position of the wire to be detected, and acquire at least one wire wiring image acquired by a drone corresponding to the position of the wire to be detected; An image recognition module, used to recognize each of the wire wiring images corresponding to the position of the wire to be detected, and obtain the wire wiring mode corresponding to the position of the wire to be detected; A current detection module, used for adjusting the position of the drone induction coil according to the wire wiring mode, so that the drone induction coil can detect at least one wire to be detected corresponding to the position of the wire to be detected, and obtain the wire detection current corresponding to each wire to be detected; A current calculation module, used to calculate a fault calculation result according to the wire detection current corresponding to each of the wires to be detected; The information confirmation module is used to determine the fault detection information corresponding to the drone according to the position of the wire to be detected and the fault calculation result.

9. A drone fault detection device, characterized in that: The drone fault detection device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the drone fault detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the drone fault detection method according to any one of claims 1 to 7 when executed.

Images