Wind power plant fault judgment method and system based on rail hanging robot

Abstract

The invention discloses a wind power plant fault judgment method and system based on an on-rail robot, and the method comprises the steps: judging the fault location of a wind power plant according to a current power distribution diagram, guaranteeing the accuracy of the fault location of the wind power plant, and further improving the accuracy of the fault location of the wind power plant. Determining a plurality of fault parameters according to the review of the rail hanging robot on the fault occurrence place, and determining a fault event according to the plurality of fault parameters, the review positions of the plurality of fault parameters relative to the fault occurrence place and the service life of the wind power plant; and according to the fault event, a judgment module of the rail-mounted robot and a repair tool of the rail-mounted robot, a corresponding repair operation track is determined, and the accuracy of the repair operation track is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power plants, and in particular, to a method and system for fault judgment of a wind power plant based on a hanging rail robot. Background Art

[0002] With the development of technology, wind power plants are gradually applied to daily life and generate electricity through wind power. In a wind power plant, there are multiple wires, all of which are used for conducting electricity and form a wire path. In the prior art, the current power distribution map is introduced, and only the corresponding fault occurrence location is output based on the judgment of the current power distribution map. The hanging rail robot is not fully utilized to recheck the fault occurrence location, and accurate control of fault events cannot be achieved. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and system for fault judgment of a wind power plant based on a hanging rail robot.

[0004] An embodiment of the present invention provides a method for fault judgment of a wind power plant based on a hanging rail robot, including: determining the wire path of the wind power plant based on the line model of the wind power plant; determining the corresponding hanging rail robot according to the wire path of the wind power plant and the wire diameter of the wire; collecting multiple current parameters based on the dynamic detection of the wire by the hanging rail robot, and constructing the current power distribution map according to the multiple current parameters and the detection position of the wire; judging the fault occurrence location of the wind power plant according to the current power distribution map; determining multiple fault parameters according to the recheck of the hanging rail robot on the fault occurrence location, and determining the fault event according to the multiple fault parameters, the recheck position of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant; determining the corresponding repair operation trajectory according to the fault event, the judgment module of the hanging rail robot, and the repair tools possessed by the hanging rail robot.

[0005] An embodiment of the present invention provides a system for fault judgment of a wind power plant based on a hanging rail robot. The system for fault judgment of a wind power plant based on a hanging rail robot is applied to the above-mentioned method for fault judgment of a wind power plant based on a hanging rail robot. The system for fault judgment of a wind power plant based on a hanging rail robot includes:

[0006] A wire path module, configured to determine the wire path of the wind power plant based on the line model of the wind power plant;

[0007] A robot module, configured to determine the corresponding hanging rail robot according to the wire path of the wind power plant and the wire diameter of the wire;

[0008] The power distribution map module is used to collect multiple current parameters based on the dynamic detection of wires by the rail-mounted robot, and construct the current power distribution map according to the multiple current parameters and the detection positions of the wires;

[0009] The fault occurrence location module is used to determine the fault occurrence location of the wind power plant according to the current power distribution map;

[0010] The fault event module is used to determine multiple fault parameters according to the re-inspection of the fault occurrence location by the rail-mounted robot, and determine the fault event according to the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant;

[0011] The repair module is used to determine the corresponding repair operation trajectory according to the fault event, the judgment module of the rail-mounted robot, and the repair tools possessed by the rail-mounted robot.

[0012] Compared with the prior art, the beneficial effects of the present invention are:

[0013] In the embodiment of the present invention, through the method in the embodiment of the present invention, the wire path of the wind power plant is determined based on the line model of the wind power plant; the corresponding rail-mounted robot is determined according to the wire path of the wind power plant and the wire diameter of the wire; multiple current parameters are collected based on the dynamic detection of the wire by the rail-mounted robot, and the current power distribution map is constructed according to the multiple current parameters and the detection positions of the wires; the fault occurrence location of the wind power plant is judged according to the current power distribution map, ensuring the accuracy of the fault occurrence location of the wind power plant.

[0014] Furthermore, multiple fault parameters are determined according to the re-inspection of the fault occurrence location by the rail-mounted robot, and the fault event is determined according to the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant, introducing multiple interactions of the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant, realizing the accurate control of the fault event.

[0015] Therefore, the corresponding repair operation trajectory is determined according to the fault event, the judgment module of the rail-mounted robot, and the repair tools possessed by the rail-mounted robot, realizing the overall consideration of the fault event, the judgment module of the rail-mounted robot, and the repair tools possessed by the rail-mounted robot, ensuring the accuracy of the repair operation trajectory. Description of the Drawings

[0016] Figure 1 It is a schematic diagram of the application scenario of the wind power plant fault judgment method based on the rail-mounted robot in the present invention;

[0017] Figure 2It is a schematic flow chart of the method for judging faults in a wind power plant based on a hanging-rail robot in the present invention;

[0018] Figure 3 It is a schematic diagram of the structural composition of the fault judgment system for a wind power plant based on a hanging-rail robot in the present invention. Specific implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0020] Embodiment 1

[0021] This application provides a method for judging faults in a wind power plant based on a hanging-rail robot, which is applied to an application environment as Figure 1 shown. Among them, the computer 102 communicates with the server 104 through the network. Among them, the terminal 102 is not limited to various personal computers, servers, and wind power plants, and the server 104 is implemented by an independent server or a server cluster composed of servers.

[0022] Please refer to Figures 1 to 3 , the method for judging faults in a wind power plant based on a hanging-rail robot includes:

[0023] Step S11: Determine the wire path of the wind power plant based on the line model of the wind power plant;

[0024] Step S12: Determine the corresponding hanging-rail robot according to the wire path of the wind power plant and the wire diameter of the wire;

[0025] Step S13: Collect multiple current parameters based on the dynamic detection of the wire by the hanging-rail robot, and construct the current power distribution map according to the multiple current parameters and the detection positions of the wire;

[0026] Step S14: Judge the fault occurrence location of the wind power plant according to the current power distribution map;

[0027] Step S15: Determine multiple fault parameters according to the re-inspection of the fault occurrence location by the hanging-rail robot, and determine the fault event according to the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant;

[0028] Step S16: Determine the corresponding repair operation trajectory according to the fault event, the judgment module of the hanging-rail robot, and the repair tools possessed by the hanging-rail robot.

[0029] Specifically, in step S11, to determine the wire path of the wind power plant based on the line model of the wind power plant, the specific steps are as follows:

[0030] S111: Collect the line model of the wind power plant;

[0031] S112: Determine multiple functional areas based on the division of the line model of the wind power plant;

[0032] S113: Collect multiple real-time images based on the circumferential aerial survey of the wind power plant by the unmanned aerial vehicle (UAV). The multiple real-time images respectively present the real-time states of the wind power plant at different positions;

[0033] S114: Determine multiple sub-guide line paths according to the matching of the multiple functional areas and the multiple real-time images;

[0034] S115: Determine the guide line path of the wind power plant based on the multiple sub-guide line paths, the multiple functional areas, and the line model of the wind power plant.

[0035] At this time, when collecting the line model of the wind power plant, a preset line model is introduced. These materials are usually stored in the archive room or engineering department of the wind power plant. Multiple functional areas are determined based on the division of the line model of the wind power plant. At the same time, after obtaining the line model, the functions of the wind power plant are analyzed, which includes identifying key functional areas such as power generation, power transmission, power distribution, and control. According to the results of the function analysis, the wind power plant is divided into multiple functional areas, and these areas are divided according to the type, layout, and operation logic of the equipment. Each functional area is marked and recorded in the line model for convenient reference and citation in subsequent steps.

[0036] Furthermore, multiple real-time images are collected based on the circumferential aerial survey of the wind power plant by the UAV. The multiple real-time images respectively present the real-time states of the wind power plant at different positions; multiple sub-guide line paths are determined according to the matching of the multiple functional areas and the multiple real-time images. The multiple functional areas and the multiple real-time images are introduced and matched, ensuring the accuracy of the multiple sub-guide line paths.

[0037] At this time, a UAV with a high-resolution camera and a stable flight control system is selected to ensure clear and stable images are captured during flight. According to the layout and scale of the wind power plant, a detailed flight plan is formulated, including flight altitude, speed, flight route, etc., to ensure that the UAV comprehensively covers all functional areas of the wind power plant. During the flight of the UAV, real-time images of the wind power plant are collected through the camera carried by it. These real-time images clearly show the real-time states of the wind power plant at different positions, including equipment operation status, line layout, environmental conditions, etc. The collected images are preliminarily processed, such as denoising and enhancing contrast, and then stored in a specified data storage device for subsequent analysis and use.

[0038] According to the functional areas divided above (such as power generation area, transmission area, distribution area, etc.), the location and range of these areas are identified in the real-time image, and the collected real-time image is matched and aligned with the line model of the wind power plant to ensure that the equipment in the image corresponds to the equipment in the model one by one. According to the matched image and model, the sub-conductor paths in each functional area are determined. These sub-conductor paths clearly show the line layout and connection relationship in each functional area.

[0039] Therefore, the conductor path of the wind power plant is determined based on multiple sub-conductor paths, multiple functional areas and the line model of the wind power plant. Multiple sub-conductor paths, multiple functional areas and the line model of the wind power plant are introduced, and multiple sub-conductor paths, multiple functional areas and the line model of the wind power plant are interacted with in multiple ways to ensure the accuracy of the conductor path of the wind power plant.

[0040] At this point, the sub-conductor paths within each functional area are integrated to form a complete conductor path map of the power plant. The integrated conductor path map is compared and updated with the original power plant line model to ensure that the line layout in the model is consistent with the actual situation. The updated line model is verified and checked to ensure the accuracy and reliability of the model, which is completed by combining it with on-site inspections of the actual power plant.

[0041] In another embodiment of the present application, the conductor path matching table is a method for matching multiple sub-conductor paths, functional areas, and elements in a line model. The following is a conductor path matching table (Table 1):

[0042] Table 1 Wire path matching table

[0043] Serial number Sub-conductor path Functional area Line model element Matching result 1 A-B-C Power generation area Generator 1 - Transformer 1 - Line 1 Match 2 D-E-F Power transmission area Line 2 - Switching station - Line 3 Match 3 G-H Power distribution area Line 4 - Distribution board Not matched (to be adjusted)

[0044] Table 1 lists multiple sub-conductor paths and their corresponding functional areas and corresponding elements in the line model. Through comparison and analysis, the matching relationship between the sub-conductor paths and the elements in the line model is determined, and then the final conductor path is determined. For example, in this embodiment, ABCD (i.e., power generation area-transmission area-distribution area-external power grid) can be used as the final conductor path.

[0045] Furthermore, in step S12, the corresponding rail-hanging robot is determined according to the wire path and wire diameter of the wind power plant, and the specific steps are as follows:

[0046] S121: Acquire the conductor path of the wind power plant;

[0047] S122: collecting the distribution position of each conductor based on the traversal of the conductor path of the wind power plant;

[0048] S123: determining a distribution style of the wires according to the distribution positions of the wires, the parallel states of the wires, and the surrounding environment of the wires;

[0049] S124: collecting multiple wire diameters based on the detection of each wire, and determining the wire diameter of the wire according to the multiple wire diameters and model information of the wire;

[0050] S125: Associating a conductor path of the wind power plant, a distribution style of the conductor, and a wire diameter of the conductor;

[0051] S126: determining first robot parameters according to the wire path of the wind power plant and the distribution style of the wires, and determining second robot parameters according to the wire path of the wind power plant and the wire diameter of the wires;

[0052] S127: Determine a corresponding rail-hanging robot based on the first robot parameters, the second robot parameters, and previous robot data of the wind power plant.

[0053] In this embodiment, the conductor path of the wind power plant is obtained; the distribution position of each conductor is collected based on the traversal of the conductor path of the wind power plant; the distribution style of the conductor is determined according to the distribution position of each conductor, the side-by-side state of each conductor and the surrounding environment of each conductor, thereby being compatible with the overall consideration of the distribution position of each conductor, the side-by-side state of each conductor and the surrounding environment of each conductor, realizing multi-dimensional control of the distribution position of each conductor, the side-by-side state of each conductor and the surrounding environment of each conductor, and ensuring the accuracy of the distribution style of the conductor.

[0054] At this time, the conductor path of the wind power plant is obtained, and the conductor path of the wind power plant is further controlled. All conductor paths in the wind power plant are traversed, including the collection lines from the booster station to each wind turbine unit, as well as the grid-connected lines, etc. During the traversal process, key information such as the direction, length, and height of each line is recorded in detail, and the collected conductor distribution location data is sorted and stored in a dedicated database for subsequent analysis and use.

[0055] According to the collected data on the distribution positions of the wires, analyze the overall layout and orientation of the wires, which helps to understand the spatial distribution characteristics of the wires and provides a basis for determining the wire distribution style later. Consider the side-by-side state between the wires, including the distance and angle of side-by-side. The side-by-side state will affect issues such as electromagnetic interference and heat dissipation of the wires and is considered when determining the wire distribution style. Evaluate the natural environment (such as terrain, landform, climate, etc.) and human environment (such as buildings, roads, farmland, etc.) around the wires. The above environmental factors will affect the safe operation and maintenance cost of the wires, so they are fully considered when determining the wire distribution style. The finally determined wire distribution style includes the orientation, arrangement method, height setting, etc. of the wires. When determining the distribution style, follow the principles of safety, economy, beauty, etc. to ensure the normal operation and maintenance of the wires.

[0056] Furthermore, collect multiple wire diameters based on the detection of each wire, and determine the wire diameter of the wire according to the multiple wire diameters and the wire model information, realizing the interaction of the multiple wire diameters and the wire model information, and then accurately controlling the wire diameter.

[0057] Therefore, associate the wire path, wire distribution style, and wire diameter of the wind power plant; determine the first robot parameters according to the wire path and wire distribution style of the wind power plant, and determine the second robot parameters according to the wire path and wire diameter of the wind power plant; determine the corresponding hanging rail robot based on the first robot parameters, the second robot parameters, and the previous robot data of the wind power plant, taking into account the overall consideration of the first robot parameters, the second robot parameters, and the previous robot data of the wind power plant, ensuring the matching accuracy of the hanging rail robot.

[0058] At this time, integrate the wire path, wire distribution style, and wire diameter data collected in the previous steps to ensure that each wire has corresponding path information, distribution style description, and wire diameter data. Further, integrate and associate the data through an association model. The association model can be in the form of a database, where each wire is used as a record, including its path coordinates, distribution style classification (such as dense, sparse, etc.), and wire diameter value.

[0059] Regarding the first robot parameters, the first robot parameters are mainly based on the wire path and wire distribution style. For example, if the wires are distributed along complex terrain, the robot requires higher mobility and obstacle avoidance capabilities. If the wires are densely arranged, the robot requires more precise navigation and positioning capabilities.

[0060] Regarding the second robot parameters, the second robot parameters are mainly based on the wire path and wire diameter. For example, wires with a larger wire diameter require stronger clamping force or a larger contact area to ensure safe operation. The complexity and length of the wire path also affect the power demand and battery life of the robot.

[0061] Meanwhile, when determining the parameters, the physical limitations of the robot (such as size, weight, etc.) and operation requirements (such as speed, accuracy, etc.) are also considered to ensure that the selected parameters not only meet the actual needs but also are within the capabilities of the robot. Optionally, the technical descriptions of the first robot parameters and the second robot parameters, the first robot parameter matching table (Table 2), and the second robot parameter matching table (Table 3) are as follows:

[0062] Table 2 Robot Parameter Matching Table

[0063]

[0064]

[0065] Table 3 Robot Parameter Matching Table

[0066] Conductor path feature Conductor diameter range Robot parameters Straight, obstacle-free Small (<2 mm) Lightweight gripper, precise control Zigzag, with a small number of obstacles Medium (2 - 5mm) Medium-strength gripper, good flexibility Complex terrain, many obstacles Large (>5mm) Heavy-duty gripper, high gripping force, wear-resistant design Any path, long distance Unlimited Long battery life, automatic charging system, fault warning

[0067] Furthermore, obtain the database of the wind power plant, collect the previous robot data of the wind power plant based on the traversal of the database of the wind power plant, and introduce the previous robot data of the wind power plant. The previous robot data of the wind power plant includes information such as the performance of the robot, maintenance records, failure rates, etc. This information helps to evaluate the potential of different robot models in meeting the current requirements. Combine the first robot parameters, the second robot parameters, and the previous data to evaluate and compare the available gantry robot models on the market, and select the most suitable robot model for the current requirements.

[0068] Specifically, assume that in a wind power plant, there are several wires, and each wire has been assigned a unique identifier. Now, integrate the path coordinates (such as GPS coordinates), distribution styles (such as "distributed along the ridge", "densely arranged", etc.), and wire diameter data (such as 2.5mm, 4.0mm, etc.) of each wire into a database. Each wire is used as a record in the database, and all its relevant information is associated together.

[0069] Suppose there is a group of wires distributed along a steep hillside and with a large wire diameter. Based on this information, the following first robot parameters are determined for the gantry robot: a highly maneuverable chassis to adapt to complex terrains, and an advanced obstacle avoidance system to ensure safe operation. At the same time, due to the large wire diameter, the following second robot parameters are determined: an enhanced clamping mechanism to provide sufficient clamping force, and a large-capacity battery to support long-term continuous operation.

[0070] Based on the previously determined first and second robot parameters and the robot data used in the past, multiple types of rail-mounted robots were evaluated and compared, and finally the robot type was determined. After the selected type was determined, on-site tests were carried out to ensure that the selected robot could operate effectively in the wind power plant environment.

[0071] In step S13, multiple current parameters are collected based on the dynamic detection of the wire by the rail-mounted robot, and the current power distribution map is constructed according to the multiple current parameters and the detection positions of the wire. The specific steps are as follows:

[0072] S131: Interact with the wire path of the wind power plant and the position where the rail-mounted robot is located;

[0073] S132: Determine the inspection route of the rail-mounted robot based on the interaction between the wire path of the wind power plant and the position where the rail-mounted robot is located;

[0074] S133: The rail-mounted robot travels dynamically on the wire along the inspection route and triggers the dynamic detection of the wire by the rail-mounted robot;

[0075] S134: Collect multiple current parameters based on the dynamic detection of the wire by the rail-mounted robot;

[0076] S135: Match the multiple current parameters with the detection positions of each wire;

[0077] S136: Construct the current power distribution map based on the multiple current parameters and the detection positions of the wire.

[0078] Among them, interact with the wire path of the wind power plant and the position where the rail-mounted robot is located; determine the inspection route of the rail-mounted robot based on the interaction between the wire path of the wind power plant and the position where the rail-mounted robot is located, and realize the interaction between the wire path of the wind power plant and the position where the rail-mounted robot is located to ensure the accuracy of the inspection route of the rail-mounted robot.

[0079] Furthermore, obtain the wire path of the wind power plant and the position where the rail-mounted robot is located. In S131, the wire path of the wind power plant is usually obtained through CAD drawings, GIS systems or on-site surveys. The wire path information includes parameters such as the starting point, ending point, turning point, height, and type of the wire. And the rail-mounted robot is usually equipped with a GPS positioning module or other positioning technologies (such as RFID, visual positioning, etc.) and can obtain its own position information on the wire path in real time.

[0080] In addition, according to the characteristics of the transmission line path in the wind power plant and the performance parameters of the hanging rail robot, and further interacting the characteristics of the transmission line path in the wind power plant and the performance parameters of the hanging rail robot, so as to generate one or more inspection routes according to the transmission line path information and the real-time position information of the hanging rail robot. The inspection route includes information such as the starting position of the robot, the inspection points (i.e., the detected wire positions), and the ending position.

[0081] Furthermore, through S133 and S134, the dynamic acquisition of multiple current parameters and the corresponding acquisition accuracy can be ensured. The hanging rail robot is equipped with sensors and detection devices for real-time monitoring of the wire state. When the hanging rail robot travels to a preset inspection point, the corresponding detection device is automatically triggered to perform real-time data transmission inspection on the wire.

[0082] Suppose in a large wind power plant, the hanging rail robot travels along the preset inspection route on the wire. When the hanging rail robot travels to the inspection point of a certain key wire, devices such as an infrared thermal imager and a current sensor are automatically triggered. The infrared thermal imager is used to monitor the temperature distribution of the wire to detect potential overheating problems; while the current sensor is used to monitor the current magnitude of the wire in real time to determine whether there are abnormalities such as overload or short circuit. The robot transmits the detection data to the ground monitoring center in real time for the operator to analyze and process.

[0083] For example, when the hanging rail robot performs dynamic detection on a certain key wire, it can collect multiple current parameters. After being processed and analyzed by the ground monitoring center, it is found that the current magnitude of the wire shows abnormal fluctuations and the harmonic content exceeds the preset threshold. At this time, the system issues a warning signal to prompt the maintenance personnel to conduct further inspections and processing on the wire.

[0084] Therefore, multiple current parameters match the detection positions of each wire; based on the multiple current parameters and the detection positions of the wire, the current power distribution map is constructed. The multiple current parameters and the detection positions of the wire can be considered as a whole to ensure the construction accuracy of the current power distribution map.

[0085] At this time, a preset data matching mechanism is collected to ensure that the collected current parameters can be accurately matched to the corresponding detection position information. The detection position information includes various types such as time stamps, position marks, and wire numbers. After the data matching is completed, the system also verifies the data to ensure the accuracy and integrity of the matching.

[0086] Meanwhile, based on the collected current parameters and wire detection location information, the system provides an intuitive display method for the power distribution map. The power distribution map includes the distribution of various parameters such as the current magnitude, phase angle, and harmonic content of the wire, as well as information such as the connection relationship between wires and the power flow direction. At the same time, to achieve the visual display of the power distribution map, the system adopts advanced data visualization technologies, including two-dimensional or three-dimensional graphic display, dynamic data refresh, color coding, etc., so that the operator can intuitively understand the operating state of the power system.

[0087] In step S14, based on the current power distribution map, determine the fault location in the wind power plant. The specific steps are as follows:

[0088] S141: Obtain the current power distribution map;

[0089] S142: Determine the abnormal interval of power based on the self-detection of the current power distribution map;

[0090] S143: Collect multiple operating parameters of the wind power plant, and determine the current power generation mode of the wind power plant according to the multiple operating parameters of the wind power plant and the recorded power generation mode of the wind power plant;

[0091] S144: Determine the loss location of the wind power plant according to the current power distribution map and the loss mark of the wind power plant;

[0092] S145: Correlate the abnormal interval of power, the current power generation mode of the wind power plant, and the loss location of the wind power plant;

[0093] S146: Determine the first fault range based on the abnormal interval of power and the current power generation mode of the wind power plant, determine the second fault range according to the abnormal interval of power and the loss location of the wind power plant, and judge the fault location of the wind power plant according to the first fault range, the second fault range, and the line model of the wind power plant.

[0094] Thus, by obtaining the current power distribution map and determining the abnormal interval of power based on the self-detection of the current power distribution map, the self-detection of the current power distribution map is realized, ensuring the screening of the abnormal interval of power, so as to facilitate the subsequent control of the abnormal interval of power.

[0095] Input the current power distribution map into a preset anomaly detection model. By calculating the anomaly scores or probabilities of each data point, identify potential anomaly intervals. Based on the output results of the anomaly detection algorithm and in combination with preset thresholds or rules, determine the anomaly intervals in the power distribution map, so as to represent the areas where parameters such as current and voltage significantly deviate from the normal range through the said anomaly intervals. Optionally, verify the determined anomaly intervals by means such as comparing with historical data, on-site investigation or expert judgment.

[0096] Further, in S143, by introducing multiple working parameters of the wind power plant and the power generation modes recorded by the wind power plant, realize the interaction of the multiple working parameters of the wind power plant and the power generation modes recorded by the wind power plant, and ensure the accuracy of the current power generation mode of the wind power plant.

[0097] At this time, through sensors, monitoring systems or other data collection means, obtain the key working parameters of the wind power plant in real time, including but not limited to wind speed, wind direction, generator speed, output power, gearbox temperature, generator winding temperature, etc., so as to reflect the operating state and performance of the wind turbine through the said key working parameters.

[0098] Further, according to the design and operation records of the wind power plant, the power generation modes of the generator under different wind speed conditions can be understood, such as rated power output mode, low wind speed operation mode, variable speed constant frequency mode, etc. Compare the collected working parameters with the known power generation modes, and analyze whether the current working parameters conform to a certain specific power generation mode. If the matching degree of the working parameters with a certain power generation mode is the highest, it is considered that the current generator is operating in that mode.

[0099] Further, determine the loss occurrence location of the wind power plant according to the current power distribution map and the loss marks of the wind power plant, so as to conduct overall management and control of the current power distribution map and the loss marks of the wind power plant.

[0100] At this time, by viewing the power distribution map, understand the parameters such as current, voltage, power factor, etc. of each wire in the power system, as well as the abnormal changes of the parameters, and determine the losses or faults in the power transmission process according to the abnormal changes of the parameters. Identify the loss or fault marks inside the wind power plant on the power distribution map, such as resistance loss, inductance loss, transformer fault, etc. These loss or fault marks are usually marked according to the operation data and historical experience of the power plant, reflecting the loss or fault conditions of each part inside the power plant. Thus, by combining the power distribution map, loss or fault marks, the specific location where the loss or fault occurs can be analyzed. If the current in a certain area increases abnormally or the voltage decreases abnormally, and there are loss or fault marks in this area, then it is determined that this area is the loss or fault occurrence location.

[0101] Suppose that on the power distribution map, it is observed that the current of a transmission line from a wind turbine to a substation has increased abnormally. At the same time, in the internal loss or fault marks of the power plant, a large resistance loss mark is found near this transmission line. Combining these two pieces of information, it is analyzed that the increase in loss of this transmission line is caused by excessive resistance or poor contact, etc. Therefore, it is determined that this transmission line is the place where the loss occurs, and it is recommended to carry out maintenance or replacement to reduce the loss.

[0102] Therefore, associate the abnormal interval of power, the current power generation mode of the wind power plant, and the loss occurrence location of the wind power plant; determine the first fault range based on the abnormal interval of power and the current power generation mode of the wind power plant, determine the second fault range according to the abnormal interval of power and the loss occurrence location of the wind power plant, and judge the fault occurrence location of the wind power plant according to the first fault range, the second fault range, and the line model of the wind power plant. Considering the overall situation of the first fault range, the second fault range, and the line model of the wind power plant, a multi-dimensional judgment of the fault occurrence location of the wind power plant is realized, and the accuracy of the fault occurrence location of the wind power plant is improved.

[0103] Furthermore, determine the first fault range based on the abnormal interval of power and the current power generation mode of the wind power plant. At this time, analyze the relationship between the abnormal interval of power and the current power generation mode, determine the cause or component that leads to the abnormality, and delimit a preliminary fault range in the power system according to this cause or component, that is, the first fault range;

[0104] And, determine the second fault range according to the abnormal interval of power and the loss occurrence location of the wind power plant. At this time, combine the information of the abnormal interval of power and the loss occurrence location to further narrow the fault range. If the loss occurrence location is spatially close or temporally related to the abnormal interval of power, these areas will be included in the second fault range.

[0105] Furthermore, use the line model of the wind power plant to cross-verify the first fault range and the second fault range. The line model usually includes information such as the physical layout, component parameters, and operating characteristics of the power system to determine the fault occurrence location.

[0106] The first fault range includes: the transmission line with abnormally increased current in the transmission line and its nearby components under the rated power output mode;

[0107] The second fault range includes: the line and its connection points where the loss coincides with the abnormality in time;

[0108] The fault occurrence location includes: the connection point of the transmission line where the current increases abnormally and has resistance loss.

[0109] In step S15, multiple fault parameters are determined based on the re-inspection of the fault occurrence location by the gantry robot. A fault event is determined based on the multiple fault parameters, the re-inspection locations of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant. The specific steps are as follows:

[0110] S151: Obtain the fault occurrence location of the wind power plant;

[0111] S152: Trigger the movement of the gantry robot according to the fault occurrence location of the wind power plant, and the gantry robot re-inspects the fault occurrence location;

[0112] S153: Determine multiple fault parameters based on the re-inspection of the fault occurrence location by the gantry robot. At this time, determine the corresponding re-inspection mode according to the actual image of the fault occurrence location, the re-inspection range of the gantry robot for the fault occurrence location, and the importance coefficient of the fault occurrence location relative to the wind power plant;

[0113] S154: Obtain multiple fault parameters, and sort the multiple fault parameters according to their magnitudes to form a fault parameter set;

[0114] S155: Associate the fault parameter set, the re-inspection locations of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant.

[0115] S156: Perform multiple interactions on the fault parameter set, the re-inspection locations of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant, and determine a fault event based on the multiple interactions of the fault parameter set, the re-inspection locations of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant.

[0116] Thus, after determining the fault occurrence location of the wind power plant, the system will immediately dispatch the gantry robot to that location. Further, during the movement of the robot, multiple fault parameters are determined based on the re-inspection of the fault occurrence location by the gantry robot. At this time, determine the corresponding re-inspection mode according to the actual image of the fault occurrence location, the re-inspection range of the gantry robot for the fault occurrence location, and the importance coefficient of the fault occurrence location relative to the wind power plant, and the gantry robot performs targeted re-inspection on the fault occurrence location along this re-inspection mode.

[0117] The fault parameters include wear degree, temperature anomaly, vibration level, electrical performance, etc. After determining the fault parameters, the system will determine the corresponding re-inspection mode according to the actual image of the fault occurrence location, the re-inspection range, and the importance coefficient of this location relative to the wind power plant. The re-inspection modes include detailed detection, real-time monitoring, regular inspection, etc. Once the re-inspection mode is determined, the gantry robot will perform comprehensive physical and electrical inspections on the fault occurrence location according to the re-inspection mode.

[0118] Therefore, multiple fault parameters are obtained, and the multiple fault parameters are sorted according to their magnitudes to form a fault parameter set; the fault parameter set, the review positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant are associated, realizing multiple interactions among the fault parameter set, the review positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant.

[0119] At this time, the hanging rail robot or other detection equipment has completed a detailed review of the fault occurrence location and collected multiple parameters related to the fault. These parameters include the degree of physical wear, abnormal temperature values, vibration amplitude, and the degree of decline in electrical performance, etc. Each collected fault parameter is evaluated to determine its severity and impact on the operation of the wind power plant.

[0120] Furthermore, in this embodiment, the fault parameter set is also associated with the review position of the fault occurrence location, and the fault parameter set is associated with the service life of the wind power plant to be used for evaluating whether the fault is related to factors such as equipment aging and insufficient maintenance, so as to formulate a more effective repair and maintenance plan.

[0121] Furthermore, multiple interactions are performed on the fault parameter set, the review positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant, and a fault event is determined based on the multiple interactions of the fault parameter set, the review positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant, accommodating the overall consideration of the fault parameter set, the review positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant, ensuring the accuracy of the fault event.

[0122] Specifically, assume that in a wind power plant, the hanging rail robot's review discovers a gearbox fault and collects the following fault parameter set:

[0123] Degree of gear wear: Severe (wear amount exceeds 70% of the normal value); Abnormal oil temperature value: Extremely high (40°C higher than the normal oil temperature); Vibration amplitude: Significant (amplitude far exceeds the normal range); The review position shows in the high-speed shaft area of the gearbox, and this wind power plant has been operating for 15 years, approaching its design life.

[0124] It indicates that wear leads to increased friction, which in turn generates more heat. The significant increase in vibration amplitude is related to the imbalance or damage of the gear, which may be caused by long-term wear, and the gearbox has approached or reached its design life, so it is more prone to failure.

[0125] Based on these analyses, the system will determine the following fault event:

[0126] Fault event: Severe wear in the high-speed shaft area of the gearbox, resulting in abnormal increase in oil temperature and significant increase in vibration amplitude;

[0127] Reason: Gear wear caused by long-term operation, combined with equipment aging approaching the design life;

[0128] Influence: If not dealt with in time, it will cause the complete failure of the gearbox, thereby affecting the operation of the entire wind turbine.

[0129] Furthermore, the relationships among the fault parameter set, the recheck position, the service life, and the fault event can be presented in the form of a fault event matching table (Table 4).

[0130] Table 4 Fault Event Matching Table

[0131]

[0132] Thus, through the above fault event matching table, each fault event and its corresponding fault parameters, recheck positions, and service life can be intuitively determined.

[0133] In step S16, according to the fault event, the judgment module of the hanging rail robot, and the repair tools possessed by the hanging rail robot, the corresponding repair operation trajectory is determined. The specific steps are as follows:

[0134] S161: Obtain the fault event;

[0135] S162: Construct a first training set for the previous detection data of the hanging rail robot and the corresponding judgment results;

[0136] S163: Form the judgment module of the hanging rail robot through self-training of the first training set in each fault dimension;

[0137] S164: Determine multiple repair plans according to the fault event and the judgment module of the hanging rail robot;

[0138] S165: Determine the best repair plan according to multiple repair plans, the corresponding repair difficulty coefficients, and the repair tools possessed by the hanging rail robot;

[0139] S166: Determine the corresponding repair nodes according to the best repair plan, the fault event, and the hanging rail robot, and mark the corresponding repair operation trajectory at the repair nodes.

[0140] In the embodiment of the present application, obtaining the fault event; constructing a first training set for the previous detection data of the hanging rail robot and the corresponding judgment results; forming the judgment module of the hanging rail robot through self-training of the first training set in each fault dimension ensures the training of the judgment module of the hanging rail robot and improves the accuracy of the judgment module of the hanging rail robot.

[0141] Among them, the input data mainly refers to the set of fault parameters detected by the hanging-rail robot at different times and positions. The set of fault parameters includes severe wear, high oil temperature, abnormal vibration, and decreased electrical performance. Further, the input data can be judged manually to determine the fault situation, or the input data can be input into a trained model, and the model outputs the fault prediction results, including the type, location, severity, etc. of the fault.

[0142] Among them, the training of the model includes: using the first training set to train the judgment module of the hanging-rail robot. This judgment module is a machine learning or deep learning algorithm that can extract useful features from the input data and make accurate fault judgments based on these features. At this time, different machine learning or deep learning algorithms are selected to train the judgment module according to the complexity of the problem and the availability of data, such as neural networks, etc. During the training process, the algorithm will automatically extract useful features from the input data. These features are certain statistics of the original data (such as mean, variance, peak value, etc.), and are also obtained through more complex transformations or combinations. To improve the accuracy of the judgment module, the model is usually optimized, which includes adjusting the hyperparameters of the algorithm (such as learning rate, number of iterations, etc.), selecting the best feature combination, and using techniques such as cross-validation to evaluate the performance of the model. After the training is completed, the model is evaluated to verify its performance.

[0143] Specifically, assume that the hanging-rail robot has regularly detected the gearbox in a wind power plant in the past year, and the vibration data, temperature data, and sound data of the gearbox have been recorded each time. At the same time, after each detection, technical experts will judge whether there is a fault in the gearbox based on these data and give the specific fault type and location.

[0144] Now, organize these detection data and judgment results into a training set. First, take all the detection data (vibration data, temperature data, sound data) as the input data, and then take the judgment results of the technical experts (fault type, location) as the output data. Before inputting the data into the training algorithm, the original data is also cleaned and preprocessed, such as removing abnormal data points caused by equipment failures or environmental interferences.

[0145] A training set is constructed with vibration data, temperature data, and sound data as input data, and the judgment results of technical experts as output data. Now, this training set will be used to train the judgment module of the hanging rail robot. A deep learning algorithm (such as Convolutional Neural Network CNN) is selected to train the judgment module. During the training process, the algorithm extracts useful features from the input data, such as vibration frequency, temperature gradient, sound spectrum, etc. Then, the algorithm uses these features to train a classifier to distinguish different types of faults (such as gear wear, bearing faults, etc.).

[0146] After the training is completed, an independent test data set is used to evaluate the performance of the model. The results show that the model has high accuracy and recall rate in the judgment of gearbox faults. Therefore, this trained judgment module is integrated into the control system of the hanging rail robot, enabling it to autonomously detect and judge gearbox faults in wind power plants.

[0147] Furthermore, multiple repair solutions are determined based on the fault event and the judgment module of the hanging rail robot. Considering the overall situation of the fault event and the judgment module of the hanging rail robot, the judgment of the fault event by the judgment module of the hanging rail robot is realized, and then multiple repair solutions are output, ensuring the rationality of the multiple repair solutions.

[0148] At this time, during the inspection process of the hanging rail robot, its built-in self-diagnosis system will continuously monitor the operating status of each component and functional module. Once an abnormality occurs in a certain key part, such as current fluctuation of the walking drive motor, deviation of sensor data, abnormal battery charging and discharging, etc., the hanging rail robot can quickly detect and accurately locate the fault point.

[0149] When the fault is identified, the judgment module of the hanging rail robot will be immediately activated. The judgment module of the hanging rail robot quickly analyzes the fault type through the built-in algorithm, and initially judges whether it is caused by hardware aging and wear, software program errors, or complex environmental interference. Based on the fault type and judgment results, the judgment module will generate multiple repair solutions.

[0150] Suppose the hanging rail robot suddenly finds that the current of the walking drive motor fluctuates abnormally during the underground inspection, resulting in the robot walking stuck. The following is the process of determining the repair solution for this fault event:

[0151] The robot's self-diagnosis system monitors the current fluctuation of the walking drive motor and locates the fault point as the drive motor. The judgment module analyzes the current fluctuation data and initially judges that it is caused by motor aging, signal transmission obstruction in the control system, or foreign objects on the track.

[0152] Solution 1: If it is determined that the motor is aging, replace it with a new drive motor. At this time, the robot automatically sends a fault alarm and detailed information to the ground control center, and requests to dispatch maintenance personnel to carry a new motor for replacement.

[0153] Solution 2: If it is determined that the signal transmission of the control system is blocked, it may be due to a software program error or a signal line fault in the control system. At this time, the personnel in the ground control center can debug or update the software through remote control, or command the robot to restart the control system function module. If the remote control is ineffective, dispatch maintenance personnel to the site to check the signal line and repair it.

[0154] Solution 3: If it is determined that there is a foreign object blocking the track, the robot adjusts its position by itself to avoid the foreign object. If it cannot be avoided, activate the braking device to fix it on the track, and continuously send a distress signal waiting for rescue. After receiving the alarm, the ground control center dispatches maintenance personnel to the site to clean up the foreign object.

[0155] Thus, the hanging-rail robot can quickly identify the fault point through the built-in self-diagnosis system and judgment module, and generate corresponding repair solutions for the remote operation or on-site maintenance of the ground control center.

[0156] Furthermore, determine the best repair solution according to multiple repair solutions, the corresponding difficulty coefficients of repair, and the repair tools available to the hanging-rail robot, taking into account the overall consideration of multiple repair solutions, the corresponding difficulty coefficients of repair, and the repair tools available to the hanging-rail robot, ensuring the accuracy of the best repair solution.

[0157] In addition, the repair solution is determined according to the repair influencing factors, where the repair influencing factors include the feasibility of the repair solution, the difficulty coefficient of repair, and the self-repair ability of the hanging-rail robot. Specifically, assume that during the inspection process, the hanging-rail robot finds that a section of the track has serious wear. For repair, the system generates the following two repair solutions based on the fault event and the judgment module:

[0158] Solution 1: Use the simple grinding tool carried by the robot to grind the worn part. This solution is simple and easy to implement, but it takes multiple round trips of grinding to achieve the ideal repair effect, and it has a high energy consumption and time cost for the robot.

[0159] Solution 2: Dispatch professional maintenance personnel to the site with professional welding equipment for welding repair. This solution has a better repair effect, but it is necessary to wait for the maintenance personnel to arrive, and the welding operation has high requirements for the environment and skills.

[0160] Considering factors such as repair effect, time cost, robot energy consumption, and availability of maintenance personnel, the system finally selects Solution 2 as the best repair solution.

[0161] Therefore, according to the optimal repair plan, the fault event, and the hanging-rail robot, the corresponding repair node is determined, and the corresponding repair operation trajectory is marked at this repair node. Control is carried out for this repair node and the corresponding repair operation trajectory, so that the hanging-rail robot can trigger the corresponding repair for the fault event.

[0162] At this time, according to the optimal repair plan, the specific repair location and time point, that is, the repair node, are determined. The repair node is usually at the location where the fault occurs. After determining the repair node, the system marks the corresponding repair operation trajectory in the navigation system of the hanging-rail robot. This trajectory is the optimal path for the robot to reach the repair node from the current position. The purpose of determining and marking the repair operation trajectory is to ensure that the robot can accurately reach the repair position and perform the repair according to the predetermined operation steps.

[0163] For example, when the system selects the above-mentioned second solution as the optimal repair plan and determines the specific position of the worn part on the track as the repair node, the system marks the optimal path from the current position of the hanging-rail robot to the repair node in the navigation system of the hanging-rail robot, and the robot reaches the repair position according to the optimal path.

[0164] After the robot reaches the repair position, the system will guide the robot to perform welding repair according to the predetermined operation steps to accurately complete the repair task.

[0165] Embodiment 2:

[0166] In another embodiment of the present application, by comparing the first fault range, the second fault range, and the key information in the line model of the wind power plant, the fault occurrence location is determined. The fault occurrence location matching table usually contains the corresponding relationships of fault characteristics, causes, and fault locations.

[0167] Suppose there is the following fault occurrence location matching table (Table 5):

[0168] Table 5 Fault Occurrence Location Matching Table

[0169]

[0170] The first fault range: the transmission line with an abnormally increased current and its nearby components, the second fault range: the transmission line with a resistance loss mark and its connection points. Comparing this information with the matching table, it is found that: an abnormally increased current in the transmission line corresponds to reasons such as "overload, poor contact, insulation damage", and the fault location is at "transmission line, connection point, insulator"; an increased resistance loss corresponds to reasons such as "resistance aging, poor contact, corrosion", and the fault location is at "resistor, connection point, line outer skin". Combining the first fault range and the second fault range, it is determined that the fault is most likely to occur at

[0171] "Connection points of transmission lines", because this is the location involved in both fault scopes.

[0172] Embodiment 3:

[0173] In another embodiment of the present application, in order to more scientifically determine the best repair plan, a method of weights and scores can be used to determine the best repair plan. For example:

[0174] Set three evaluation indicators: repair effect (weight 0.5), repair cost (weight 0.3), and repair time (weight 0.2).

[0175] Plan 1: Repair effect (7 points, because the effect is limited), repair cost (9 points, because the cost is low), repair time (8 points, because of multiple round trips but short single - time). Plan 2: Repair effect (9 points, because the effect is good), repair cost (7 points, because of external support but low equipment cost), repair time (7 points, because of waiting for maintenance personnel to arrive but fast repair process). Plan 3: Repair effect (10 points, because it solves the problem thoroughly), repair cost (5 points, because the cost is high), repair time (5 points, because of a long cycle).

[0176] Plan 1: Weighted score = 0.5×7 + 0.3×9 + 0.2×8 = 3.5 + 2.7 + 1.6 = 7.8 points; Plan 2: Weighted score = 0.5×9 + 0.3×7 + 0.2×7 = 4.5 + 2.1 + 1.4 = 8.0 points; Plan 3: Weighted score = 0.5×10 + 0.3×5 + 0.2×5 = 5.0 + 1.5 + 1.0 = 7.5 points; According to the weighted scores, Plan 2 has the highest score (8.0 points), so it is determined as the best repair plan.

[0177] Embodiment 3

[0178] Please refer to Figure 3 , Figure 3 is a schematic structural composition diagram of a wind power plant fault judgment system based on a hanging - rail robot provided in this embodiment. It can implement the wind power plant fault judgment method described in Embodiment 1 or 2. The wind power plant fault judgment system based on a hanging - rail robot includes:

[0179] A wire path module 21, configured to determine the wire path of the wind power plant based on the line model of the wind power plant;

[0180] A robot module 22, configured to determine the corresponding hanging - rail robot according to the wire path of the wind power plant and the wire diameter of the wire;

[0181] A power distribution map module 23, configured to collect a plurality of current parameters based on the dynamic detection of the wire by the hanging - rail robot, and construct the current power distribution map according to the plurality of current parameters and the detection position of the wire;

[0182] The fault occurrence location module 24 is configured to determine the fault occurrence location of the wind power plant according to the current power distribution map;

[0183] The fault event module 25 is configured to determine a plurality of fault parameters based on the re-inspection of the fault occurrence location by the hanging rail robot, and determine the fault event according to the plurality of fault parameters, the re-inspection positions of the plurality of fault parameters relative to the fault occurrence location, and the service life of the wind power plant;

[0184] The repair module 26 is configured to determine the corresponding repair operation trajectory according to the fault event, the judgment module of the hanging rail robot, and the repair tools possessed by the hanging rail robot.

[0185] For any combination of the technical features of the above embodiments, for the sake of brevity of description, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

Claims

1. A fault judgment method for a wind power plant based on a hanging-rail robot, characterized in that, Including: Determine the wire path of the wind power plant based on the line model of the wind power plant; Determine the corresponding rail-mounted robot according to the wire path of the wind power plant and the wire diameter of the wire; Collect multiple current parameters based on the dynamic detection of the wire by the rail-mounted robot, and construct the current power distribution map according to the multiple current parameters and the detection position of the wire; Judge the fault occurrence location of the wind power plant according to the current power distribution map; Determine multiple fault parameters according to the re-inspection of the fault occurrence location by the rail-mounted robot, and determine the fault event according to the multiple fault parameters, the re-inspection position of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant; Determine the corresponding repair operation trajectory according to the fault event, the judgment module of the rail-mounted robot, and the repair tools possessed by the rail-mounted robot.

2. The wind power plant fault judgment method according to claim 1, wherein The determination of the wire path of the wind power plant based on the line model of the wind power plant includes: Collect the line model of the wind power plant; Determine multiple functional areas based on the division of the line model of the wind power plant; Collect multiple real-time images based on the circumferential aerial survey of the wind power plant by the unmanned aerial vehicle, and the multiple real-time images respectively present the real-time states of the wind power plant at different positions; Determine multiple sub-wire paths according to the matching of the multiple functional areas and the multiple real-time images; Determine the wire path of the wind power plant based on the multiple sub-wire paths, the multiple functional areas, and the line model of the wind power plant.

3. The method for judging faults in a wind power plant according to claim 2, characterized in that, The determination of the corresponding rail-mounted robot according to the wire path of the wind power plant and the wire diameter of the wire includes: Obtain the wire path of the wind power plant; Collect the distribution positions of each wire based on the traversal of the wire path of the wind power plant; Determine the distribution style of the wire according to the distribution positions of each wire, the side-by-side state of each wire, and the surrounding environment of each wire; Collect multiple wire diameters based on the detection of each wire, and determine the wire diameter of the wire according to the multiple wire diameters and the model information of the wire; Associate the wire path of the wind power plant, the distribution style of the wire, and the wire diameter of the wire; Determine the first robot parameter according to the wire path of the wind power plant and the distribution style of the wire, and determine the second robot parameter according to the wire path of the wind power plant and the wire diameter of the wire; Determine the corresponding rail-mounted robot based on the first robot parameter, the second robot parameter, and the previous robot data of the wind power plant.

4. The method for judging faults in a wind power plant according to claim 3, characterized in that, The collection of multiple current parameters based on the dynamic detection of the wire by the rail-mounted robot, and the construction of the current power distribution map according to the multiple current parameters and the detection position of the wire includes: Interact with the wire path of the wind power plant and the position where the rail-mounted robot is located; Determine the inspection route of the rail-mounted robot based on the interaction between the wire path of the wind power plant and the position where the rail-mounted robot is located; The rail-mounted robot dynamically travels on the wire along the inspection route, and triggers the dynamic detection of the wire by the rail-mounted robot; Collect multiple current parameters based on the dynamic detection of the wire by the rail-mounted robot; The multiple current parameters match the detection positions of each wire; Construct the current power distribution map according to the multiple current parameters and the detection position of the wire.

5. The method for judging faults in a wind power plant according to any one of claims 1 to 4, characterized in that, Determining the fault location of a wind power plant based on the current power distribution map includes: Obtaining the current power distribution map; Determining the abnormal interval of power based on the autonomous detection of the current power distribution map; Collecting multiple working parameters of the wind power plant, and determining the current power generation mode of the wind power plant according to the multiple working parameters of the wind power plant and the power generation mode recorded in the wind power plant; Determining the loss location of the wind power plant according to the current power distribution map and the loss mark of the wind power plant; Associating the abnormal interval of power, the current power generation mode of the wind power plant, and the loss location of the wind power plant; Determining the first fault range based on the abnormal interval of power and the current power generation mode of the wind power plant, determining the second fault range according to the abnormal interval of power and the loss location of the wind power plant, and judging the fault location of the wind power plant according to the first fault range, the second fault range, and the line model of the wind power plant.

6. The method for judging faults in a wind power plant according to claim 5, characterized in that, Determining multiple fault parameters according to the re-inspection of the fault location by the hanging rail robot, and determining the fault event according to the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault location, and the service life of the wind power plant, including: Obtaining the fault location of the wind power plant; Triggering the movement of the hanging rail robot according to the fault location of the wind power plant, and the hanging rail robot re-inspects the fault location; Determining multiple fault parameters based on the re-inspection of the fault location by the hanging rail robot. At this time, according to the actual image of the fault location, the re-inspection range of the hanging rail robot for the fault location, and the importance coefficient of the fault location relative to the wind power plant, the corresponding re-inspection mode is determined.

7. The method for judging faults in a wind power plant according to claim 6, characterized in that, Determining multiple fault parameters according to the re-inspection of the fault location by the hanging rail robot, and determining the fault event according to the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault location, and the service life of the wind power plant, further includes: Obtaining multiple fault parameters, and sorting the multiple fault parameters according to their magnitudes to form a fault parameter set; Associating the fault parameter set, the re-inspection positions of the multiple fault parameters relative to the fault location, and the service life of the wind power plant. Performing multiple interactions on the fault parameter set, the re-inspection positions of the multiple fault parameters relative to the fault location, and the service life of the wind power plant, and determining the fault event according to the multiple interactions of the fault parameter set, the re-inspection positions of the multiple fault parameters relative to the fault location, and the service life of the wind power plant.

8. The method for fault judgment of a wind power plant according to claim 7, characterized in that, Determining the corresponding repair operation trajectory according to the fault event, the judgment module of the hanging rail robot, and the repair tools possessed by the hanging rail robot, including: Obtaining the fault event; Constructing a first training set from the previous detection data of the hanging rail robot and the corresponding judgment results; Forming the judgment module of the hanging rail robot through autonomous training in each fault dimension based on the first training set.

9. The method for judging faults in a wind power plant according to claim 8, characterized in that, Determining the corresponding repair operation trajectory according to the fault event, the judgment module of the hanging rail robot, and the repair tools possessed by the hanging rail robot, further includes: Determining multiple repair plans according to the fault event and the judgment module of the hanging rail robot; Determine the optimal repair plan based on multiple repair plans, the corresponding repair difficulty coefficients, and the repair tools available to the rail-mounted robot; Determine the corresponding repair nodes based on the optimal repair plan, the fault event, and the rail-mounted robot, and mark the corresponding repair operation trajectories at these repair nodes.

10. A fault judgment system for a wind power plant based on a hanging rail robot, characterized in that, The wind power plant fault judgment system based on a rail-mounted robot is applied to the wind power plant fault judgment method based on a rail-mounted robot as described in any one of claims 1-9. The wind power plant fault judgment system based on a rail-mounted robot includes: A wire path module for determining the wire path of the wind power plant based on the wire path model of the wind power plant; A robot module for determining the corresponding rail-mounted robot according to the wire path of the wind power plant and the wire diameter of the wire; A power distribution map module for collecting multiple current parameters based on the dynamic detection of the wire by the rail-mounted robot, and constructing the current power distribution map according to the multiple current parameters and the detection positions of the wire; A fault occurrence location module for judging the fault occurrence location of the wind power plant according to the current power distribution map; A fault event module for determining multiple fault parameters based on the re-inspection of the fault occurrence location by the rail-mounted robot, and determining the fault event according to the multiple fault parameters, the re-inspection positions of the multiple fault parameters relative to the fault occurrence location, and the service life of the wind power plant; A repair module for determining the corresponding repair operation trajectory according to the fault event, the judgment module of the rail-mounted robot, and the repair tools available to the rail-mounted robot.

Images