Offshore wind power transmission system fault location method and system based on virtual reality

Abstract

The present invention discloses a fault location method and system for an offshore wind power transmission system based on virtual reality, which is applied to fault location technology. First, a virtual scene is constructed. The virtual scene can be displayed through a VR device or a display device, and each device of the offshore wind power transmission system is simulated and restored. Then, operation attributes are given to each device in the virtual scene, including working parameters for normal operation of each device, working parameter thresholds allowed for faults, etc.; finally, an Unreal Engine is imported to update the virtual scene data in real time, and the operating status of the offshore wind power transmission system is simulated. The fault point is characterized according to the data of each instrument, and a pop-up window is used to remind the fault through a display device or a VR device; in addition, by constructing a fault simulation library and combining the working parameters to predict the fault trend and perform fault prediction, the offshore wind power transmission system fault can be monitored in real time, and the occurrence of faults can be avoided in time by predicting the faults, thereby reducing property losses, etc.

Description

Technical Field

[0001] The present invention relates to the technical field of fault location, and more particularly to a method and system for locating faults in an offshore wind power transmission system based on virtual reality. Background Art

[0002] Fault location in offshore wind power transmission systems has always been a key challenge. Offshore wind power transmission systems are complex in structure, and hidden dangers and defects in various locations can lead to failures. Furthermore, different operating environments can significantly impact the operating status of wind power transmission systems. Consequently, offshore wind power transmission systems present a wide variety of faults, with complex cross-correlations among these fault hazards. The application of big data technology can extract more valuable information from this complex and vast data set. However, operators rely on extensive work experience to identify the fault using instrumentation. Furthermore, repairs typically require that a fault already occur or have occurred for some time before they can be performed. Fault monitoring is often not very real-time, potentially resulting in significant economic losses.

[0003] Therefore, how to provide a virtual reality-based offshore wind power transmission system fault location method and system that can monitor offshore wind power transmission system faults in real time and predict faults is an urgent problem that technical personnel in this field need to solve. Summary of the Invention

[0004] In view of this, the present invention provides a virtual reality-based offshore wind power transmission system fault location method and system, which can monitor offshore wind power transmission system faults in real time and predict faults.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A method for locating faults in an offshore wind power transmission system based on virtual reality, comprising the following steps:

[0007] Constructing a virtual scene model, wherein the virtual scene model is obtained through three-dimensional scanning based on a real offshore wind power transmission system;

[0008] Assigning the operating attributes of each device in the real offshore wind power transmission system to the virtual scene model;

[0009] The virtual scene model is imported into the Unreal Engine, and the operation data is updated in real time. The operation of the virtual scene model is controlled by the Unreal Engine, and the operation status of the virtual scene model is monitored in real time.

[0010] Preferably, in the above-mentioned method for locating faults in an offshore wind power transmission system based on virtual reality, the specific steps of constructing a virtual scene model are as follows:

[0011] Conduct 3D scanning of real offshore wind power transmission systems;

[0012] Establishing a virtual scene database, wherein the virtual scene database includes world coordinate value information of scene feature points and related attribute information;

[0013] Calibrate the wind turbines and collection devices, generators, offshore converter stations, DC cables, and onshore converter stations of the offshore wind power transmission system, and project the offshore wind power transmission system into a world coordinate system through coordinate transformation;

[0014] Process the real scene image frame data, obtain the pixel coordinate values ​​of the real scene feature points and extract the feature target image;

[0015] The real scene feature points are aligned with the corresponding feature points in the three-dimensional virtual scene model, and the extracted real scene feature target image is superimposed on the corresponding position of the virtual three-dimensional scene model.

[0016] Preferably, in the above-mentioned method for locating faults in an offshore wind power transmission system based on virtual reality, the specific steps of assigning the operating attributes of each device in the real offshore wind power transmission system to the virtual scene model are as follows:

[0017] Configuration operation instructions, wherein the operation instructions include device location information, operation attributes, and operating parameters;

[0018] The virtual scene model adjusts the operating status of each device in the current virtual scene according to the configuration operation instruction.

[0019] Preferably, in the above-mentioned method for locating faults in an offshore wind power transmission system based on virtual reality, the specific steps of importing the virtual scene model into the Unreal Engine are as follows:

[0020] The Unreal Engine establishes a data interaction channel between the data acquisition device in the real scene and the virtual scene model;

[0021] Transmitting operating data in real time, determining the priority of the operating data, and adjusting the operating status of each device according to the priority of the operating data;

[0022] Display in real time whether each device has a fault.

[0023] Preferably, the above-mentioned method for locating faults in an offshore wind power transmission system based on virtual reality further includes: fault prediction; the specific steps of the fault prediction are as follows:

[0024] Building a fault simulation library, wherein the fault simulation library stores the operating parameters of each device that has failed in historical data, and using the fault simulation library to preliminarily predict the failure;

[0025] Constructing a fault trend prediction model, training it with historical data from the fault simulation library, and predicting fault trends based on current operating parameters of each device;

[0026] The preliminary fault prediction results and predicted fault trends are integrated to ultimately locate the fault point.

[0027] A virtual reality-based offshore wind power transmission system fault location system, comprising:

[0028] A virtual scene construction module, wherein the virtual scene model is obtained through three-dimensional scanning based on a real offshore wind power transmission system;

[0029] an operation attribute assignment module for assigning operation attributes of each device in a real offshore wind power transmission system to the virtual scene model;

[0030] The Unreal Engine import module updates the operation data in real time, controls the operation of the virtual scene model through the Unreal Engine, and monitors the operation status of the virtual scene model in real time.

[0031] Preferably, in the above-mentioned virtual reality-based offshore wind power transmission system fault location system, the virtual scene construction module includes:

[0032] 3D scanning unit, which performs 3D scanning of the actual offshore wind power transmission system;

[0033] A virtual scene virtual library is used to establish a virtual scene database, wherein the virtual scene database includes world coordinate value information of scene feature points and related attribute information;

[0034] A coordinate calibration unit calibrates the wind turbines and collection devices, generators, offshore converter stations, DC cables, and onshore converter stations of the offshore wind power transmission system, and projects the offshore wind power transmission system into a world coordinate system through coordinate transformation;

[0035] The feature extraction unit processes the real scene image frame data, obtains the pixel coordinate values ​​of the real scene feature points and extracts the feature target image;

[0036] The registration unit aligns the feature points of the real scene with the corresponding feature points in the three-dimensional virtual scene model, and superimposes the extracted real scene feature target image on the corresponding position of the virtual three-dimensional scene model.

[0037] Preferably, in the above-mentioned virtual reality-based offshore wind power transmission system fault location system, the operation attribute assignment module includes:

[0038] An operation instruction configuration unit, configured to configure an operation instruction, wherein the operation instruction includes device location information, operation attributes, and operation parameters;

[0039] The adjustment unit adjusts the operating status of each device in the current virtual scene according to the configuration operation instruction.

[0040] Preferably, in the above-mentioned virtual reality-based offshore wind power transmission system fault location system, the Unreal Engine import module includes:

[0041] An interactive channel establishing unit, wherein the Unreal Engine establishes a data interactive channel between a data acquisition device in a real scene and the virtual scene model;

[0042] An operation status unit transmits operation data in real time, determines the priority of the operation data, and adjusts the operation status of each device according to the priority of the operation data;

[0043] The display unit shows in real time whether any device has any fault.

[0044] Preferably, the above-mentioned virtual reality-based offshore wind power transmission system fault location system further includes: a fault prediction module; the fault prediction module includes:

[0045] a fault simulation library construction unit, wherein the fault simulation library stores operating parameters of various devices that have failed in historical data, and uses the fault simulation library to preliminarily predict faults;

[0046] A fault trend prediction model building unit is trained using historical data in the fault simulation library and predicts fault trends based on current operating parameters of each device;

[0047] The fusion unit integrates the preliminary fault prediction results and the predicted fault trend to finally locate the fault point.

[0048] It can be seen from the above technical solution that compared with the existing technology, the present invention discloses a method and system for locating faults in an offshore wind power transmission system based on virtual reality. First, a virtual scene is constructed. The virtual scene can be displayed through a VR device or a display device, and each device of the offshore wind power transmission system is simulated and restored. Then, each device in the virtual scene is given operational attributes, including the working parameters for normal operation of each device, the working parameter thresholds allowed for faults, etc.; finally, an Unreal Engine is constructed to update the virtual scene data in real time, simulate the operating status of the offshore wind power transmission system, characterize the fault point according to the data of each instrument, and at the same time, a pop-up window is used to remind the fault through a display device or a VR device; in addition, by constructing a fault simulation library and combining the working parameters to predict the fault trend and perform fault prediction, the offshore wind power transmission system fault can be monitored in real time, and the fault can be avoided in time by predicting the fault, thereby reducing property losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0050] Figure 1 is a flow chart of the method of the present invention;

[0051] Figure 2 A flow chart of the method for constructing a virtual scene model of the present invention;

[0052] Figure 3 A flow chart of the method for assigning operation attributes to a virtual scene model of the present invention;

[0053] Figure 4 A flow chart of the method for importing a virtual scene model into Unreal Engine according to the present invention;

[0054] Figure 5 This is a flow chart of the fault prediction method of the present invention;

[0055] Figure 6 It is a structural block diagram of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0057] The embodiment of the present invention discloses a virtual reality-based offshore wind power transmission system fault location method and system, which can monitor offshore wind power transmission system faults in real time, and can timely avoid faults by predicting faults, thereby reducing property losses, etc.

[0058] The embodiment of the present invention discloses a method for locating faults in an offshore wind power transmission system based on virtual reality. Figure 1-5 As shown, the specific steps include:

[0059] S101 builds a virtual scene model, which is obtained through 3D scanning based on the actual offshore wind power transmission system;

[0060] S102 assigns the operational attributes of each device in the real offshore wind power transmission system to the virtual scene model;

[0061] In step S103, the virtual scene model is imported into the Unreal Engine, the operation data is updated in real time, the operation of the virtual scene model is controlled by the Unreal Engine, and the operation status of the virtual scene model is monitored in real time.

[0062] Through the above technical solution, a virtual scene is first constructed. The virtual scene can be displayed through a VR device or a display device, and each device of the offshore wind power transmission system is simulated and restored. Then, each device in the virtual scene is given operational attributes, including the working parameters for normal operation of each device, the threshold value of the working parameters allowed by faults, etc.; finally, an Unreal Engine is constructed to update the virtual scene data in real time, simulate the operating status of the offshore wind power transmission system, characterize the fault point according to the data of each instrument, and at the same time, a pop-up window is used to remind the fault through the display device or VR device.

[0063] In order to further optimize the above technical solution, the specific steps of S101 to construct a virtual scene model are as follows:

[0064] S1011 performs 3D scanning of real offshore wind power transmission systems;

[0065] S1012 establishes a virtual scene database, which includes world coordinate value information of scene feature points and related attribute information;

[0066] S1013 calibrates the wind turbines and collection devices, generators, offshore converter stations, DC cables, and onshore converter stations of the offshore wind power transmission system, and projects the offshore wind power transmission system into the world coordinate system through coordinate transformation.

[0067] S1014 processes the real scene image frame data, obtains the pixel coordinate values ​​of the real scene feature points and extracts the feature target image;

[0068] S1015 aligns the feature points of the real scene with the corresponding feature points in the three-dimensional virtual scene model, and superimposes the extracted real scene feature target image on the corresponding position of the virtual three-dimensional scene model.

[0069] In order to further optimize the above technical solution, S102 assigns the operational attributes of each device in the real offshore wind power transmission system to the virtual scene model. The specific steps are as follows:

[0070] S1021 configures operation instructions, which include device location information, operation attributes, and operating parameters;

[0071] S1022 The virtual scene model adjusts the operating status of each device in the current virtual scene according to the configuration operation instruction.

[0072] In order to further optimize the above technical solution, the specific steps of importing the virtual scene model into the Unreal Engine in S103 are as follows:

[0073] S1031 Unreal Engine establishes a data interaction channel between the data acquisition device in the real scene and the virtual scene model;

[0074] S1032 transmits operating data in real time, determines the priority of the operating data, and adjusts the operating status of each device according to the priority of the operating data;

[0075] S1033 displays in real time whether each device has a fault.

[0076] In order to further optimize the above technical solution, the following further steps are included: 104 fault prediction; the specific steps of fault prediction are as follows:

[0077] S1041 builds a fault simulation library, which stores the operating parameters of each device that has failed in historical data, and uses the fault simulation library to preliminarily predict faults;

[0078] S1042 builds a fault trend prediction model, trains it with historical data from the fault simulation library, and predicts fault trends based on the current operating parameters of each device;

[0079] S1043 integrates the preliminary predicted fault results and predicted fault trends to ultimately locate the fault point.

[0080] Specifically, the fault simulation library stores the operating parameters of each device with historical data of faults, and preliminarily predicts the fault type based on the current device operating parameters;

[0081] Furthermore, the specific steps of building a fault trend prediction model are as follows:

[0082] Obtain the operating parameters of each device at different times, and use the difference between the operating parameters at adjacent times to determine the fault change trend. The specific formula is as follows:

[0083]

[0084] in, Indicates the weight corresponding to the difference between the ith parameter at the ith adjacent moment, Δa i represents the difference of the i-th parameter, n represents the number of working parameters that determine the occurrence of the fault; θ i Indicates the compensation values ​​corresponding to different parameters;

[0085] Going further, It is determined by using a neural network through historical data, in which different weights are determined to correspond to different working parameters through correlation analysis.

[0086] The compensation value is based on historical data, and the standard threshold is determined based on historical data. The selection of the compensation value depends on the situation. The first compensation value is obtained by the difference between the actual value and the standard value. If there are multiple working parameters that jointly determine a certain fault, the compensation value needs to be determined as a comprehensive compensation value based on the fault contribution.

[0087] Furthermore, the fault contribution is obtained through correlation analysis.

[0088] In summary, the fault type can be preliminarily predicted based on the current equipment working parameters, and the possibility of fault occurrence can be further judged based on the fault change trend.

[0089] Another embodiment of the present invention discloses a virtual reality-based offshore wind power transmission system fault location system, such as Figure 6 As shown, including:

[0090] Virtual scene construction module: the virtual scene model is obtained through 3D scanning based on the real offshore wind power transmission system;

[0091] The operation attribute assignment module assigns the operation attributes of each device in the real offshore wind power transmission system to the virtual scene model;

[0092] Unreal Engine import module, real-time update of running data, control of virtual scene model operation through Unreal Engine, and real-time monitoring of virtual scene model operation status.

[0093] In order to further optimize the above technical solutions, the virtual scene construction module includes:

[0094] 3D scanning unit, which performs 3D scanning of the actual offshore wind power transmission system;

[0095] Virtual scene virtual library, establishes a virtual scene database, and the virtual scene database includes the world coordinate value information of the scene feature points and their related attribute information;

[0096] The coordinate calibration unit calibrates the wind turbines and collection devices, generators, offshore converter stations, DC cables, and onshore converter stations of the offshore wind power transmission system, and projects the offshore wind power transmission system into the world coordinate system through coordinate transformation;

[0097] The feature extraction unit processes the real scene image frame data, obtains the pixel coordinate values ​​of the real scene feature points and extracts the feature target image;

[0098] The registration unit aligns the feature points of the real scene with the corresponding feature points in the three-dimensional virtual scene model, and superimposes the extracted real scene feature target image on the corresponding position of the virtual three-dimensional scene model.

[0099] In order to further optimize the above technical solution, the operation attribute assignment module includes:

[0100] An operation instruction configuration unit is used to configure operation instructions, which include device location information, operation attributes, and operation parameters;

[0101] The adjustment unit adjusts the operating status of each device in the current virtual scene according to the configuration operation instructions.

[0102] To further optimize the above technical solutions, the Unreal Engine import module includes:

[0103] An interactive channel establishment unit, wherein the Unreal Engine establishes a data interactive channel between a data acquisition device in a real scene and a virtual scene model;

[0104] The operation status unit transmits operation data in real time, determines the priority of the operation data, and adjusts the operation status of each device according to the priority of the operation data;

[0105] The display unit shows in real time whether any device has any fault.

[0106] In order to further optimize the above technical solution, it also includes: a fault prediction module; the fault prediction module includes:

[0107] A fault simulation library construction unit stores the operating parameters of each device that has failed in historical data, and uses the fault simulation library to preliminarily predict faults;

[0108] The fault trend prediction model building unit is trained using historical data from the fault simulation library and predicts fault trends based on the current operating parameters of each device;

[0109] The fusion unit integrates the preliminary fault prediction results and the predicted fault trend to finally locate the fault point.

[0110] Specifically, the fault simulation library stores the operating parameters of each device with historical data of faults, and preliminarily predicts the fault type based on the current device operating parameters;

[0111] Furthermore, the fault trend prediction model building unit:

[0112] Obtain the operating parameters of each device at different times, and use the difference between the operating parameters at adjacent times to determine the fault change trend. The specific formula is as follows:

[0113]

[0114] in, represents the weight corresponding to the difference between the ith parameter at the ith adjacent moment, Δα i represents the difference of the i-th parameter, n represents the number of working parameters that determine the occurrence of the fault; θ i Indicates the compensation values ​​corresponding to different parameters;

[0115] Going further, It is determined by using a neural network through historical data, in which different weights are determined to correspond to different working parameters through correlation analysis.

[0116] The compensation value is based on historical data, and the standard threshold is determined based on historical data. The selection of the compensation value depends on the situation. The first compensation value is obtained by the difference between the actual value and the standard value. If there are multiple working parameters that jointly determine a certain fault, the compensation value needs to be determined as a comprehensive compensation value based on the fault contribution.

[0117] Furthermore, the fault contribution is obtained through correlation analysis.

[0118] In summary, the fault simulation library construction unit preliminarily predicts the fault type based on the current equipment working parameters, and further determines the possibility of fault occurrence based on the fault change trend determined by the fault trend prediction model construction unit.

[0119] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0120] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for locating faults in an offshore wind power transmission system based on virtual reality, characterized in that: The specific steps include: Constructing a virtual scene model, wherein the virtual scene model is obtained through three-dimensional scanning based on a real offshore wind power transmission system; Assigning the operating attributes of each device in the real offshore wind power transmission system to the virtual scene model; The virtual scene model is imported into the Unreal Engine, the operation data is updated in real time, the operation of the virtual scene model is controlled by the Unreal Engine, and the operation status of the virtual scene model is monitored in real time; Fault prediction: The specific steps of fault prediction are as follows: Building a fault simulation library, wherein the fault simulation library stores the operating parameters of each device that has failed in historical data, and using the fault simulation library to preliminarily predict the failure; Constructing a fault trend prediction model, training it with historical data from the fault simulation library, and predicting fault trends based on current operating parameters of each device; Integrate the preliminary fault prediction results and predicted fault trends to ultimately locate the fault point; The specific steps to build a fault trend prediction model are as follows: Obtain the operating parameters of each device at different times, and use the difference between the operating parameters at adjacent times to determine the fault change trend.

2. A method for locating faults in an offshore wind power transmission system based on virtual reality according to claim 1, characterized in that: The specific steps to build a virtual scene model are as follows: Conduct 3D scanning of real offshore wind power transmission systems; Establishing a virtual scene database, wherein the virtual scene database includes world coordinate value information of scene feature points and related attribute information; Calibrate the wind turbines and collection devices, generators, offshore converter stations, DC cables, and onshore converter stations of the offshore wind power transmission system, and project the offshore wind power transmission system into a world coordinate system through coordinate transformation; Process the real scene image frame data, obtain the pixel coordinate values ​​of the real scene feature points and extract the feature target image; The real scene feature points are aligned with the corresponding feature points in the three-dimensional virtual scene model, and the extracted real scene feature target image is superimposed on the corresponding position of the virtual three-dimensional scene model.

3. The method for locating faults in an offshore wind power transmission system based on virtual reality according to claim 1, characterized in that: The specific steps of assigning the operational attributes of each device in the real offshore wind power transmission system to the virtual scene model are as follows: Configuration operation instructions, wherein the operation instructions include device location information, operation attributes, and operating parameters; The virtual scene model adjusts the operating status of each device in the current virtual scene according to the configuration operation instruction.

4. The method for locating faults in an offshore wind power transmission system based on virtual reality according to claim 1, characterized in that: The specific steps of importing the virtual scene model into the Unreal Engine are as follows: The Unreal Engine establishes a data interaction channel between the data acquisition device in the real scene and the virtual scene model; Transmitting operating data in real time, determining the priority of the operating data, and adjusting the operating status of each device according to the priority of the operating data; Display in real time whether each device has a fault.

5. A virtual reality-based offshore wind power transmission system fault location system, characterized in that: include: Virtual scene construction module: the virtual scene model is obtained through 3D scanning based on the real offshore wind power transmission system; an operation attribute assignment module for assigning operation attributes of each device in a real offshore wind power transmission system to the virtual scene model; An Unreal Engine import module updates the operation data in real time, controls the operation of the virtual scene model through the Unreal Engine, and monitors the operation status of the virtual scene model in real time; Fault prediction module; The fault prediction module includes: a fault simulation library construction unit, wherein the fault simulation library stores operating parameters of various devices that have failed in historical data, and uses the fault simulation library to preliminarily predict faults; A fault trend prediction model building unit is trained using historical data in the fault simulation library and predicts fault trends based on current operating parameters of each device; The fusion unit integrates the preliminary fault prediction results and the predicted fault trend to ultimately locate the fault point; Fault trend prediction model building unit: Obtain the operating parameters of each device at different times, and use the difference between the operating parameters at adjacent times to determine the fault change trend.

6. A virtual reality-based offshore wind power transmission system fault location system according to claim 5, characterized in that: The virtual scene construction module includes: 3D scanning unit, which performs 3D scanning of the actual offshore wind power transmission system; A virtual scene virtual library is used to establish a virtual scene database, wherein the virtual scene database includes world coordinate value information of scene feature points and related attribute information; A coordinate calibration unit calibrates the wind turbines and collection devices, generators, offshore converter stations, DC cables, and onshore converter stations of the offshore wind power transmission system, and projects the offshore wind power transmission system into a world coordinate system through coordinate transformation; The feature extraction unit processes the real scene image frame data, obtains the pixel coordinate values ​​of the real scene feature points and extracts the feature target image; The registration unit aligns the feature points of the real scene with the corresponding feature points in the three-dimensional virtual scene model, and superimposes the extracted real scene feature target image on the corresponding position of the virtual three-dimensional scene model.

7. The virtual reality-based offshore wind power transmission system fault location system according to claim 5, characterized in that: The operation attribute assignment module includes: An operation instruction configuration unit, configured to configure an operation instruction, wherein the operation instruction includes device location information, operation attributes, and operation parameters; The adjustment unit adjusts the operating status of each device in the current virtual scene according to the configuration operation instruction.

8. The virtual reality-based offshore wind power transmission system fault location system according to claim 5, characterized in that: The Unreal Engine import module includes: An interactive channel establishing unit, wherein the Unreal Engine establishes a data interactive channel between a data acquisition device in a real scene and the virtual scene model; An operation status unit transmits operation data in real time, determines the priority of the operation data, and adjusts the operation status of each device according to the priority of the operation data; The display unit shows in real time whether any device has any fault.

Images