Water turbine operation and maintenance virtual dismounting training cloud side cooperation device

Abstract

The invention relates to the technical field of virtual reality, in particular to a water turbine operation and maintenance virtual disassembly training cloud edge cooperation device, which comprises a user disassembly module, an evaluation teaching module and a disassembly path planning module, and is characterized in that a user uses an operation handle to perform interactive operation on water turbine virtual information displayed in a head-mounted VR unit; the water turbine dismounting function is completed; the evaluation teaching module receives and manages the multi-dimensional data of the user dismounting and mounting module, and scores the dismounting and mounting actions of the user by adopting a collision detection algorithm; and the disassembly and assembly path planning module receives the preprocessed video data from the edge end, completes video positioning and cutting, identifies the position where collision easily occurs in the water turbine disassembly and assembly process, plans and generates an optimal recommended path for water turbine part disassembly and assembly, and generates a user operation report. According to the method, efficient and accurate water turbine disassembly and assembly guidance and immersive visual disassembly and assembly experience are provided for operation and maintenance construction technicians, water turbine disassembly and assembly steps are fully understood and optimized, the construction efficiency is improved, and the disassembly and assembly quality is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of virtual reality technology, and in particular to a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance. Background Art

[0002] As the core equipment of a hydropower plant, the operating status of a hydropower unit is directly related to the power generation efficiency and safety of the hydropower plant. At present, the highly complex characteristics of the structural maintenance of hydropower units have the phenomenon of "under-maintenance" and "over-maintenance", making it difficult to fully release the efficiency of the turbine units. Therefore, it is of great significance to improve the intelligent level of unit maintenance by conducting unit disassembly and assembly rehearsals through digital and information means to assist employees in fully understanding the maintenance process information of hydropower units.

[0003] Virtual disassembly and maintenance of hydropower units uses virtual reality (VR) to simulate the disassembly, installation and maintenance process of hydropower units, providing operators with a safe and repeatable training environment. However, there are certain limitations. On the one hand, the existing technology is very inadequate in terms of interactivity, and it is difficult for users to receive feedback when they make incorrect operations; on the other hand, there is a lack of a complete operation evaluation system, and users cannot obtain systematic evaluation and improvement suggestions after completing the operation. As the scale of hydropower plants continues to expand, the amount of user operation data is also increasing, and traditional data processing methods can no longer meet the requirements of real-time and accuracy.

[0004] To sum up, in order to realize the intelligent maintenance of the operating status of hydropower units, improve the disassembly and assembly efficiency, and reduce the operation and maintenance costs, it is necessary to study a cloud-edge collaborative virtual disassembly and assembly training device for turbine operation and maintenance to solve the above-mentioned problems. Summary of the invention

[0005] The main purpose of this application is to provide a solution to the existing technology.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] According to a first aspect of the present invention, the present invention claims protection for a cloud-edge collaborative device for virtual disassembly and assembly training of a hydraulic turbine operation and maintenance inspection, comprising: a user disassembly and assembly module located at a client, an evaluation and teaching module located at an edge, and a disassembly and assembly path planning module located at a cloud;

[0008] The user disassembly module includes a head-mounted VR unit, an operating handle and a space positioning unit;

[0009] The user disassembly module performs virtual disassembly operations of the turbine, and captures and tracks the position and movement of the disassembly user in the virtual disassembly environment;

[0010] The evaluation and teaching module receives and manages the video operation data from the disassembly and assembly user, displays the disassembly and assembly user operation screen in real time, analyzes the user operation process and scoring results, and corrects the user's erroneous operation

[0011] The disassembly and assembly path planning preprocesses the data of the evaluation teaching module, completes the collision point positioning and cutting of the components of the turbine and the analysis and planning of the disassembly and assembly path, outputs the optimal disassembly and assembly path of the turbine, and optimizes the disassembly and assembly steps of the turbine by working in collaboration with the edge end.

[0012] Furthermore, the user disassembly and assembly module is equipped with multiple sets of virtual wearable devices for disassembly and assembly of turbines, which can be used by multiple users in parallel. Each set of equipment includes a head-mounted VR unit, a spatial positioning unit and an operating handle.

[0013] The head-mounted VR unit is equipped with a high-resolution display screen 2 to display virtual reality interactive information of the turbine unit to be disassembled and assembled to the disassembling user;

[0014] The operating handle is connected to the head-mounted VR unit via Bluetooth to perform the disassembly and assembly operations of the turbine group components;

[0015] The space positioning unit cooperates with the operating handle and the head-mounted VR unit through infrared communication to track the roaming position and grasping action of the disassembling and assembling user in the turbine disassembling and assembling virtual reality environment.

[0016] Furthermore, the head-mounted VR unit of the user disassembly module includes:

[0017] Interpupillary distance sensor 1, acceleration sensor 3 and gravity sensor;

[0018] The head movement information of the disassembling user when picking up and disassembling the assembly components is collected.

[0019] The operating handle is equipped with an acceleration sensor 3 to collect motion information, and cooperates with the infrared positioning function of the spatial positioning unit to locate the positions of various components of the turbine to be disassembled and assembled, thereby avoiding collision deductions caused by incorrect positioning.

[0020] Furthermore, the operating handle is provided with an interactive function key 6, a component grabbing key 5, and a roaming key 7;

[0021] Single-click the interactive function key 6 to open the infrared ray and virtual reality scene interactive interface, and double-click the interactive function key 6 to switch the unit disassembly and assembly components;

[0022] The component grabbing key 5 is used to pick up the components of the turbine to be assembled from the ground during the assembly process, and to remove the components of the turbine from the unit during the disassembly process;

[0023] The roaming key 7 is used to adjust the distance between the turbine disassembly and assembly scene and the disassembly and assembly user, and adjust the disassembly and assembly user to a suitable position for disassembly and assembly operations;

[0024] The head-mounted VR unit of the user disassembly module is provided with a microphone device 4, which gives a voice prompt to the user when the user performs an incorrect disassembly operation;

[0025] The operating handle of the user disassembly and assembly module has a built-in vibration device. When the disassembly and assembly user performs an incorrect disassembly and assembly operation, the vibration device sends a vibration prompt and adjusts the vibration intensity according to the penalty points for the incorrect disassembly and assembly operation.

[0026] Furthermore, the evaluation and teaching module is wirelessly connected to the virtual wearable devices in the plurality of user disassembly and assembly modules through a wireless adapter, and the operation data of the plurality of disassembly and assembly users are synchronously transmitted to the evaluation and teaching module;

[0027] The evaluation teaching module is equipped with a data storage unit, a collision detection unit and a scoring teaching unit;

[0028] The data storage unit is configured with a memory and a solid state hard disk, and stores relevant disassembly and assembly user information and disassembly and assembly operation data corresponding to the disassembly and assembly user;

[0029] The evaluation teaching module is equipped with a processor to complete the collision detection and scoring teaching of video data;

[0030] The collision detection unit of the evaluation teaching module deploys Gilbert-Johnson-Keerth collision detection operator to detect whether a collision occurs by calculating the shortest distance between the disassembled and assembled parts of the turbine;

[0031] If a component assembly collision is detected, collision feedback is provided to the disassembling user through the vibration device of the operating handle or the microphone voice prompt function of the head-mounted VR unit.

[0032] Furthermore, the scoring teaching unit of the evaluation teaching module establishes a weighted collision scoring mechanism between various components during the turbine disassembly and assembly process;

[0033] According to the number of collision points in a collision action, the collision operation is classified and corresponding weights are set;

[0034] The total collision score is calculated by deducting points for different types of collision maneuvers.

[0035] Furthermore, the disassembly and assembly path planning module uses the TCP / IP protocol to receive the video data from the evaluation and teaching module, and shares the optimal disassembly and assembly path obtained by cloud computing planning back to the scoring teaching unit of the evaluation and teaching module for user learning and reference.

[0036] Furthermore, the cloud server of the disassembly and assembly path planning module is embedded in the system processor, which supports the deep learning algorithm to realize the data preprocessing, collision trajectory acquisition and optimal disassembly and assembly trajectory planning involved in the turbine disassembly and assembly process.

[0037] Furthermore, the data processing unit in the disassembly and assembly path planning module adopts a spatiotemporal filter algorithm to complete the noise reduction processing of the disassembly and assembly operation video, and adopts YOLO, spatiotemporal segmentation or optical flow method to crop the collision positions during assembly and disassembly of the unit components in the video, automatically amplify the details of the erroneous disassembly and assembly operation in the video, and obtain the trajectory of the erroneous disassembly and assembly operation.

[0038] Furthermore, the disassembly and assembly path planning module collects and stores the coordinate information of the disassembled and assembled parts in real time, automatically draws the disassembly and assembly trajectory curves of each disassembled and assembled part in the coordinate system, obtains multiple disassembly and assembly trajectories in the process of disassembling and assembling the turbine, and finds and compares the optimal path of the motion trajectory, and feeds back the optimal path trajectory to the scoring teaching unit of the evaluation teaching module for user learning;

[0039] The assembly and disassembly track includes component assembly and disassembly tracks and component hoisting tracks. The component assembly and disassembly tracks include upper frame assembly and disassembly tracks, rotor assembly and disassembly tracks, and top cover assembly and disassembly tracks. The hoisting tracks include tracks for hoisting the runner into and out of the foundation pit, tracks for hoisting the top cover into and out of the foundation pit, and tracks for hoisting the upper frame into and out of the foundation pit.

[0040] The disassembly and assembly path planning module generates a user's disassembly and assembly scoring report, which includes the disassembly and assembly user's various scores and deduction details during the disassembly and assembly operation, and provides optimal path suggestions for the disassembly and assembly operation to help the user improve his operating skills and optimize the disassembly and assembly process.

[0041] The present application relates to the field of virtual reality technology, and in particular to a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance inspection, including: a user disassembly and assembly module, an evaluation teaching module, and a disassembly and assembly path planning module. The user uses an operating handle to interact with the virtual information of the turbine displayed in the head-mounted VR unit to complete the turbine disassembly and assembly function; the evaluation teaching module receives and manages the multi-dimensional data of the user disassembly and assembly module, and uses a collision detection algorithm to score the user's disassembly and assembly actions; the disassembly and assembly path planning module receives pre-processed video data from the edge end, completes video positioning and cropping, identifies the locations prone to collision during the turbine disassembly and assembly process, plans and generates the optimal recommended path for the disassembly and assembly of turbine components, and generates a user operation report. The present invention provides efficient and accurate turbine disassembly and assembly guidance and immersive visual disassembly and assembly experience for operation and maintenance inspection construction technicians, fully understands and optimizes the turbine disassembly and assembly steps, improves construction efficiency, and ensures disassembly and assembly quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A structural block diagram of a cloud-edge collaborative device for virtual disassembly and assembly training of a hydraulic turbine operation and maintenance inspection as claimed in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of the arrangement of multiple wearable devices of a cloud-edge collaborative device for virtual disassembly and assembly training of a hydraulic turbine operation and maintenance inspection as claimed in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of a head-mounted VR device for a cloud-edge collaborative device for virtual disassembly and assembly training of a hydraulic turbine operation and maintenance inspection as claimed in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of an operating handle of a cloud-edge collaborative device for virtual disassembly and assembly training of a hydraulic turbine operation and maintenance inspection as claimed in an embodiment of the present application;

[0046] Figure 5 A schematic diagram of a scoring standard flow chart of a cloud-edge collaborative device for virtual disassembly and assembly training of a hydraulic turbine operation and maintenance inspection as claimed in an embodiment of the present application;

[0047] Reference numerals: pupil distance sensor -1, display screen -2, acceleration sensor -3, microphone device -4, component grabbing key -5, interactive function key -6, roaming key -7. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The terms "first", "second" and "third" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present application (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0050] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0051] In recent years, the rapid development of new technologies in cloud computing and edge computing has provided a new solution for the virtual disassembly and maintenance of hydropower units. Cloud computing has powerful data processing and storage capabilities, which can realize the rapid processing and analysis of massive data; edge computing can migrate some computing tasks from the cloud to the device side, reduce data transmission delays, and improve real-time performance. Therefore, combining cloud computing and edge computing technologies to build a cloud-edge collaborative virtual disassembly and assembly training device for turbine operation and maintenance is of great significance to improving the maintenance efficiency and safety of hydropower units.

[0052] According to the first embodiment of the present invention, the present invention claims a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, referring to Figure 1 , including: a user disassembly and assembly module located at the client, an evaluation and teaching module located at the edge, and a disassembly and assembly path planning module located at the cloud;

[0053] The user disassembly module includes a head-mounted VR unit, an operating handle and a space positioning unit;

[0054] The user disassembly module performs virtual disassembly operations of the turbine, and captures and tracks the position and movement of the disassembly user in the virtual disassembly environment;

[0055] The evaluation and teaching module receives and manages the video operation data from the disassembly and assembly user, displays the disassembly and assembly user operation screen in real time, analyzes the user operation process and scoring results, and corrects the user's erroneous operation

[0056] The disassembly and assembly path planning preprocesses the data of the evaluation teaching module, completes the collision point positioning and cutting of the components of the turbine and the analysis and planning of the disassembly and assembly path, outputs the optimal disassembly and assembly path of the turbine, and optimizes the disassembly and assembly steps of the turbine by working in collaboration with the edge end.

[0057] Further, refer to Figure 2-4 The user disassembly and assembly module is equipped with multiple sets of virtual wearable devices for disassembly and assembly of turbines, which can be used by multiple users in parallel. Each set of equipment includes a head-mounted VR unit, a spatial positioning unit and an operating handle.

[0058] The head-mounted VR unit is equipped with a high-resolution display screen 2 to display virtual reality interactive information of the turbine unit to be disassembled and assembled to the disassembling user;

[0059] The operating handle is connected to the head-mounted VR unit via Bluetooth to perform the disassembly and assembly operations of the turbine group components;

[0060] The space positioning unit cooperates with the operating handle and the head-mounted VR unit through infrared communication to track the roaming position and grasping action of the disassembling and assembling user in the turbine disassembling and assembling virtual reality environment.

[0061] Furthermore, the head-mounted VR unit of the user disassembly module includes:

[0062] Interpupillary distance sensor 1, acceleration sensor 3 and gravity sensor;

[0063] The head movement information of the disassembling user when picking up and disassembling the assembly components is collected.

[0064] The operating handle is equipped with an acceleration sensor 3 to collect motion information, and cooperates with the infrared positioning function of the spatial positioning unit to locate the positions of various components of the turbine to be disassembled and assembled, thereby avoiding collision deductions caused by incorrect positioning.

[0065] Furthermore, the operating handle is provided with an interactive function key 6, a component grabbing key 5, and a roaming key 7;

[0066] Single-click the interactive function key 6 to open the infrared ray and virtual reality scene interactive interface, and double-click the interactive function key 6 to switch the unit disassembly and assembly components;

[0067] The component grabbing key 5 is used to pick up the components of the turbine to be assembled from the ground during the assembly process, and to remove the components of the turbine from the unit during the disassembly process;

[0068] The roaming key 7 is used to adjust the distance between the turbine disassembly and assembly scene and the disassembly and assembly user, and adjust the disassembly and assembly user to a suitable position for disassembly and assembly operations;

[0069] The head-mounted VR unit of the user disassembly module is provided with a microphone device 4, which gives a voice prompt to the user when the user performs an incorrect disassembly operation;

[0070] The operating handle of the user disassembly and assembly module has a built-in vibration device. When the disassembly and assembly user performs an incorrect disassembly and assembly operation, the vibration device sends a vibration prompt and adjusts the vibration intensity according to the penalty points for the incorrect disassembly and assembly operation.

[0071] Furthermore, the evaluation and teaching module is wirelessly connected to the virtual wearable devices in the plurality of user disassembly and assembly modules through a wireless adapter, and the operation data of the plurality of disassembly and assembly users are synchronously transmitted to the evaluation and teaching module;

[0072] The evaluation teaching module is equipped with a data storage unit, a collision detection unit and a scoring teaching unit;

[0073] The data storage unit is configured with a memory and a solid state hard disk, and stores relevant disassembly and assembly user information and disassembly and assembly operation data corresponding to the disassembly and assembly user;

[0074] The evaluation teaching module is equipped with a processor to complete the collision detection and scoring teaching of video data;

[0075] The collision detection unit of the evaluation teaching module deploys Gilbert-Johnson-Keerth collision detection operator to detect whether a collision occurs by calculating the shortest distance between the disassembled and assembled parts of the turbine;

[0076] If a component assembly collision is detected, collision feedback is provided to the disassembling user through the vibration device of the operating handle or the microphone voice prompt function of the head-mounted VR unit.

[0077] Among them, in this embodiment, the data storage unit is configured with 16GB memory and 1TB solid-state hard disk to store relevant user information and the corresponding user's disassembly and assembly operation data; the evaluation teaching module is configured with an eight-core processor with a main frequency of 2.5GHZ and above to complete collision detection and scoring teaching of video data.

[0078] Further, refer to Figure 5 , the scoring teaching unit of the evaluation teaching module establishes a weighted collision scoring mechanism between various components during the turbine disassembly and assembly process;

[0079] According to the number of collision points in a collision action, the collision operation is classified and corresponding weights are set;

[0080] The total collision score is calculated by deducting points for different types of collision maneuvers.

[0081] In this embodiment, the operation is divided into a slight collision, a moderate collision and a severe collision according to the number of collision points in one collision action.

[0082] The specific classification is as follows: less than 2 collision points are recorded as minor collisions, between 2 and 4 collision points are moderate collisions, and more than 4 collision points are severe collisions. The corresponding weights are set to 0.2, 0.5, and 0.9, respectively. Each operation action is initially scored 10 points, and different types of collisions are deducted according to their weights. The final total score is calculated by deducting the scores of different types of collisions.

[0083] The above-mentioned deduction calculation method uses an embedded language to write into the core computing chip of the scoring teaching unit to achieve fast calculation and reduce latency.

[0084] Furthermore, the disassembly and assembly path planning module uses the TCP / IP protocol to receive the video data from the evaluation and teaching module, and shares the optimal disassembly and assembly path obtained by cloud computing planning back to the scoring teaching unit of the evaluation and teaching module for user learning and reference.

[0085] Furthermore, the cloud server of the disassembly and assembly path planning module is embedded in the system processor, which supports the deep learning algorithm to realize the data preprocessing, collision trajectory acquisition and optimal disassembly and assembly trajectory planning involved in the turbine disassembly and assembly process.

[0086] Among them, in this embodiment, the cloud server of the disassembly and assembly path planning module is embedded with a 64-bit system processor based on the ARPv8-A architecture, which supports the deep learning algorithm to realize the data preprocessing, collision trajectory acquisition and optimal disassembly and assembly trajectory planning functions involved in the turbine disassembly and assembly process.

[0087] Furthermore, the data processing unit in the disassembly and assembly path planning module adopts a spatiotemporal filter algorithm to complete the noise reduction processing of the disassembly and assembly operation video, and adopts YOLO, spatiotemporal segmentation or optical flow method to crop the collision positions during assembly and disassembly of the unit components in the video, automatically amplify the details of the erroneous disassembly and assembly operation in the video, and obtain the trajectory of the erroneous disassembly and assembly operation.

[0088] Furthermore, the disassembly and assembly path planning module collects and stores the coordinate information of the disassembled and assembled parts in real time, automatically draws the disassembly and assembly trajectory curves of each disassembled and assembled part in the coordinate system, obtains multiple disassembly and assembly trajectories in the process of disassembling and assembling the turbine, and finds and compares the optimal path of the motion trajectory, and feeds back the optimal path trajectory to the scoring teaching unit of the evaluation teaching module for user learning;

[0089] The assembly and disassembly track includes component assembly and disassembly tracks and component hoisting tracks. The component assembly and disassembly tracks include upper frame assembly and disassembly tracks, rotor assembly and disassembly tracks, and top cover assembly and disassembly tracks. The hoisting tracks include tracks for hoisting the runner into and out of the foundation pit, tracks for hoisting the top cover into and out of the foundation pit, and tracks for hoisting the upper frame into and out of the foundation pit.

[0090] The disassembly and assembly path planning module generates a user's disassembly and assembly scoring report, which includes the disassembly and assembly user's various scores and deduction details during the disassembly and assembly operation, and provides optimal path suggestions for the disassembly and assembly operation to help the user improve his operating skills and optimize the disassembly and assembly process.

[0091] In this embodiment, it also includes:

[0092] Collecting the minimum period and the maximum period of the assembly and disassembly action to be compared, collecting at least one historical comparison information from the assembly and disassembly trajectory library according to the minimum period and the maximum period, and outputting the directory of historical comparison information to be compared, wherein the assembly and disassembly trajectory library stores historical comparison information, and each historical comparison information stores the assembly and disassembly component information within a preset time period according to the type information;

[0093] Collecting video images provided by the turbine server, obtaining disassembly and assembly actions that meet the video images from the historical comparison information directory, and outputting candidate disassembly and assembly actions, wherein the video images contain metadata of disassembly and assembly component information in the disassembly and assembly actions to be compared;

[0094] Collecting the minimum execution frequency of the assembly and disassembly action to be compared, and collecting the preferred assembly and disassembly action from the candidate assembly and disassembly actions according to the minimum execution frequency, wherein the minimum execution frequency is the minimum number of execution times included in the assembly and disassembly action to be compared, and the assembly and disassembly components between two adjacent assembly and disassembly component entities in the assembly and disassembly action constitute one execution time;

[0095] The disassembly and assembly component information in the preferred disassembly and assembly action is collected, and the preferred disassembly and assembly components compared by the turbine server are output.

[0096] Collecting the preferred assembly and disassembly actions from the candidate assembly and disassembly actions according to the minimum execution frequency includes:

[0097] Determining whether the execution frequency of the candidate assembly / disassembly action is greater than the minimum execution frequency;

[0098] In the case where the execution frequency of the candidate assembly and disassembly action is greater than the minimum execution frequency, collecting the candidate assembly and disassembly action as the preferred assembly and disassembly action;

[0099] After collecting the preferred disassembly and assembly actions from the candidate disassembly and assembly actions according to the minimum execution frequency, the method further includes:

[0100] Collecting the minimum number of disassembly and assembly actions that the turbine server needs to compare, and determining whether the number of disassembly and assembly parts is greater than the minimum number of disassembly and assembly actions, wherein the number of disassembly and assembly parts is the number of the preferred disassembly and assembly actions;

[0101] When the number of disassembly and assembly parts is greater than the minimum number of disassembly and assembly actions, the steps of collecting disassembly and assembly parts information in the preferred disassembly and assembly actions and outputting the preferred disassembly and assembly parts compared by the turbine server are performed;

[0102] When the number of disassembly and assembly parts of the preferred disassembly and assembly action is less than the minimum number of disassembly and assembly actions, other preferred disassembly and assembly actions are filtered out from the secondary disassembly and assembly actions according to the minimum number of disassembly and assembly actions and the minimum execution frequency, wherein the secondary disassembly and assembly action is a disassembly and assembly action whose execution frequency of the candidate disassembly and assembly action is less than the minimum execution frequency;

[0103] Combining the preferred assembly and disassembly action with the other preferred assembly and disassembly actions, and outputting an adjusted preferred assembly and disassembly action;

[0104] The step of collecting disassembly and assembly component information in the preferred disassembly and assembly action according to the adjusted preferred disassembly and assembly action and outputting the preferred disassembly and assembly components compared by the turbine server is performed.

[0105] Filtering out other preferred assembly and disassembly actions from the secondary assembly and disassembly actions according to the minimum number of assembly and disassembly actions and the minimum execution frequency includes:

[0106] Collecting the execution frequency interval to which the minimum execution frequency belongs, and collecting the weight score of the minimum execution frequency according to the execution frequency interval;

[0107] Calculate the product of the minimum number of assembly and disassembly actions, the minimum execution frequency and the weight score, and output the number of comparisons;

[0108] Arrange all secondary disassembly and assembly actions in order of execution frequency from small to large, and output the optimal sequence;

[0109] Collecting the first P disassembly and assembly actions from the preferred sequence, where P is the number of comparisons;

[0110] The assembly and disassembly actions whose execution frequencies are greater than the minimum execution frequency among the first P assembly and disassembly actions are collected as the other preferred assembly and disassembly actions.

[0111] After combining the preferred assembly and disassembly action with the other preferred assembly and disassembly actions to output an adjusted preferred assembly and disassembly action, the method further includes:

[0112] Determining whether the optimized number of disassembly and assembly parts is greater than the minimum number of disassembly and assembly actions, wherein the optimized number of disassembly and assembly parts is the number of the adjusted preferred disassembly and assembly actions;

[0113] Under the condition that the optimized number of disassembly and assembly parts is greater than the minimum number of disassembly and assembly actions, the steps of collecting disassembly and assembly parts information in the preferred disassembly and assembly actions and outputting the preferred disassembly and assembly parts compared by the turbine server are performed;

[0114] In the case where the optimized number of disassembly and assembly parts is less than the minimum number of disassembly and assembly actions, a first warning message is displayed, wherein the first warning message is used to warn the turbine server to re-collect the minimum period and the maximum period of the disassembly and assembly actions to be compared.

[0115] Collecting the disassembly and assembly component information in the preferred disassembly and assembly action, and outputting the preferred disassembly and assembly components compared by the turbine server includes:

[0116] Collecting the serial number of the preferred assembly and disassembly action, and collecting the preferred assembly and disassembly component from the assembly and disassembly track library according to the historical comparison information directory and the serial number;

[0117] After collecting the minimum period and the maximum period of the assembly and disassembly actions to be compared, the method further includes:

[0118] Determine whether there is historical comparison information between the minimum period and the maximum period in the assembly and disassembly trajectory library;

[0119] When there is a piece of historical comparison information between the minimum period and the maximum period in the assembly and disassembly trajectory library, performing the step of collecting at least one piece of historical comparison information from the assembly and disassembly trajectory library storing assembly and disassembly component information according to the minimum period and the maximum period;

[0120] For an individual case where the historical comparison information does not exist between the minimum period and the maximum period in the assembly and disassembly trajectory library, a second warning message is displayed, wherein the second warning message is used to warn that the turbine server data comparison fails.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0122] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated units may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent range of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection range of the present application.

[0123] The specific implementation methods of the invention are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: include: The user disassembly and assembly module located at the client, the evaluation and teaching module located at the edge, and the disassembly and assembly path planning module located at the cloud; The user disassembly module includes a head-mounted VR unit, an operating handle and a space positioning unit; The user disassembly module performs virtual disassembly operations of the turbine, and captures and tracks the position and movement of the disassembly user in the virtual disassembly environment; The evaluation and teaching module receives and manages the video operation data from the disassembly and assembly user, and displays the disassembly and assembly user operation screen in real time, so as to analyze the user operation process and scoring results, and correct the user's wrong operation. The disassembly and assembly path planning preprocesses the data of the evaluation teaching module, completes the collision point positioning and cutting of the components of the turbine and the analysis and planning of the disassembly and assembly path, outputs the optimal disassembly and assembly path of the turbine, and optimizes the disassembly and assembly steps of the turbine by working in collaboration with the edge end.

2. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The user disassembly and assembly module is equipped with multiple sets of virtual wearable devices for disassembly and assembly of turbines, which can be used by multiple users in parallel. Each set of equipment includes a head-mounted VR unit, a spatial positioning unit and an operating handle. The head-mounted VR unit is equipped with a high-resolution display screen (2) for displaying virtual reality interactive information of the turbine unit to be disassembled and assembled to the disassembling user; The operating handle is connected to the head-mounted VR unit via Bluetooth to perform the disassembly and assembly operations of the turbine group components; The space positioning unit cooperates with the operating handle and the head-mounted VR unit through infrared communication to track the roaming position and grasping action of the disassembling user in the turbine disassembly and assembly virtual reality environment.

3. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The head-mounted VR unit of the user disassembly module includes: A pupil distance sensor (1), an acceleration sensor (3) and a gravity sensor; The head movement information of the disassembling user when picking up and disassembling the assembly components is collected. The operating handle is equipped with an acceleration sensor (3) to collect motion information, and cooperates with the infrared positioning function of the spatial positioning unit to locate the positions of various components of the turbine to be disassembled and assembled, thereby avoiding collision deductions caused by incorrect positioning.

4. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The operating handle is provided with an interactive function key (6), a component grabbing key (5), and a roaming key (7); Single-clicking the interactive function key (6) opens the infrared ray and virtual reality scene interactive interface, and double-clicking the interactive function key (6) switches the assembly and disassembly components of the unit; The component grabbing key (5) is used to pick up the components of the turbine to be assembled from the ground during the assembly process, and to remove the components of the turbine from the unit during the disassembly process; The roaming key (7) is used to adjust the distance between the turbine disassembly and assembly scene and the disassembly and assembly user, and to adjust the disassembly and assembly user to a suitable position to perform the disassembly and assembly operation; The head-mounted VR unit of the user disassembly module is provided with a microphone device (4) for providing a voice prompt to the user when the user performs an incorrect disassembly operation; The operating handle of the user disassembly and assembly module has a built-in vibration device. When the disassembly and assembly user performs an incorrect disassembly and assembly operation, the vibration device sends a vibration prompt and adjusts the vibration intensity according to the penalty points for the incorrect disassembly and assembly operation.

5. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The evaluation and teaching module is wirelessly connected to the virtual wearable devices in the plurality of user disassembly and assembly modules through a wireless adapter, and the operation data of the plurality of disassembly and assembly users are synchronously transmitted to the evaluation and teaching module; The evaluation teaching module is equipped with a data storage unit, a collision detection unit and a scoring teaching unit; The data storage unit is configured with a memory and a solid state hard disk, and stores relevant disassembly and assembly user information and disassembly and assembly operation data corresponding to the disassembly and assembly user; The evaluation teaching module is equipped with a processor to complete the collision detection and scoring teaching of video data; The collision detection unit of the evaluation teaching module deploys the Gilbert-Johnson-Keerth collision detection operator to detect whether a collision occurs by calculating the shortest distance between the disassembled and assembled parts of the turbine; If a component assembly collision is detected, collision feedback is provided to the disassembling user through the vibration device of the operating handle or the microphone voice prompt function of the head-mounted VR unit.

6. According to claim 5, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The scoring teaching unit of the evaluation teaching module establishes a weighted collision scoring mechanism between various components during the turbine disassembly and assembly process; According to the number of collision points in a collision action, the collision operation is classified and corresponding weights are set; The total collision score is calculated by deducting points for different types of collision maneuvers.

7. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The assembly and disassembly path planning module uses the TCP / IP protocol to receive the video data from the evaluation and teaching module, and shares the optimal assembly and disassembly path obtained by cloud computing planning back to the scoring teaching unit of the evaluation and teaching module for user learning and reference.

8. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The cloud server of the disassembly and assembly path planning module is embedded in the system processor, which supports the deep learning algorithm to realize the data preprocessing, collision trajectory acquisition and optimal disassembly and assembly trajectory planning involved in the turbine disassembly and assembly process.

9. According to claim 1, a cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance, characterized in that: The data processing unit in the disassembly and assembly path planning module adopts a spatiotemporal filter algorithm to complete the noise reduction processing of the disassembly and assembly operation video, and adopts YOLO, spatiotemporal segmentation or optical flow method to crop the collision positions during assembly and disassembly of the unit components in the video, automatically amplify the details of the incorrect disassembly and assembly operation in the video, and obtain the trajectory of the incorrect disassembly and assembly operation.

10. The cloud-edge collaborative device for virtual disassembly and assembly training of turbine operation and maintenance according to claim 1 is characterized in that: The disassembly and assembly path planning module collects and stores the coordinate information of the disassembled and assembled parts in real time, automatically draws the disassembly and assembly trajectory curves of each disassembled and assembled part in the coordinate system, obtains multiple disassembly and assembly trajectories in the process of disassembling and assembling the turbine, and finds and compares the optimal path of the motion trajectory, and feeds back the optimal path trajectory to the scoring teaching unit of the evaluation teaching module for user learning; The assembly and disassembly track includes component assembly and disassembly tracks and component hoisting tracks. The component assembly and disassembly tracks include upper frame assembly and disassembly tracks, rotor assembly and disassembly tracks, and top cover assembly and disassembly tracks. The hoisting tracks include tracks for hoisting the runner into and out of the foundation pit, tracks for hoisting the top cover into and out of the foundation pit, and tracks for hoisting the upper frame into and out of the foundation pit. The disassembly and assembly path planning module generates a user's disassembly and assembly scoring report, which includes the disassembly and assembly user's various scores and deduction details during the disassembly and assembly operation, and provides optimal path suggestions for the disassembly and assembly operation to help the user improve his operating skills and optimize the disassembly and assembly process.

Images