CN117910266A

CN117910266A - AI-based hydropower equipment operation and maintenance decision method and system

Info

Publication number: CN117910266A
Application number: CN202410131534.1A
Authority: CN
Inventors: 叶波; 田云; 赵娅; 王荣; 邹佳成; 潘家余; 陈松; 蒋勤伟; 宁红兵; 夏祥
Original assignee: Guizhou Jinyuan Zunyi Hydropower Development Co Ltd Of State Power Investment Group
Current assignee: Guizhou Jinyuan Zunyi Hydropower Development Co Ltd Of State Power Investment Group
Priority date: 2024-01-31
Filing date: 2024-01-31
Publication date: 2024-04-19

Abstract

The embodiment of the invention provides an AI-based hydropower equipment operation and maintenance decision method and system, which can provide clear and visual space layout information for an inspection entity by rendering a locator and an operation and maintenance inspection path of a key hydropower equipment in a digital twin scene, thereby improving inspection efficiency and reducing operation and maintenance cost. And secondly, determining a first operation and maintenance inspection path with the largest number of observable key hydropower equipment in each operation and maintenance inspection path cluster, further optimizing inspection plans, improving inspection coverage rate and ensuring safe and stable operation of hydropower station equipment. Furthermore, by rendering the first operation and maintenance inspection path after the salification and outputting the corresponding operation and maintenance decision result, operation and maintenance personnel can be effectively guided to make decisions, errors are reduced, and operation and maintenance quality is improved.

Description

AI-based hydropower equipment operation and maintenance decision method and system

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to an operation and maintenance decision method and system for hydroelectric equipment based on AI.

Background

The equipment inspection of the hydropower station is an important link for ensuring the normal operation of the equipment and preventing the equipment from failure. However, in the conventional inspection mode, the inspection workload is large and the inspection efficiency is low due to the numerous devices and the wide distribution and the complexity of the inspection path. In addition, how to reasonably arrange the inspection path to cover more key devices is also a problem to be solved.

On the other hand, the existing routing inspection path planning method generally depends on manual experience, and lacks scientific data support and optimization strategies, so that the optimization effect of the routing inspection path is not ideal. Meanwhile, the output of the operation and maintenance decision result also depends on the experience judgment of operation and maintenance personnel, and errors can exist.

In addition, although the digital twin technology is widely applied in a plurality of fields, the potential of the digital twin technology is not fully utilized in the aspects of equipment inspection, operation and maintenance decision and the like of a hydropower station. How to use digital twin technology to improve the equipment inspection efficiency and the accuracy of operation and maintenance decision of a hydropower station is a current problem to be solved urgently.

Disclosure of Invention

In order to at least overcome the above-mentioned shortcomings in the prior art, an object of an embodiment of the present application is to provide a method and a system for determining operation and maintenance of a hydropower device based on AI.

In a first aspect, an embodiment of the present application provides an AI-based operation and maintenance decision method for a hydropower device, where the method includes:

Rendering X hydroelectric equipment positioners and Y operation and maintenance inspection paths in a digital twin scene of a hydropower station, wherein the digital twin scene of the hydropower station is used for rendering space scene layout of internal equipment of the hydropower station, the X hydroelectric equipment positioners are used for representing positioning information of X key hydroelectric equipment in the hydropower station, and when an inspection entity executes inspection operation according to each operation and maintenance inspection path in the Y operation and maintenance inspection paths, the key hydroelectric equipment observable by the inspection entity comprises one or more key hydroelectric equipment in the X key hydroelectric equipment, and X, Y is a natural number not less than 2;

Determining a first operation and maintenance inspection path cluster in each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths, wherein in each operation and maintenance inspection path cluster in the Y operation and maintenance inspection paths, when the inspection entity executes inspection operation according to the first operation and maintenance inspection path formed by the first operation and maintenance inspection path cluster, the number of the key hydropower equipment observable by the inspection entity in the X key hydropower equipment is maximized;

Rendering the first operation and maintenance inspection paths after the saliency processing in the digital twin scene of the hydropower station, and outputting corresponding operation and maintenance decision results of the hydropower equipment based on the rendered first operation and maintenance inspection paths.

In a possible implementation manner of the first aspect, the determining a first operation and maintenance routing path cluster in each operation and maintenance routing path cluster formed by the Y operation and maintenance routing paths includes:

When a group of observation nodes are defined on each operation and maintenance inspection path in the Y operation and maintenance inspection paths, an observation penetration scene partition of each observation node is determined in the digital twin scene of the hydropower station, when the inspection entity is positioned at an x-th observation node, scene objects in the observation penetration scene partition of the x-th observation node can observe the inspection entity, and x is a natural number not less than 1;

When each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths comprises Z operation and maintenance inspection path clusters, merging the observation penetration scene partitions of each observation node on each operation and maintenance inspection path in each operation and maintenance inspection path cluster in the Z operation and maintenance inspection path clusters to generate Z observation penetration scene partitions, wherein Z is a natural number not less than 2;

Outputting a y-th operation and maintenance inspection path cluster corresponding to a y-th observation and permeation scene partition in the Z operation and maintenance inspection path clusters as the first operation and maintenance inspection path cluster when the number of key hydropower equipment in the X key hydropower equipment included in the y-th observation and permeation scene partition in the Z observation and permeation scene partitions is maximized, wherein y is a natural number which is not less than 1 and not more than Z.

In a possible implementation manner of the first aspect, the method further includes:

Acquiring loaded W hydroelectric equipment positioners, wherein the W hydroelectric equipment positioners are used for representing W key hydroelectric equipment in the X key hydroelectric equipment, and W is a natural number which is not less than 1 and not more than X;

Determining a second operation and maintenance inspection path cluster in each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths, wherein in each operation and maintenance inspection path cluster in the Y operation and maintenance inspection paths, when the inspection entity executes inspection operation according to the second operation and maintenance inspection path formed by the second operation and maintenance inspection path cluster, the key hydropower equipment observable by the inspection entity comprises W key hydropower equipment;

Rendering the second operation and maintenance inspection path after the saliency processing in the digital twin scene of the hydropower station.

In a possible implementation manner of the first aspect, the determining a second operation and maintenance routing path cluster in each operation and maintenance routing path cluster formed by the Y operation and maintenance routing paths includes:

When the h observation penetration scene partition in the Z observation penetration scene partitions comprises the W key hydropower devices, outputting an h operation and maintenance inspection path cluster corresponding to the h observation penetration scene partition in the Z operation and maintenance inspection path clusters as a second operation and maintenance inspection path cluster, wherein h is a natural number which is not less than 1 and not more than Z.

In a possible implementation manner of the first aspect, when the W key hydropower devices are included in an h observation penetration scene partition in the Z observation penetration scene partitions, outputting an h operation and maintenance inspection path cluster corresponding to the h observation penetration scene partition in the Z operation and maintenance inspection path clusters as the second operation and maintenance inspection path cluster includes:

When the T observing and penetrating scene partitions in the Z observing and penetrating scene partitions all comprise the W key hydropower devices, determining an operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path in T operation and maintenance inspection path clusters corresponding to the T observing and penetrating scene partitions, outputting the operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path as the second operation and maintenance inspection path cluster, wherein T is a natural number which is not less than 2 and not more than Z, and the h operation and maintenance inspection path cluster is the operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path;

Or when all the T observing and penetrating scene partitions in the Z observing and penetrating scene partitions comprise the W key hydropower devices, determining the observing and penetrating scene partition with the maximized number of the key hydropower devices in the X key hydropower devices in the T observing and penetrating scene partitions, and outputting an operation and maintenance inspection path cluster corresponding to the determined observing and penetrating scene partition in the Z operation and maintenance inspection path clusters as a second operation and maintenance inspection path cluster, wherein the h operation and maintenance inspection path cluster is an operation and maintenance inspection path cluster corresponding to the determined observing and penetrating scene partition.

In a possible implementation manner of the first aspect, after the determining a first operation and maintenance routing path cluster in each operation and maintenance routing path cluster formed by the Y operation and maintenance routing paths, the method further includes:

When L observation nodes are defined on the first operation and maintenance inspection path formed by the first operation and maintenance inspection path cluster, P observation nodes are determined in the L observation nodes based on the observation penetration scene partition of each observation node in the L observation nodes, and when the inspection entity executes inspection operation according to the first operation and maintenance inspection path, the key hydropower equipment observable by the inspection entity comprises P key hydropower equipment in the X key hydropower equipment, L is a natural number not less than 2, and P is a natural number not less than 1 and not more than L;

Rendering the P observation nodes subjected to the saliency treatment in the digital twin scene of the hydropower station, wherein the e-th observation node in the P observation nodes is used for representing positioning information of the routing inspection entity for routing inspection of the e-th key hydropower device in the P key hydropower devices, and e is a natural number which is not less than 1 and not more than P.

In a possible implementation manner of the first aspect, the determining P observing nodes among the L observing nodes based on the observing penetration scene partition of each of the L observing nodes includes:

determining the e-th observation node of the P observation nodes, the e-th observation node and the e-th critical hydropower device based on:

When the L observation nodes comprise Ge observation nodes and the observation penetration scene partition of each observation node comprises the e-th key hydropower equipment, acquiring operation scene state data of the node where the e-th key hydropower equipment is located, and generating Ge simulation inspection data streams corresponding to the Ge observation nodes based on the operation scene state data and the scene nodes corresponding to the Ge observation nodes, wherein Ge is a natural number not smaller than 2, and the Ge simulation inspection data streams are simulation inspection data streams generated by conducting simulation inspection on the e-th key hydropower equipment on the Ge observation nodes;

And determining a target simulation inspection data stream in the Ge simulation inspection data streams, and outputting an observation node corresponding to the target simulation inspection data stream in the Ge observation nodes as the e-th observation node.

In a possible implementation manner of the first aspect, the determining a target simulated patrol data stream from the Ge simulated patrol data streams includes:

loading the Ge simulation inspection data streams to a target simulation effectiveness evaluation network, and determining Ge simulation effectiveness values corresponding to the Ge simulation inspection data streams based on the target simulation effectiveness evaluation network;

And determining the target simulation patrol data stream in the Ge simulation patrol data stream based on the Ge simulation validity values, wherein the simulation validity value corresponding to the target simulation patrol data stream is the largest in the Ge simulation validity values.

In a possible implementation manner of the first aspect, after determining a target simulated patrol data stream from the Ge simulated patrol data streams, the method further includes:

Based on the target simulation inspection data flow, rendering the positioning information and the observation azimuth information of the e observation node and the node where the e observation node is located after the salification in the digital twin scene of the hydropower station, wherein the positioning information is used for representing the positioning information of the inspection entity for inspecting the e-th key hydropower equipment, and the observation azimuth information is used for representing azimuth vector information of the inspection entity when the e-th key hydropower equipment performs multidirectional observation.

In a second aspect, the embodiment of the present application further provides an AI-based hydropower device operation and maintenance decision system, which includes a processor and a machine-readable storage medium having stored therein machine-executable instructions loaded and executed by the processor to implement the AI-based hydropower device operation and maintenance decision method in any one of the possible implementations of the first aspect.

According to any aspect, the space scene layout of the internal equipment of the hydropower station and the accurate positioning of the key hydropower equipment are realized by rendering X hydropower equipment locators and Y operation and maintenance inspection paths in the digital twin scene of the hydropower station. Further, by determining the first operation and maintenance inspection path cluster, the inspection entity can maximize the number of the observed key hydropower devices when performing inspection operation according to the first operation and maintenance inspection path cluster, so that the inspection efficiency is improved. In addition, the first operation and maintenance inspection path is rendered after being subjected to the saliency treatment, so that operation and maintenance personnel can more intuitively identify the optimal inspection path, and a corresponding operation and maintenance decision result of the hydropower equipment is output based on the rendered first operation and maintenance inspection path, and powerful support is provided for operation and maintenance management of the hydropower station.

That is, the embodiment can provide clear and visual space layout information for the inspection entity by rendering the locator and the operation and maintenance inspection path of the key hydropower equipment in the digital twin scene, thereby improving the inspection efficiency and reducing the operation and maintenance cost. And secondly, determining a first operation and maintenance inspection path with the largest number of observable key hydropower equipment in each operation and maintenance inspection path cluster, further optimizing inspection plans, improving inspection coverage rate and ensuring safe and stable operation of hydropower station equipment. Furthermore, by rendering the first operation and maintenance inspection path after the salification and outputting the corresponding operation and maintenance decision result, operation and maintenance personnel can be effectively guided to make decisions, errors are reduced, and operation and maintenance quality is improved.

Drawings

For a clearer description of the technical solutions of the embodiments of the present invention, reference will be made to the accompanying drawings, which are needed to be activated in the embodiments, and it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and other related drawings can be extracted by those skilled in the art without the inventive effort.

FIG. 1 is a schematic flow chart of an operation and maintenance decision method of a hydroelectric device based on AI according to an embodiment of the invention;

Fig. 2 is a schematic block diagram of an AI-based operation and maintenance decision system of a hydropower device for implementing the AI-based operation and maintenance decision method of a hydropower device according to an embodiment of the invention.

Detailed Description

The following description is presented to enable one of ordinary skill in the art to make and use the invention and is provided in the context of a particular application and its requirements. It will be apparent to those having ordinary skill in the art that various changes can be made to the disclosed embodiments and that the general principles defined herein may be applied to other embodiments and applications without departing from the principles and scope of the invention. Therefore, the present invention is not limited to the described embodiments, but is to be accorded the widest scope consistent with the claims.

Fig. 1 is a flow chart of an operation and maintenance decision method of an AI-based hydropower device according to an embodiment of the invention, and the operation and maintenance decision method of the AI-based hydropower device will be described in detail.

And step S110, rendering X hydropower equipment positioners and Y operation and maintenance inspection paths in the digital twin scene of the hydropower station.

In this embodiment, the digital twin scene of the hydropower station is used for rendering a spatial scene layout of internal devices of the hydropower station, the X hydropower device locators are used for characterizing positioning information of X key hydropower devices in the hydropower station, and when the inspection entity performs an inspection operation according to each of the Y operation and maintenance inspection paths, the key hydropower devices observable by the inspection entity include one or more key hydropower devices of the X key hydropower devices, and X, Y is a natural number not less than 2.

In detail, the embodiment firstly renders the internal space layout of the hydropower station in the digital twin scene of the hydropower station. This hydropower station digital twin scenario can be understood as a three-dimensional model that accurately simulates each hydropower plant and its relative position within the hydropower station. For example, the hydropower station digital twin scenario may refer to a virtual hydropower station environment created through digital technology (such as 3D modeling, sensor data integration of the internet of things, etc.), and this virtual hydropower station environment can simulate the spatial layout, the operation state and the interrelationship of the internal devices of the real hydropower station. By way of example, a three-dimensional hydropower station model is envisaged, which is represented by means of advanced computer graphics technology, in which the position of the generator, the rotation of the turbine, the operating state of the transformer, and even the direction and speed of the water flow, are seen, all updated in real time or in a simulated manner on the basis of the data of the real hydropower station.

In the embodiment, in the digital twin scene of the hydropower station, X key hydropower equipment positioners are specially rendered, wherein the hydropower equipment positioners refer to virtual symbols or marks used for marking and indicating the positions of key hydropower equipment in the digital twin scene, and can help operation and maintenance personnel to quickly find and identify corresponding real equipment in the virtual environment. For example, the generator may be marked with a three-dimensional icon with a "generator" label, which may be highlighted in a particular color or shape so that the operator can identify the location of the generator at a glance in a number of devices. That is, each hydroelectric device locator corresponds to a real critical hydroelectric device in the hydropower station, wherein the critical hydroelectric device is the device which is critical to the overall operation of the hydropower station, and the fault or abnormality of the critical hydroelectric device can cause the interruption or the reduction of the efficiency of the overall hydropower station, for example, a water turbine, a generator and a transformer can be regarded as critical hydroelectric devices, because the water turbine is responsible for converting water energy into mechanical energy, the generator is responsible for converting mechanical energy into electric energy, and the transformer is responsible for adjusting voltage to match the requirement of a power grid. The hydropower device locators may be presented in the form of special icons, colors or labels so that the service personnel can recognize the location of the key hydropower devices at a glance.

Meanwhile, Y operation and maintenance tour-inspection paths can be rendered in the digital twin scene. These operation and maintenance patrol paths are virtual, but they are simulated based on the actual patrol route inside the hydropower station. Specifically, the operation and maintenance inspection path refers to a virtual path defined in a digital twin scene and used for simulating operation and maintenance personnel to inspect. These operation and maintenance inspection paths pass through a series of critical hydropower devices, ensuring that every important area can be inspected. For example, in a digital twin hydropower station model, the operation and maintenance tour path may be a closed loop path from the entrance, through the generator, the transformer, the control room, and back to the entrance. Along this path of operation and maintenance inspection, the operation and maintenance personnel can check the status and performance of each critical hydropower device.

That is, each operation and maintenance inspection path can pass through a part of the area inside the hydropower station to access a plurality of key hydropower devices. When an operation and maintenance entity (such as a virtual inspection robot or an avatar of an operation and maintenance engineer) inspects according to the operation and maintenance inspection paths, key hydropower equipment on the operation and maintenance inspection paths can be observed, and the overall operation condition of the hydropower station can be estimated according to the state of the key hydropower equipment.

The inspection entity refers to a virtual or physical object for performing inspection operation in a digital twin scene, and the inspection entity can be a virtual inspection robot, an unmanned aerial vehicle, or an avatar or a real character of an operation and maintenance engineer. For example, during a simulated inspection process, a virtual inspection robot may move along a predetermined operation and maintenance inspection path, collect data of critical hydropower devices, such as temperature, vibration frequency, etc., and send the data back to a control center for analysis in real time.

Step S120, determining a first operation and maintenance inspection path cluster in each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths, and maximizing the number of critical hydropower devices observable by the inspection entity in the X critical hydropower devices when the inspection entity performs the inspection operation according to the first operation and maintenance inspection path formed by the first operation and maintenance inspection path cluster in each operation and maintenance inspection path cluster in the Y operation and maintenance inspection paths.

The operation and maintenance inspection path cluster refers to a set formed by a plurality of operation and maintenance inspection paths in a digital twin scene. The above-mentioned multiple operation and maintenance inspection paths are spatially similar or logically related, and generally cover the same area or the same type of equipment, so as to perform centralized management and optimization. For example, in a digital twin model of a hydropower station, there may be multiple generator areas, each with its own operational maintenance routing path. These paths may constitute a cluster of generator area inspection paths, as they all involve inspection and maintenance of the generator.

The first operation and maintenance inspection path cluster refers to one cluster which is considered to be the most important or the most preferred among all operation and maintenance inspection path clusters. The selection of this first cluster of operation and maintenance inspection paths is typically based on some optimization criteria, such as maximizing the number of critical hydropower devices that can be observed. For example, assuming a critical transformer area in a hydropower station, equipment failure of that transformer area may result in a power outage throughout the plant. Therefore, the operation and maintenance inspection path covering the transformer area may be selected as the first operation and maintenance inspection path cluster, so as to ensure that the critical hydropower devices are focused on priority.

The inspection operation refers to inspection activities performed by an inspection entity along an operation and maintenance inspection path in a digital twin scene. These operations include collecting plant data, observing plant status, recording anomalies, etc., to assess the overall operation of the hydropower station. For example, in a digital twin hydropower station model, a virtual inspection robot may move along a preset operation and maintenance inspection path, and the sensors carried by the virtual inspection robot are used to measure parameters such as temperature, vibration and sound of equipment, and these data are transmitted to a control center for analysis and processing in real time.

The maximum number of observable key hydropower devices refers to that when an operation and maintenance inspection path is designed or selected, an inspection entity can observe as many key hydropower devices as possible when inspecting along the path by optimizing the layout and the sequence of the path. For example, assuming that 10 key hydropower stations need to be inspected, by planning operation and maintenance inspection paths, it can be ensured that an inspection entity can directly observe all 10 devices when moving along the paths, rather than only observing part of the devices or needing to move multiple times to observe all the devices.

On the basis of the above description, this step can analyze the Y operation and maintenance inspection paths and divide them into different operation and maintenance inspection path clusters. Each operation and maintenance inspection path cluster comprises a group of operation and maintenance inspection paths which are similar in space and are related in logic. The present embodiment focuses on an operation and maintenance routing path cluster, where the number of key hydropower devices that can be observed is the largest when an operation and maintenance entity performs routing according to an operation and maintenance routing path in the operation and maintenance routing path cluster. This operation and maintenance inspection path cluster is marked as a first operation and maintenance inspection path cluster.

For example, in one possible example, there are three operation and maintenance tour paths A, B and C inside the hydropower station. The operation and maintenance inspection paths A and B both pass through the power generation area, and the operation and maintenance inspection path C passes through the water pump area. If there are more critical hydropower devices in the power generation area, the operation and maintenance routing paths a and B form an operation and maintenance routing path cluster, which may be identified as the first operation and maintenance routing path cluster in the analysis of the present embodiment.

And step S130, rendering the first operation and maintenance inspection paths after the salification in the digital twin scene of the hydropower station, and outputting corresponding operation and maintenance decision results of the hydropower equipment based on each rendered first operation and maintenance inspection path.

Finally, the embodiment can particularly highlight and render the first operation and maintenance inspection path in the first operation and maintenance inspection path cluster in the digital twin scene of the hydropower station. Such highlighting may include changing the color of the first operation and maintenance tour path, adding animation effects, or adding additional labeling information to attract the attention of the operation and maintenance personnel. Therefore, based on the first operation and maintenance inspection path which is prominently rendered, a corresponding operation and maintenance decision result of the hydropower equipment can be further generated. The hydropower device operation and maintenance decision result may include a suggested inspection route, a list of key hydropower devices that need to be focused on, and possible maintenance tasks predicted from the current device state, etc. The information is integrated into a report and sent to the relevant operators to help them perform the hydropower station operation and maintenance more efficiently.

For example, in a hydropower station digital twin scenario, the first operation and maintenance tour path may be highlighted in red, while the other paths are represented in green or blue. In addition, key hydropower device locators on the first operation and maintenance tour path may also be presented in larger icons or more striking labels. When the operation and maintenance personnel or the virtual inspection entity conduct inspection in the digital twin scene, the operation and maintenance personnel or the virtual inspection entity can plan own action routes according to the paths after the salification. Along the first operation and maintenance inspection path, they can quickly and accurately reach the critical hydropower equipment positions which need important attention, and carry out necessary inspection and maintenance operations. And further generating a corresponding operation and maintenance decision result of the hydropower equipment based on each rendered first operation and maintenance inspection path. The operation and maintenance decision results of the hydropower equipment are comprehensively analyzed according to real-time data, historical maintenance records and preset operation and maintenance rules of the equipment on the first operation and maintenance inspection path.

The hydropower device operation and maintenance decision results may include:

device status assessment: and (3) carrying out state evaluation on the key hydropower equipment on the path, and judging whether the key hydropower equipment runs normally or has potential faults.

Maintenance task recommendation: based on the device status evaluation results, corresponding maintenance tasks, such as replacement of components, cleaning of the device, adjustment of parameters, etc., are recommended.

Sorting inspection priority: and (3) prioritizing the devices on different paths to guide operation and maintenance personnel to process which devices or which problems are processed first.

Resource allocation proposal: and according to the requirements and the priorities of maintenance tasks, operation and maintenance resources such as personnel, time, materials and the like are reasonably distributed.

For example, if an abnormal rise in temperature of a certain transformer on the first operation and maintenance inspection path is detected, it may recommend immediate cooling of the transformer in the decision result and dispatch the nearest operation and maintenance personnel to the site for inspection and maintenance. The operation and maintenance decision result of the hydropower equipment is beneficial to quick response to equipment faults, reduces downtime and improves the operation efficiency and safety of the hydropower station.

Based on the steps, the embodiment realizes the spatial scene layout of the internal equipment of the hydropower station and the accurate positioning of the key hydropower equipment by rendering X hydropower equipment locators and Y operation and maintenance inspection paths in the digital twin scene of the hydropower station. Further, by determining the first operation and maintenance inspection path cluster, the inspection entity can maximize the number of the observed key hydropower devices when performing inspection operation according to the first operation and maintenance inspection path cluster, so that the inspection efficiency is improved. In addition, the first operation and maintenance inspection path is rendered after being subjected to the saliency treatment, so that operation and maintenance personnel can more intuitively identify the optimal inspection path, and a corresponding operation and maintenance decision result of the hydropower equipment is output based on the rendered first operation and maintenance inspection path, and powerful support is provided for operation and maintenance management of the hydropower station.

In one possible implementation, step S120 may include:

Step S121, when a set of observation nodes is defined on each operation and maintenance inspection path of the Y operation and maintenance inspection paths, an observation penetration scene partition of each observation node is determined in the digital twin scene of the hydropower station, and when the inspection entity is located at the x-th observation node, a scene object in the observation penetration scene partition of the x-th observation node is observable to the inspection entity, and x is a natural number not less than 1.

For example, in a digital twin scenario in a hydropower station, a set of observation nodes is first defined for each operation and maintenance tour path. These observation nodes are virtual and represent locations where the operator may stay during the inspection process. For each observation node, its observation penetration scene partition is further determined. This means that when a patrol entity (such as a virtual patrol robot or an operation and maintenance person) is located at a certain observation node, it can observe all scene objects within the observation penetration scene partition, including critical hydropower devices.

For example, on a specific operation and maintenance inspection path, 5 observation nodes are set, and each observation node corresponds to a specific observation penetration scene partition. When the inspection entity moves to the 3 rd observation node, the inspection entity can clearly see and collect data of all key hydropower equipment in the observation penetration scene partition, such as the running state of a generator, the temperature of a transformer and the like.

Step S122, when each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths includes Z operation and maintenance inspection path clusters, merging the observation penetration scene partitions of each observation node on each operation and maintenance inspection path in each operation and maintenance inspection path cluster in the Z operation and maintenance inspection path clusters to generate Z observation penetration scene partitions, where Z is a natural number not less than 2.

In this embodiment, after defining the observation node on each operation and maintenance inspection path and the corresponding observation penetration scene partition, processing is started on each operation and maintenance inspection path cluster formed by Y operation and maintenance inspection paths. It is assumed that these operation and maintenance inspection paths are divided into Z operation and maintenance inspection path clusters. And for each operation and maintenance routing inspection path cluster, the observation penetration scene partitions of the observation nodes on all the operation and maintenance routing inspection paths contained in the operation and maintenance routing inspection path cluster can be combined.

This means that for each operation and maintenance inspection path cluster, a comprehensive observation penetration scene partition is created, and the observation penetration scene partition contains all scene objects which can be observed by observation nodes on all operation and maintenance inspection paths in the operation and maintenance inspection path cluster. Thus, each operation and maintenance inspection path cluster corresponds to a unique observation penetration scene partition.

For example, if one operation and maintenance inspection path cluster includes 3 operation and maintenance inspection paths, and each operation and maintenance inspection path has 5 observation nodes, the observation penetration scene of the 15 observation nodes can be partitioned to generate a comprehensive observation penetration scene partition, and the observation penetration scene partition includes the observation information of all the key hydropower devices on the 3 operation and maintenance inspection paths.

Step S123, outputting, as the first operation and maintenance inspection path cluster, a y-th operation and maintenance inspection path cluster corresponding to the y-th observation and penetration scene partition in the Z operation and maintenance inspection path clusters when the number of key hydropower devices in the X key hydropower devices included in the y-th observation and penetration scene partition is maximized, where y is a natural number not less than 1 and not more than Z.

In this embodiment, after Z observation penetration scene partitions are generated, the next task is to determine which operation and maintenance routing path cluster should be selected as the first operation and maintenance routing path cluster. To this end, the number of critical hydropower devices contained in each observed penetration scene zone may be compared.

For example, the present embodiment looks for the operation and maintenance routing cluster that maximizes the number of critical hydropower devices contained in its observed penetration scene partition. When such an operation and maintenance patrol path cluster is found, it may be output as a first operation and maintenance patrol path cluster.

For example, after comparing the observed penetration scene partitions of the 5 operation and maintenance inspection path clusters, the observed penetration scene partition of the 3 rd operation and maintenance inspection path cluster is found to contain the most critical hydropower devices. Thus, the 3 rd operation and maintenance inspection path cluster may be determined as the first operation and maintenance inspection path cluster and subjected to a saliency process so as to be highlighted in the digital twin scene.

Through the processing flow, the key hydropower equipment can be observed to the maximum extent when the inspection entity inspects along the first operation and maintenance inspection path cluster, so that the inspection efficiency and the timeliness of equipment maintenance are improved.

In one possible embodiment, the method further comprises:

And step A110, acquiring loaded W hydropower equipment positioners, wherein the W hydropower equipment positioners are used for representing W key hydropower equipment in the X key hydropower equipment, and W is a natural number not less than 1 and not more than X.

In a hydropower station digital twin scenario, the embodiment first obtains the loaded W hydropower device locators. These hydropower device positioners are specifically designed to characterize W particular ones of the X key hydropower devices. Each of the hydro-electric device locators contains location information and identification codes of specific key hydro-electric devices, thereby facilitating the ability to accurately find and locate such devices in a digital twinning scenario.

For example, this step loads 5 hydropower plant positioners, which correspond to 5 key water turbines, respectively. Each hydro-electric device locator contains the three-dimensional coordinates, the device model and the unique identification code of the corresponding water turbine, so that the key hydro-electric devices can be identified without error and positioned in a digital twin scene.

And step A120, determining a second operation and maintenance inspection path cluster in each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths, wherein in each operation and maintenance inspection path cluster in the Y operation and maintenance inspection paths, when the inspection entity executes inspection operation according to the second operation and maintenance inspection path formed by the second operation and maintenance inspection path cluster, the key hydropower equipment observable by the inspection entity comprises the W key hydropower equipment.

In this embodiment, after W hydropower device positioners are acquired, the next task is to determine a second operation and maintenance routing path cluster from the operation and maintenance routing path clusters formed by the Y operation and maintenance routing paths. This selection is based on a condition: when the inspection entity (such as a virtual inspection robot or an operation and maintenance personnel) performs inspection operation according to a second operation and maintenance inspection path formed by the second operation and maintenance inspection path cluster, the inspection entity can observe all W key hydropower devices.

For example, it may be determined which of the operation and maintenance routing clusters can satisfy the above condition by analyzing the coverage area of each of the operation and maintenance routing clusters and the observation node. Once such an operation and maintenance patrol path cluster is found, it is marked as a second operation and maintenance patrol path cluster.

For example, 10 operation and maintenance inspection path clusters were analyzed, and it was found that the observation node of the 7 th operation and maintenance inspection path cluster could cover the positions of all 5 key water turbines. Therefore, the 7 th operation and maintenance inspection path cluster is determined as a second operation and maintenance inspection path cluster, and a second operation and maintenance inspection path is generated according to the second operation and maintenance inspection path cluster.

And step A130, rendering the second operation and maintenance tour-inspection path after the saliency treatment in the digital twin scene of the hydropower station.

In this embodiment, after the second operation and maintenance routing inspection path cluster is determined, the second operation and maintenance routing inspection path after the saliency processing is rendered in the digital twin scene of the hydropower station. The highlighting may include highlighting the second operation and maintenance tour path using a conspicuous color, a bold line, or a special animation effect.

The purpose of this is to guide the attention of the inspection entity, ensuring that it can efficiently observe all W critical hydropower devices as it is inspected along this operation and maintenance inspection path.

For example, a second operation and maintenance inspection path can be rendered in a digital twinning scene using red bold lines, while a flashing animation effect is added at key observation points on this operation and maintenance inspection path. Therefore, when the virtual inspection robot or the operation and maintenance personnel conduct inspection along the operation and maintenance inspection path, the key observation points can be clearly seen and quickly reached, so that key hydropower equipment can be effectively observed and maintained.

In one possible embodiment, step a120 may include:

And a step A121, when a group of observation nodes are defined on each operation and maintenance inspection path in the Y operation and maintenance inspection paths, determining an observation penetration scene partition of each observation node in the digital twin scene of the hydropower station, and when the inspection entity is positioned at the x-th observation node, observing scene objects in the observation penetration scene partition of the x-th observation node by the inspection entity, wherein x is a natural number not less than 1.

In a digital twin scenario of a hydropower station, this step first defines a set of observation nodes for each of the Y operation and maintenance tour-inspection paths. These observation nodes are virtual and represent locations where the operator may stay during the inspection process. For each observation node, its observation penetration scene partition is further determined. This means that when a patrol entity (such as a virtual patrol robot or an operation and maintenance person) is located at a certain observation node, it can observe all scene objects within the observation penetration scene partition, including critical hydropower devices.

For example, 5 observation nodes are set on a specific operation and maintenance inspection path, and each observation node corresponds to a specific observation penetration scene partition. When the inspection entity moves to the 3 rd observation node, the data of all key hydropower equipment in the observation penetration scene partition, such as the running state of a generator, the temperature of a transformer and the like, can be clearly seen and collected.

And step A122, when each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths comprises Z operation and maintenance inspection path clusters, merging the observation penetration scene partitions of each observation node on each operation and maintenance inspection path in each operation and maintenance inspection path cluster in the Z operation and maintenance inspection path clusters to generate Z observation penetration scene partitions, wherein Z is a natural number not less than 2.

After defining the observation nodes and the corresponding observation penetration scene partitions on each operation and maintenance inspection path, starting to process each operation and maintenance inspection path cluster formed by Y operation and maintenance inspection paths. It is assumed that these paths are divided into Z operation and maintenance tour-inspection path clusters. And for each operation and maintenance routing inspection path cluster, carrying out merging treatment on the observation penetration scene partitions of the observation nodes on all the operation and maintenance routing inspection paths contained in the operation and maintenance routing inspection path clusters.

For example, the present embodiment deals with an operation and maintenance routing path cluster including 3 operation and maintenance routing paths, each of which has 5 observation nodes. Then, the observation penetration scene subareas of the 15 observation nodes are combined into a comprehensive observation penetration scene subarea, and the observation penetration scene subarea contains the observation information of all the key hydropower equipment on the 3 operation and maintenance inspection paths.

And step A123, when the h observation penetration scene partition in the Z observation penetration scene partitions comprises the W key hydropower devices, outputting the h operation and maintenance inspection path cluster corresponding to the h observation penetration scene partition in the Z operation and maintenance inspection path clusters as the second operation and maintenance inspection path cluster, wherein h is a natural number which is not less than 1 and not more than Z.

After the Z observed-penetration scene partitions are generated, the next task is to determine which of the operation and maintenance routing path clusters should be selected as the second operation and maintenance routing path cluster. For example, the critical hydropower devices contained in each observed penetration scene zone may be checked, particularly concerning whether all W critical hydropower devices are contained.

When an observation penetration scene partition is found, and the observation penetration scene partition comprises all W key hydropower devices, determining an operation and maintenance inspection path cluster corresponding to the observation penetration scene partition as a second operation and maintenance inspection path cluster.

For example, after comparing the observed penetration scene partitions of the 5 operation and maintenance inspection path clusters, it is found that the 4 th observed penetration scene partition contains all 5 key hydropower devices (assuming that W is 5). Thus, the 4 th operation and maintenance inspection path cluster may be determined as a second operation and maintenance inspection path cluster and prepared to be subjected to a saliency process so as to be highlighted in the digital twin scene.

Through the processing flow, when the inspection entity inspects along the second operation and maintenance inspection path cluster, all W key hydropower devices can be observed to the maximum extent, so that inspection efficiency and timeliness of device maintenance are improved.

In one possible embodiment, step a123 may include:

When the T observing and penetrating scene partitions in the Z observing and penetrating scene partitions all comprise the W key hydropower devices, determining an operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path in T operation and maintenance inspection path clusters corresponding to the T observing and penetrating scene partitions, outputting the operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path as the second operation and maintenance inspection path cluster, wherein T is a natural number which is not less than 2 and not more than Z, and the h operation and maintenance inspection path cluster is the operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path.

For example, the present embodiment first examines the Z observed osmotic scene partitions and finds that there are T observed osmotic scene partitions (T is not less than 2 and not greater than Z) that all include W key hydropower devices. This means that the observation range of a plurality of operation and maintenance inspection path clusters can be covered on all key hydropower devices.

After the T operation and maintenance inspection path clusters are determined, the costs of the operation and maintenance inspection paths in the path clusters are compared. The cost may be a comprehensive consideration including the length of the path, the time required for inspection, the complexity of the path (e.g., number of turns, climbing height, etc.), and possibly safety risk.

And comparing to find the operation and maintenance inspection path cluster with the minimum cost of the operation and maintenance inspection path. For example, in the case where the 3 rd and 7 th operation and maintenance inspection path clusters both contain all critical hydropower devices, the 7 th path cluster is determined to be less costly because the path is shorter and turns less.

Thus, the operation and maintenance patrol path cluster (7 th path cluster in this example) with the minimum cost of the found operation and maintenance patrol path can be output as the second operation and maintenance patrol path cluster. This means that when a patrol is required, it will be recommended that the patrol entity follows this least costly cluster of operation and maintenance patrol paths.

For example, similar to the previous scenario, the present embodiment first finds that T out of the Z observed-penetration scenario partitions all include W key hydropower devices.

Next, not only whether all W key hydropower devices are contained is considered, but the total number of key hydropower devices contained in each of the T observed penetration scene partitions is further compared. The goal is to find an observed penetration scene partition that includes not only all W designated critical hydropower devices, but possibly also more other critical hydropower devices.

By comparison, an observation penetration scene partition is found, and the number of key hydropower devices in the observation penetration scene partition is the largest in all T observation penetration scene partitions. For example, while all of the observed osmotic scene partitions include W key hydropower devices, one of the observed osmotic scene partitions additionally includes several other key hydropower devices because of a wider viewing angle or a more concentrated layout.

And finally, outputting the operation and maintenance inspection path cluster corresponding to the observation penetration scene partition with the maximized quantity of the key hydropower equipment as a second operation and maintenance inspection path cluster. This means that when the inspection entity inspects along this operation and maintenance inspection path cluster, not only can it be ensured that all W key hydropower devices are observed, but also more other key hydropower devices are likely to be observed, thereby improving the comprehensiveness and efficiency of inspection.

In one possible implementation manner, after determining the first operation and maintenance inspection path cluster in each operation and maintenance inspection path cluster formed by the Y operation and maintenance inspection paths, the method further includes:

And B110, when L observation nodes are defined on the first operation and maintenance inspection path formed by the first operation and maintenance inspection path cluster, determining P observation nodes in the L observation nodes based on the observation penetration scene partition of each observation node in the L observation nodes, wherein when the inspection entity executes inspection operation according to the first operation and maintenance inspection path, the key hydropower equipment observable by the inspection entity comprises P key hydropower equipment in the X key hydropower equipment, L is a natural number not less than 2, and P is a natural number not less than 1 and not more than L.

In this embodiment, first, L observation nodes are defined on the first operation and maintenance routing path. These observation nodes are virtual locations along the inspection path for collecting data and observation information of critical hydropower devices. Each observation node has an observation-penetrating scene partition associated with it that defines the range of scenes that can be observed from that node.

The observed-penetration scene partitions for each of the observation nodes are then analyzed. This includes determining critical hydropower devices visible within each observed penetration scene zone and status information for those devices. The aim of this embodiment is to find a set of observation nodes, such that as many critical hydropower devices as possible can be observed through these.

After all L observation nodes are analyzed, P key observation nodes are determined. These critical observation nodes are chosen because they can cover P of all X critical hydropower devices. The present embodiment ensures that the combination of these P observation nodes is able to maximize the observation coverage for critical hydropower devices while taking into account the efficiency and feasibility of the inspection path.

For example, if L is 10 and there are 8 critical hydropower devices in X, a combination of observation nodes P of 6 may be selected, which can directly observe 6 critical hydropower devices while the rest of the critical hydropower devices can be covered by indirect observation or data analysis.

And step B120, rendering the P observation nodes subjected to the saliency treatment in the digital twin scene of the hydropower station, wherein the e-th observation node in the P observation nodes is used for representing positioning information of the routing inspection entity for routing inspection of the e-th key hydropower equipment in the P key hydropower equipment, and e is a natural number which is not less than 1 and not more than P.

In this embodiment, the selected P observation nodes may be subjected to saliency processing, for example, special marks, highlighting or animation effects may be added to the nodes in the digital twin scene, so that the inspection entity can quickly and accurately identify them when performing the inspection operation.

This embodiment needs to ensure that each of the visualised observation nodes contains positional information about the critical hydropower device it characterizes. This means that when the inspection entity reaches the e-th observation node, the exact location of that observation node and the location information of the e-th critical hydropower device associated therewith can be known.

For example, the observation node of the 3 rd saliency process may contain an arrow mark pointing to a particular turbine and provide a data interface regarding the turbine's operational status and maintenance history.

In the inspection process, the embodiment can also provide real-time navigation information, guide the inspection entity to move along the first operation and maintenance inspection path, and provide the latest state update of the key hydropower equipment when approaching each observation node for the salification. This helps to ensure the accuracy and timeliness of the inspection.

Through the steps, the observation nodes can be effectively defined and rendered in the digital twin scene of the hydropower station, so that accurate inspection operation of key hydropower equipment is supported.

In one possible implementation, step B110 may include:

And B111, when the L observation nodes comprise Ge observation nodes and the observation penetration scene partition of each observation node comprises the e-th key hydropower equipment, acquiring operation scene state data of the node where the e-th key hydropower equipment is located, and generating Ge simulation inspection data streams corresponding to the Ge observation nodes based on the operation scene state data and the scene nodes corresponding to the Ge observation nodes, wherein Ge is a natural number not less than 2, and the Ge simulation inspection data streams are simulation inspection data streams generated by inspecting the e-th key hydropower equipment through simulation operation on the Ge observation nodes.

And step B112, determining a target simulation patrol data stream in the Ge simulation patrol data streams, and outputting an observation node corresponding to the target simulation patrol data stream in the Ge observation nodes as the e-th observation node.

After the first operation and maintenance routing cluster is determined and the L observation nodes are defined, the following detailed steps are further performed to determine the e-th observation node in the P observation nodes, so as to ensure that the e-th key hydropower device can be effectively observed by the observation node. The following are specific examples of scenarios:

The method comprises the steps of firstly analyzing L observation nodes, and finding that the e-th key hydropower device is contained in an observation penetration scene partition with Ge observation nodes. This means that the e-th critical hydropower device can be at least partially seen from any of the Ge observation nodes.

And then acquiring real-time operation scene state data of the node where the e-th key hydropower equipment is located. Such data may include the operating state of the device, environmental parameters (e.g., temperature, humidity), and any external factors that may affect the performance of the device.

With the acquired operational scenario status data, simulation operations may be performed for each observation node (i.e., ge observation nodes) containing the e-th critical hydropower device. These simulation operations simulate data that a patrol entity might collect when actually patrol the e-th critical hydropower device on each observation node. In this way, ge simulated patrol data streams corresponding to Ge observation nodes are generated.

After the Ge simulated patrol data streams are generated, they are evaluated and compared according to a series of predefined criteria (e.g., data stream sharpness, integrity, stability, etc.). Finally, an optimal simulated inspection data stream is selected as a target simulated inspection data stream. The target simulation inspection data flow provides the most accurate and reliable virtual inspection information for the e-th key hydropower equipment.

And finally, determining an observation node corresponding to the target simulation patrol data stream, and outputting the observation node as an e-th observation node. This observation node will become an important reference point for the inspection entity when actually performing the inspection operation, as it provides the best observation location for the e-th critical hydropower device.

Through the steps, the optimal observation node corresponding to each key hydropower device can be accurately determined, so that the efficiency and the accuracy of the inspection operation are improved.

In one possible embodiment, step B112 may include:

And step B1121, loading the Ge simulation patrol data streams to a target simulation effectiveness evaluation network, and determining Ge simulation effectiveness values corresponding to the Ge simulation patrol data streams based on the target simulation effectiveness evaluation network.

And step B1122, determining the target simulation patrol data stream in the Ge simulation patrol data streams based on the Ge simulation validity values, wherein the simulation validity value corresponding to the target simulation patrol data stream is the largest in the Ge simulation validity values.

In this embodiment, the generated Ge simulation patrol data streams are loaded into a pre-trained target simulation effectiveness evaluation network. The target simulation effectiveness evaluation network is a deep learning model that is capable of analyzing an input simulated inspection data stream and outputting a value indicative of the simulation effectiveness of the data stream.

Wherein the training configuration process of the target simulation effectiveness evaluation network involves a plurality of steps, which will be described in detail below:

First, a large number of simulated patrol data stream samples need to be collected, and the simulated patrol data stream samples should contain simulation data under different scenes and different equipment states. Meanwhile, each simulation inspection data stream sample needs to have corresponding actual inspection data as a label for supervised learning.

And then, the collected simulation inspection data stream samples are subjected to preprocessing operations such as cleaning, formatting, normalization and the like, so that the quality and consistency of the data are ensured, and model learning is facilitated. Based on this, a suitable deep learning model architecture, such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN), may be selected. And determining the characteristics of the simulated patrol data stream that can be received by the input layer of the simulated effectiveness evaluation network, and designing the output layer as a single or a plurality of neurons capable of outputting the simulated effectiveness value. In addition, a certain number of hidden layers can be designed according to the requirement, and a proper activation function is selected to capture the nonlinear relation in the data.

It is also necessary to set a suitable learning rate that determines the weight update step size of the simulation effectiveness evaluation network during training. And determining the number of data samples for training for each batch, which affects the training speed of the model and the stability of the gradient descent. And selecting an optimizer, such as random gradient descent (SGD), adam or RMSprop, for minimizing the loss function and updating the model weights. And, if necessary, regularization parameters (e.g., L1, L2 regularization coefficients) are set to prevent model overfitting. And defining a suitable loss function, such as a Mean Square Error (MSE) or cross entropy loss, for quantifying the difference between the predicted value and the actual label of the simulation effectiveness evaluation network.

On the basis, the preprocessed simulation routing inspection data stream sample can be divided into a training set, a verification set and a test set, wherein the training set is used for training a model, the verification set is used for adjusting super parameters, and the test set is used for evaluating the simulation effectiveness and evaluating the performance of the network. The simulation effectiveness evaluation network is iteratively trained using a training set, and model weights are updated by a back propagation algorithm and an optimizer to minimize a loss function. After each iteration cycle, the verification set is used for evaluating the model performance, and the weight parameters of the optimal simulation effectiveness evaluation network are recorded. An early-stop strategy may be employed to terminate training prematurely when performance on the validation set is no longer improving, preventing overfitting. And then, evaluating the performance of the final model by using the test set, calculating indexes such as accuracy, recall rate, F1 score and the like, and drawing a ROC curve, a confusion matrix and other visualization tools to perform performance analysis. And according to the evaluation result, optimizing the simulation effectiveness evaluation network, including adjusting the network structure, super parameters or trying different optimization algorithms, and the like.

Therefore, the trained target simulation effectiveness evaluation network can be deployed in an actual environment, and real-time support is provided for the evaluation of the simulation routing inspection data stream. In addition, the performance of the target simulation effectiveness evaluation network in practical application can be monitored regularly, feedback data are collected, and the model is updated and optimized when necessary. Therefore, an effective target simulation effectiveness evaluation network can be trained, and is used for accurately evaluating the simulation effectiveness of the simulation inspection data flow and assisting in determining the optimal observation node.

Therefore, the target simulation effectiveness evaluation network processes each input simulation inspection data stream, and calculates a simulation effectiveness value corresponding to each simulation inspection data stream through an algorithm in the target simulation effectiveness evaluation network and weight parameters obtained through training. The simulation effectiveness value is a quantization index used for measuring how much the simulation inspection data stream can accurately reflect the effect of actual inspection operation.

After obtaining the Ge simulation effectiveness values, these simulation effectiveness values are compared to find the largest one of them. The simulated inspection data stream corresponding to the maximum value is the data stream which can simulate the actual inspection operation and provide the most valuable observation information in all candidate data streams.

And finally, determining the simulated inspection data stream corresponding to the maximum simulation effectiveness value as a target simulated inspection data stream, and preparing to apply the target simulated inspection data stream to the subsequent inspection task planning and execution. Through the target simulation inspection data flow, an inspection entity can more accurately know the operation state of the e-th key hydropower equipment and possible problems.

Through the steps, the optimal one of the simulation inspection data streams can be selected by utilizing the target simulation effectiveness evaluation network, so that the intelligent level and efficiency of inspection operation are improved.

In a possible implementation manner, after the step B112, the embodiment may further render, in the digital twin scene of the hydropower station, positioning information and observing azimuth information of the e-th observation node and a node where the e-th observation node is located after the salifying, where the positioning information is used for characterizing positioning information that the inspection entity inspects the e-th key hydropower device, and the observing azimuth information is used for characterizing azimuth vector information of the inspection entity when the e-th key hydropower device performs multi-azimuth observation, based on the target simulation inspection data stream.

For example, the present embodiment first prepares data required for rendering the e-th observation node. These data include three-dimensional models of the observation nodes, texture maps, and models and data of key hydropower devices associated with the observation nodes. And necessary information such as the running state of the equipment, environmental parameters and the like can be extracted from the target simulation inspection data stream, so that the accuracy and instantaneity of a rendering result are ensured.

In a digital twin scene of a hydropower station, the e observation node can be subjected to salification. This may include changing the color of the node, adding a highlighting effect, or using dynamic markers to draw the attention of the patrol entity. The purpose of the saliency process is to make the observation nodes easily identified and located in complex digital twinning scenarios.

Next, the e-th observation node after the saliency processing is rendered in the digital twin scene. Meanwhile, positioning information and observing azimuth information related to the observing node can be rendered. The positioning information may be presented in the form of coordinates, marks or paths for accurately indicating the position in physical space where the inspection entity should arrive. The observation azimuth information may be displayed in the form of an arrow, an indicator or a three-dimensional direction indicator, so that the inspection entity is helped to know the direction and the angle which should be faced when the e-th key hydropower device is observed.

In order to ensure smooth running of the inspection operation, a real-time updating function can be further provided, so that the rendering result is updated according to the actual state change of the equipment in the inspection process. In addition, an interactive function can be supported, allowing the inspection entity to interact with the digital twin scene through an interface, such as zooming in, zooming out, rotating the view, or selecting to view the observed azimuth information at different angles.

Through the steps, the observation node after the salification and the relevant positioning information and the observation azimuth information thereof can be accurately and intuitively displayed in the digital twin scene of the hydropower station, so that the inspection entity is assisted to efficiently and accurately execute the inspection task.

Fig. 2 illustrates a hardware structural intent of an AI-based hydropower device operation and maintenance decision system 100 for implementing the above-described AI-based hydropower device operation and maintenance decision method according to an embodiment of the invention, as shown in fig. 2, the AI-based hydropower device operation and maintenance decision system 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

In an exemplary design, the AI-based hydropower device operation and maintenance decision system 100 may be a single server or a group of servers. The server set may be centralized or distributed (e.g., the AI-based hydropower device operation and maintenance decision system 100 may be a distributed system). In an exemplary design, the AI-based hydropower device operation and maintenance decision system 100 can be local or remote. For example, the AI-based hydropower device operation and maintenance decision system 100 can access information and/or data stored in the machine-readable storage medium 120 via a network. As another example, the AI-based hydropower device operational decision system 100 can be directly connected to the machine-readable storage medium 120 to access stored information and/or data. In an exemplary design concept, the AI-based hydropower device operation and maintenance decision system 100 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

The machine-readable storage medium 120 may store data and/or instructions. In an exemplary design, machine-readable storage medium 120 may store data obtained from an external terminal. In an exemplary design concept, the machine-readable storage medium 120 may store data and/or instructions for use by the AI-based hydropower device operation and maintenance decision system 100 to perform or use to perform the exemplary methods described herein. In an exemplary design, machine-readable storage medium 120 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, tape, and the like. Exemplary volatile read-write memory can include Random Access Memory (RAM). Exemplary RAM may include active random access memory (DRAM), double data rate synchronous active random access memory (DDR SDRAM), passive random access memory (SRAM), thyristor random access memory (T-RAM), zero capacitance random access memory (Z-RAM), and the like. Exemplary read-only memory may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (PEROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disk read-only memory, and the like. In an exemplary design, machine-readable storage medium 120 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

In a specific implementation, at least one processor 110 executes computer-executable instructions stored by the machine-readable storage medium 120, so that the processor 110 may execute the AI-based hydropower device operation and maintenance decision method of the method embodiment above, the processor 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 may be used to control the transceiving actions of the communication unit 140.

The specific implementation process of the processor 110 may refer to the above embodiments of the method performed by the AI-based operation and maintenance decision system 100 for a hydropower device, and the implementation principle and technical effects are similar, which are not described herein again.

In addition, the embodiment of the invention also provides a readable storage medium, wherein computer executable instructions are preset in the readable storage medium, and when a processor executes the computer executable instructions, the above AI-based hydropower equipment operation and maintenance decision method is realized.

It is to be understood that the above description is intended to be illustrative only and is not intended to limit the scope of the present invention. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the description of the invention. However, such modifications and variations do not depart from the scope of the present invention.

While the basic concepts have been described above, it will be apparent to those of ordinary skill in the art after reading this application that the above disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the invention may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.

Meanwhile, the present invention uses specific words to describe embodiments of the present invention. For example, "one embodiment," "an embodiment," and/or "some embodiments" means a particular feature, structure, or characteristic in connection with at least one embodiment of the invention. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the invention may be combined as suitable.

Furthermore, those of ordinary skill in the art will appreciate that the various aspects of the invention are capable of being illustrated and described in connection with a variety of patentable categories or circumstances, including any novel and useful process, machine, product, or combination of materials, or any novel and useful modifications thereof. Accordingly, aspects of the present invention may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "unit," module, "or" system. Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media, wherein the computer-readable program code is embodied therein.

The computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable signal medium may be propagated in connection with any suitable medium including radio, cable, fiber optic cable, RF, or the like, or any combination thereof.

The computer program code necessary for operation of portions of the present invention may be written in any one or more programming languages, including a body oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., a conventional programming language such as C language, visual basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, an active programming language such as python, ruby and groovy, or other programming languages, etc. The program code may execute entirely on the computer or as a stand-alone software package, partly on the computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the computer in any network form, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, in connection with the Internet), or the connection may be made to a cloud computing environment, or as a service, such as software as a service (SaaS).

Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the invention is not intended to limit the sequence of the processes and methods unless specifically recited in the claims. While certain presently useful inventive embodiments have been discussed in connection with various examples thereof, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the invention. For example, while the system components described above may be implemented in connection with hardware devices, it may also be implemented in connection with software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more embodiments of the invention, various features are sometimes grouped together in a single embodiment, figure, or description thereof. Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more embodiments of the invention, various features are sometimes grouped together in a single embodiment, figure, or description thereof.

Claims

1. An AI-based hydropower device operation and maintenance decision method, the method comprising:

2. The AI-based hydropower device operation and maintenance decision method of claim 1, wherein determining a first operation and maintenance inspection path cluster among the operation and maintenance inspection path clusters each constituted by the Y operation and maintenance inspection paths comprises:

3. The AI-based hydropower device operation and maintenance decision method of claim 1, further comprising:

4. The AI-based hydropower device operation and maintenance decision method of claim 3, wherein determining a second operation and maintenance inspection path cluster among the operation and maintenance inspection path clusters each constituted by the Y operation and maintenance inspection paths comprises:

5. The AI-based hydropower device operation and maintenance decision method according to claim 4, wherein when the W key hydropower devices are included in an h one of the Z observed penetration scene partitions, outputting an h one of the Z operation and maintenance routing path clusters corresponding to the h one of the Z observed penetration scene partitions as the second operation and maintenance routing path cluster, comprising:

6. The AI-based hydropower device operation and maintenance decision method of claim 1, wherein after determining a first operation and maintenance inspection path cluster among the operation and maintenance inspection path clusters each constituted by the Y operation and maintenance inspection paths, the method further comprises:

7. The AI-based hydropower device operation and maintenance decision method of claim 6, wherein the determining P of the L observation nodes based on the observation penetration scene partition of each of the L observation nodes comprises:

8. The AI-based hydropower device operation and maintenance decision method of claim 7, wherein the determining a target simulated inspection data stream from the Ge simulated inspection data streams comprises:

9. The AI-based hydropower device operation and maintenance decision method of claim 8, wherein after determining a target simulated inspection data stream from the Ge simulated inspection data streams, the method further comprises:

10. An AI-based hydropower device operation and maintenance decision system, comprising a processor and a machine-readable storage medium having stored therein machine-executable instructions loaded and executed by the processor to implement the AI-based hydropower device operation and maintenance decision method of any one of claims 1-9.