WO2020228346A1

WO2020228346A1 - Transformer substation three-dimensional digital modeling method, system and device and storage medium

Info

Publication number: WO2020228346A1
Application number: PCT/CN2019/129939
Authority: WO
Inventors: 李新福
Original assignee: 广东康云科技有限公司
Priority date: 2019-05-14
Filing date: 2019-12-30
Publication date: 2020-11-19
Also published as: CN110322546A

Abstract

Disclosed are a transformer substation three-dimensional digital modeling method, system and device and a storage medium. The method comprises: acquiring three-dimensional data in a transformer substation, processing the three-dimensional data by means of an artificial intelligence algorithm to obtain three-dimensional model data, and uploading the three-dimensional model data; and carrying out integration processing on the obtained three-dimensional model data, and constructing to obtain a three-dimensional model of a transformer substation. According to the present invention, both scanning collection and modeling calculation are completed at the front end at the same time, so that the modeling time of a cloud server at a later stage is greatly shortened, thereby improving the modeling speed and efficiency of the three-dimensional model of the transformer substation. The present invention can be widely applied to transformer substation modeling.

Description

Three-dimensional digital modeling method, system, device and storage medium of substation

Technical field

The present invention relates to the technical field of three-dimensional modeling, in particular to a three-dimensional digital modeling method, system, device and storage medium of a substation.

Background technique

Substations play a pivotal role in our modern life. Realizing data collection and modeling of substations with information technology is a new trend in the development and application of the power industry. The first task for substation data modeling is to collect data. The traditional substation modeling method mainly uses professional 3D modeling software to repair and modify the collected substation data, which requires professional and technical personnel to spend a lot of time and energy to complete, and this method of modeling takes a long time. Low efficiency.

Summary of the invention

In order to solve the above technical problems, the purpose of the present invention is to provide a three-dimensional digital modeling method, system, device and storage medium for a substation that can improve modeling efficiency.

The technical scheme adopted by the present invention is:

A three-dimensional digital modeling method for substations includes the following steps:

Obtain 3D data in the substation and process the 3D data through artificial intelligence algorithms at the same time to obtain and upload 3D model data;

The obtained three-dimensional model data is integrated and processed to construct a three-dimensional model of the substation.

As a further improvement of the aforementioned three-dimensional digital modeling method for substations, the step of acquiring three-dimensional data in the substation and simultaneously processing the three-dimensional data through artificial intelligence algorithms to obtain and upload three-dimensional model data includes:

Scanning the substation by a scanning device to obtain three-dimensional data, the three-dimensional data including the substation image and depth information;

The 3D data is processed by artificial intelligence algorithms to obtain and upload 3D model data.

As a further improvement of the aforementioned three-dimensional digital modeling method for a substation, the substation image includes an image of a substation room, an image of instrumentation in the room, an image of an outdoor facility, and an image of on-site construction of the substation.

As a further improvement of the aforementioned three-dimensional digital modeling method for substations, the three-dimensional data is processed by artificial intelligence algorithms to obtain and upload three-dimensional model data. This step specifically includes:

Perform a first processing operation according to the three-dimensional data, the first processing operation including denoising, UV optimization and anti-aliasing;

Perform a second processing operation according to the result of the first processing operation to obtain the original three-dimensional model data. The second processing operation includes sharpening, denoising, saturation optimization, picture HDR optimization, coloring, model repair, and rendering optimization. The second processing operation also uses artificial intelligence algorithms and super pixel algorithms for image processing;

The original 3D model data is compressed, and the compressed 3D model data is obtained and uploaded.

As a further improvement of the three-dimensional digital modeling method for campus, the three-dimensional model data obtained is integrated and processed to construct a three-dimensional substation model. This step specifically includes:

Further processing the obtained 3D model data through artificial intelligence algorithms to obtain the 3D model data after secondary processing;

Integrate all the three-dimensional model data after secondary processing to construct a three-dimensional model of the substation.

As a further improvement of the three-dimensional digital modeling method for substations, it also includes the following steps:

Display the three-dimensional model of the substation to display the three-dimensional model of the substation through at least one of a smart display screen, an AR device, a VR device, and a browser. The smart display screen includes an air imaging device, an air screen, a mobile terminal, and a tablet computer Terminal, PC computer terminal, LED display, LCD display, OLED display and dot matrix display.

As a further improvement of the three-dimensional digital modeling method for substations, the artificial intelligence algorithm includes a deep learning algorithm, and the deep learning algorithm uses a generative confrontation network model.

Another technical solution adopted by the present invention is:

A three-dimensional digital modeling system for substations, including:

The image acquisition and processing unit is used to obtain 3D data in the substation and at the same time process the 3D data through artificial intelligence algorithms to obtain and upload 3D model data;

The cloud server is used to integrate and process the obtained 3D model data to construct a 3D model of the substation.

Another technical solution adopted by the present invention is:

A three-dimensional digital modeling device for substations, including:

At least one processor;

At least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor realizes the three-dimensional digital modeling method of the substation.

Another technical solution adopted by the present invention is:

A computer-readable storage medium includes a computer program. When the computer program runs on a computer, the campus three-dimensional digital modeling method is executed.

The beneficial effects of the present invention are:

The three-dimensional digital modeling method, system, device and storage medium of the substation of the present invention complete scanning acquisition and modeling calculation at the same time at the front end, thereby greatly reducing the modeling time of the later cloud server, and effectively improving the modeling speed and efficiency of the three-dimensional model of the substation .

Description of the drawings

Figure 1 is a flow chart of an embodiment of a three-dimensional digital modeling method for a substation of the present invention;

Fig. 2 is a block diagram of an embodiment of a three-dimensional digital modeling system for a substation of the present invention.

Detailed ways

The specific embodiments of the present invention will be further described below in conjunction with the drawings:

It should be noted that, unless otherwise specified, when a feature is called "fixed" or "connected" to another feature, it can be directly fixed and connected to another feature, or indirectly fixed or connected to another feature. One feature. In addition, the top, bottom, left, right and other descriptions used in the present disclosure are only relative to the mutual positional relationship of the components of the present disclosure in the drawings. The singular forms of "a", "said" and "the" used in the present disclosure are also intended to include plural forms, unless the context clearly indicates other meanings. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art. The terms used in this specification are only for describing specific embodiments, not for limiting the present invention. The term "and/or" as used herein includes any combination of one or more related listed items.

It should be understood that, although the terms first, second, third, etc. may be used in this disclosure to describe various elements, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, without departing from the scope of the present disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element. The use of any and all examples or exemplary language ("such as", "such as", etc.) provided herein is only intended to better illustrate the embodiments of the present invention, and unless otherwise required, will not impose limitations on the scope of the present invention .

Referring to Fig. 1, an embodiment of the present invention provides a three-dimensional digital modeling method for a substation, including the following steps:

S1. Obtain 3D data in the substation and process the 3D data through artificial intelligence algorithms at the same time to obtain 3D model data and upload it;

In this embodiment, the three-dimensional data in the substation includes an image of a substation room, an image of instruments and meters in the room, an image of an outdoor facility, and an image of on-site construction of the substation. It can be collected by manual or automatic scanning equipment (such as cameras, aerial drones, automatic scanning robots, etc.).

Model repair is mainly to repair the holes and other structures that affect the display effect in the generated model. The texture processing is mainly for UV optimization, and image bonding according to the two-dimensional image and depth information obtained by the scanning equipment, etc., so as to paste the two-dimensional image on the three-dimensional model according to the depth information. Super-resolution processing mainly uses super-resolution algorithms to improve the resolution of the picture. Semantic segmentation is to meet the requirements of artificial intelligence algorithms.

In this embodiment, a camera equipped with a GPU is used for image collection. Therefore, an artificial intelligence algorithm can also be used to process the obtained three-dimensional data while collecting images, which greatly improves the speed of modeling.

S2. Integrate the obtained three-dimensional model data to construct a three-dimensional model of the substation.

In this embodiment, a camera equipped with a GPU is used for image collection. Therefore, while collecting images, artificial intelligence algorithms can also be used to process the obtained three-dimensional data. In this way, most of the three-dimensional data has been processed in the front end, which greatly It reduces the burden of the cloud server, and effectively shortens the modeling time, greatly improving the modeling speed and efficiency.

The three-dimensional model of the substation is a virtual 3D model, which can be accessed by users through browser links (such as URL links) for 360-degree browsing or viewing without blind spots, and can be viewed through air imaging devices, air screens, mobile terminals, and tablet computers. , PC computer terminal, LED display, LCD display, OLED display and dot matrix display, etc. interact with users to achieve model enlargement, reduction, color change and visual switching, meeting the individual needs of different viewers. The present invention supports different intelligent terminals and devices such as air imaging devices, air screens, mobile terminals, tablet computers, PC computers, LED displays, LCD displays, OLED displays, and dot matrix displays to access and access 3D models. Display, more functions.

Further as a preferred embodiment, the step of acquiring three-dimensional data in the substation and simultaneously processing the three-dimensional data through artificial intelligence algorithms to obtain and upload three-dimensional model data includes:

S11. Scan the substation by scanning equipment to obtain three-dimensional data, where the three-dimensional data includes the substation image and depth information;

In this embodiment, the scanning device includes at least one of an aerial scanner, an indoor scanner, an outdoor scanning model, an object scanner, and a human body scanner; and the scanning device in this embodiment is equipped with a GPU, The image can also be processed by artificial intelligence algorithms on the obtained three-dimensional data.

Specifically, the aerial scanner may use an unmanned aerial vehicle with a camera or other aerial scanning equipment, which can obtain scan data of a specific area in a certain substation through aerial scanning.

The indoor scanner can be a handheld scanning device (such as a camera with a support frame) or other automatic scanning equipment (such as an automatic scanning robot), which can scan spatial data in the substation room.

The outdoor scanner can be a handheld scanning device (such as a camera with a support frame) or other automatic scanning equipment (such as an automatic scanning robot), which can scan spatial data outside the substation.

The object scanner can be a handheld scanning device (such as an RGB-D camera with a support frame, etc.), which can scan the structure data of the equipment in the substation.

The human body scanner may be an existing human body scanner specifically for human body modeling, which can scan three-dimensional data of the human body.

The above-mentioned scanning devices all have edge computing capabilities and are integrated with GPU chips, which can perform artificial intelligence algorithm processing on collected two-dimensional images and other data locally, so that most of the three-dimensional data has been processed at the front end. It greatly reduces the burden of the cloud server, and effectively shortens the modeling time, greatly improving the modeling speed and efficiency. Scanning equipment applies optical principles, uses RGB or depth camera, lidar, structured light and other methods to measure the distance of objects, indoor and outdoor space, aerial survey geographic information, etc., and collect data model of the object structure, scan and calculate, and upload Intelligent optimization and data restoration for cloud servers.

S12. Process the three-dimensional data through artificial intelligence algorithms to obtain and upload three-dimensional model data.

Further as a preferred embodiment, the three-dimensional data is processed by artificial intelligence algorithms to obtain and upload three-dimensional model data. This step specifically includes:

S111. Perform a first processing operation according to the three-dimensional data, where the first processing operation includes denoising, UV optimization, and anti-aliasing.

S112. Perform a second processing operation according to the result of the first processing operation to obtain original 3D model data, where the second processing operation includes sharpening, denoising, saturation optimization, picture HDR optimization, coloring, model repair, and rendering optimization. The second processing operation also uses artificial intelligence algorithms and super pixel algorithms for image processing;

S23. Compress the original three-dimensional model data to obtain and upload the compressed three-dimensional model data.

In this embodiment, the substation image and depth information collected by the scanning device are simultaneously processed using artificial intelligence algorithms and super pixel algorithms.

Among them, the scanning equipment can use GPU, with artificial intelligence algorithms and graphics and image algorithms to achieve fast calculation, fully automatic 3D modeling and optimization, without manual intervention.

After the model data (such as point cloud data and photos) are collected, the scanning device will process the model data as follows:

1) Model (mainly point cloud data) denoising Denoise;

2) Model UV optimization;

3) Model de-aliasing Remove Compression Artefacts.

After the model has been processed above, the following processing needs to be done on the collected photos:

1) Picture sharpening;

2) Picture denoising;

3) Picture Saturation (saturation) optimization;

4) Picture HDR+ optimization;

5) AI (artificial intelligence) + super pixel algorithm processing.

The key to the display effect of a model lies in the quality of the model and the quality of the image. The traditional way is generally to repair and modify the image manually. In this embodiment, the AI+ algorithm is used to upgrade the quality of the model and the image, using the least computing power to achieve the highest quality The display effect does not require manual labor at all, and AI+3D automatic intelligent modeling is realized through artificial intelligence combined with graphics and image algorithms.

Further as a preferred embodiment, the step of integrating the obtained three-dimensional model data to construct a three-dimensional model of the substation includes:

S21, further processing the obtained three-dimensional model data through artificial intelligence algorithms to obtain the three-dimensional model data after secondary processing;

In this embodiment, most of the processing on the three-dimensional model data has been performed in the front end, so the cloud only needs to perform subsequent processing on the three-dimensional model data through artificial intelligence algorithms to obtain the three-dimensional model data after the secondary processing. For example, the front-end has already generated two-thirds of the three-dimensional model of the substation through artificial intelligence algorithms, so the cloud only needs to use the same artificial intelligence algorithm as the front-end to generate the remaining one-third of the three-dimensional model of the substation.

S22. Integrate all the three-dimensional model data after secondary processing to construct a three-dimensional model of the substation.

In this embodiment, the front end only has a variety of scanning devices to scan each part of the substation. Therefore, the cloud can obtain 3D model data about each part of the substation from the front end. After the cloud performs secondary processing on the 3D model data, it will The three-dimensional model data of each part is integrated, so that a complete three-dimensional model of the substation can be constructed.

Further as a preferred embodiment, it also includes the following steps:

S3. Display the three-dimensional model of the substation to display the three-dimensional model of the substation through at least one of a smart display screen, an AR device, a VR device, and a browser. The smart display screen includes an air imaging device, an air screen, a mobile terminal, Tablet computer terminal, PC computer terminal, LED display, LCD display, OLED display and dot matrix display.

Specifically, the three-dimensional model of the substation in this embodiment can support online and offline display of various screens or cross-platform display, such as air imaging devices, air screens, mobile terminals, tablet computers, PC computers, LED displays, On the LCD display, OLED display, and dot matrix display, users only need to access them through the corresponding links (such as URL links), eliminating the need for the process of loading APP, which is more efficient and more convenient.

Further as a preferred embodiment, the artificial intelligence algorithm includes a deep learning algorithm, and the deep learning algorithm adopts a generative confrontation network model.

Specifically, this embodiment uses the GANs (Generated Adversarial Network) model to perform image generation, image repair, image denoising, image super-resolution, draft image restoration, image coloring, etc., to achieve a fully automated intelligent model and image without manual labor. optimization. Generating adversarial network models is one of the important methods in unsupervised learning. Compared with unsupervised learning methods such as autoencoders and autoregressive models, it has the advantages of being able to fully fit data, faster, and more sharply generated samples.

Referring to Figure 2, a three-dimensional digital modeling system for substations includes:

The contents of the above method embodiments are all applicable to this system embodiment, and the specific functions implemented by this system embodiment are the same as the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

Further as a preferred embodiment, the image acquisition and processing unit specifically includes:

The scanning unit is used to scan the substation through the scanning device to obtain three-dimensional data, the three-dimensional data including the substation image and depth information;

The three-dimensional processing unit is used to process three-dimensional data through artificial intelligence algorithms to obtain and upload three-dimensional model data.

Further as a preferred embodiment, the three-dimensional processing unit includes:

The first processing unit is configured to perform a first processing operation according to the three-dimensional data, the first processing operation including denoising, UV optimization and anti-aliasing processing;

The second processing unit is configured to perform a second processing operation according to the result of the first processing operation to obtain the original three-dimensional model data. The second processing operation includes sharpening, denoising, saturation optimization, picture HDR optimization, coloring, and modeling Repair and rendering optimization, the second processing operation also uses artificial intelligence algorithms and super pixel algorithms for image processing;

The compression unit is used to compress the original 3D model data to obtain the compressed 3D model data and upload it.

The present invention also provides a three-dimensional digital modeling device for a substation, which includes:

At least one processor;

At least one memory for storing at least one program;

The present invention also provides a computer readable storage medium, including a computer program, when the computer program runs on a computer, the campus three-dimensional digital modeling method is executed.

To sum up, the three-dimensional digital modeling method, system, device and storage medium of the substation of the present invention complete scanning acquisition and modeling calculation at the same time at the front end, thereby greatly reducing the modeling time of the later cloud server and effectively improving the three-dimensional model of the substation. Modeling speed and efficiency.

It should be realized that the embodiments of the present invention can be realized or implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method can be implemented in a computer program using standard programming techniques-including a non-transitory computer readable storage medium configured with a computer program, where the storage medium so configured allows the computer to operate in a specific and predefined manner-according to the specific The methods and drawings described in the examples. Each program can be implemented in a high-level process or object-oriented programming language to communicate with the computer system. However, if necessary, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.

In addition, the operations of the processes described herein may be performed in any suitable order, unless otherwise indicated herein or otherwise clearly contradictory to the context. The processes (or variants and/or combinations thereof) described herein can be executed under the control of one or more computer systems configured with executable instructions, and can be used as code (for example, , Executable instructions, one or more computer programs, or one or more applications), implemented by hardware or a combination thereof. The computer program includes a plurality of instructions executable by one or more processors.

Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computing platform, including but not limited to a personal computer, a mini computer, a main frame, a workstation, a network or a distributed computing environment, a separate or integrated computer Platform, or communication with charged particle tools or other imaging devices, etc. Aspects of the present invention can be implemented by machine-readable codes stored on non-transitory storage media or devices, whether removable or integrated into a computing platform, such as hard disks, optical reading and/or writing storage media, RAM, ROM, etc., so that they can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. In addition, the machine-readable code, or part thereof, can be transmitted through a wired or wireless network. When such a medium includes instructions or programs that implement the steps described above in combination with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programming according to the methods and techniques of the present invention, the present invention also includes the computer itself.

A computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data that is stored in non-volatile memory. The output information can also be applied to one or more output devices such as displays. In a preferred embodiment of the present invention, the converted data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.

The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. These equivalent modifications or replacements are all included in the scope defined by the claims of this application.

Claims

A three-dimensional digital modeling method for a substation is characterized in that it includes the following steps:

Obtain 3D data in the substation and process the 3D data through artificial intelligence algorithms at the same time to obtain and upload 3D model data;

The obtained three-dimensional model data is integrated and processed to construct a three-dimensional model of the substation.
A three-dimensional digital modeling method for a substation according to claim 1, wherein the step of obtaining three-dimensional data in the substation and processing the three-dimensional data through artificial intelligence algorithms at the same time to obtain and upload three-dimensional model data Specifically:

Scanning the substation by a scanning device to obtain three-dimensional data, the three-dimensional data including the substation image and depth information;

The 3D data is processed by artificial intelligence algorithms to obtain and upload 3D model data.
A three-dimensional digital modeling method for a substation according to claim 2, wherein the substation image includes an image of a substation room, an image of instrumentation in the room, an image of outdoor facilities, and an image of on-site construction of the substation.
A three-dimensional digital modeling method for a substation according to claim 2, wherein the step of processing three-dimensional data through artificial intelligence algorithms to obtain and upload three-dimensional model data specifically includes:

Perform a first processing operation according to the three-dimensional data, the first processing operation including denoising, UV optimization and anti-aliasing;

Perform a second processing operation according to the result of the first processing operation to obtain the original three-dimensional model data. The second processing operation includes sharpening, denoising, saturation optimization, picture HDR optimization, coloring, model repair, and rendering optimization. The second processing operation also uses artificial intelligence algorithms and super pixel algorithms for image processing;

The original 3D model data is compressed, and the compressed 3D model data is obtained and uploaded.
A three-dimensional digital modeling method for a substation according to claim 1, wherein the step of integrating the obtained three-dimensional model data to construct a three-dimensional model of the substation specifically includes:

Further processing the obtained 3D model data through artificial intelligence algorithms to obtain the 3D model data after secondary processing;

Integrate all the three-dimensional model data after secondary processing to construct a three-dimensional model of the substation.
A three-dimensional digital modeling method for a substation according to claim 1, characterized in that it further comprises the following steps:

Display the three-dimensional model of the substation to display the three-dimensional model of the substation through at least one of a smart display screen, an AR device, a VR device, and a browser. The smart display screen includes an air imaging device, an air screen, a mobile terminal, and a tablet computer Terminal, PC computer terminal, LED display, LCD display, OLED display and dot matrix display.
A three-dimensional digital modeling method for a substation according to claim 1, wherein the artificial intelligence algorithm includes a deep learning algorithm, and the deep learning algorithm uses a generative confrontation network model.
A three-dimensional digital modeling system for substation, which is characterized in that it includes:

The image acquisition and processing unit is used to obtain 3D data in the substation and at the same time process the 3D data through artificial intelligence algorithms to obtain and upload 3D model data;

The cloud server is used to integrate and process the obtained 3D model data to construct a 3D model of the substation.
A three-dimensional digital modeling device for a substation, which is characterized in that it includes:

At least one processor;

At least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor realizes the three-dimensional digital modeling method for a substation according to any one of claims 1-6.
A computer-readable storage medium, characterized by comprising a computer program, when the computer program is run on a computer, the campus three-dimensional digital modeling method according to any one of claims 1-7 is executed.