Ai-based intelligent energy generation integrated operation system

Abstract

A system according to one embodiment of the present disclosure comprises: a plurality of power generation facilities installed within a first power plant; at least one sensor and a plurality of camera devices mounted within the first power plant; and a first server, wherein the first server: generates and updates a digital twin platform for the operation of the first power plant based on a first database related to the plurality of power generation facilities, first sensing data acquired through the at least one sensor, and a plurality of images acquired from the plurality of camera devices; monitors whether a dangerous situation event occurs for each of the plurality of power generation facilities based on the first database and the first sensing data; and, based on the detection of a first dangerous situation event related to the first power generation facility among the plurality of power generation facilities, identifies a first worker related to the first dangerous situation event and transmits information related to the first dangerous situation event to a first terminal device used by the identified first worker, and the first terminal device may: provide information related to the first dangerous situation event on a first screen representing the digital twin platform.

Description

Technology Field

[0001] The present disclosure relates to power plant integrated operation technology, and more specifically, to an artificial intelligence (AI)-based intelligent energy generation integrated operation system. Background Technology

[0003] AI is a collective term for technologies in the field of computer science that implement human intellectual abilities—specifically, complex human capabilities such as learning, reasoning, perception, judgment, and language comprehension—using electronic methods. By mimicking human thinking patterns, AI can create systems that analyze data and, in the process, recognize patterns, solve problems, and acquire new knowledge.

[0004] The core principle of AI is that computers independently discover rules and patterns within vast amounts of data and, based on this, automatically perform various tasks such as prediction and classification. In this process, artificial intelligence algorithms repeatedly learn from input data and gradually improve accuracy through the setting of biases and weights. Ultimately, these learning-based models can respond to new inputs in a manner similar to humans or effectively solve complex problems.

[0005] As AI is integrated and applied across various fields, it can enhance efficiency and productivity. For example, AI can be applied to manufacturing infrastructure, such as smart factories, or energy generation facilities. However, the industry is still discussing how to integrate AI technology into such facilities. The problem to be solved

[0007] The purpose of the present disclosure is to provide an artificial intelligence-based intelligent energy generation integrated operation system.

[0008] The purpose of the present disclosure is to provide a system for optimizing power generation efficiency and reducing carbon emissions based on AI and digital twins.

[0009] The purpose of the present disclosure is to provide a digital twin-based power plant safety and fault response system combined with AI predictive maintenance and a Real-Time Location System (RTLS).

[0010] The purpose of the present disclosure is to provide a power plant worker safety management system that integrates AI image analysis and RTLS.

[0011] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0013] A system according to one embodiment of the present disclosure comprises: a plurality of power generation facilities installed within a first power plant; at least one sensor and a plurality of camera devices mounted within the first power plant; and a first server, wherein the first server: generates and updates a digital twin platform for the operation of the first power plant based on a first database related to the plurality of power generation facilities, first sensing data acquired through the at least one sensor, and a plurality of images acquired from the plurality of camera devices; monitors whether a dangerous situation event occurs for each of the plurality of power generation facilities based on the first database and the first sensing data; and, based on the detection of a first dangerous situation event related to the first power generation facility among the plurality of power generation facilities, identifies a first worker related to the first dangerous situation event and transmits information related to the first dangerous situation event to a first terminal device used by the identified first worker, and the first terminal device may: provide information related to the first dangerous situation event on a first screen representing the digital twin platform.

[0014] And, the information related to the first dangerous situation event includes: the type of the first dangerous situation event, the type of the first power generation facility, the management history of the first power generation facility, and standard manual information for resolving the first dangerous situation event, and the first terminal device identifies a first 3D (dimension) model corresponding to the first power generation facility displayed in the first screen based on the information related to the first dangerous situation event; and can overlay a second screen containing information related to the first dangerous situation event on the area where the first 3D model is located.

[0015] And, the system further includes a second terminal device used by an administrator, and the first server: overlays the movement path of the first worker on the first screen through at least one of the first terminal device or a communication tag device worn by the first worker; and the second terminal device: can display the first screen on which the movement path of the first worker is overlaid.

[0016] And, the first database includes at least one of the operating speed, power generation amount, fuel consumption, power trading unit price, power generation efficiency, internal pressure, or management history of each of the plurality of power generation facilities, and the first server inputs the first database and the first sensing data into a first artificial intelligence (AI) model according to a predefined period to obtain a risk index for each of the plurality of power generation facilities; and can determine that the first risk situation event related to the first power generation facility is detected based on the risk index of the first power generation facility among the plurality of power generation facilities exceeding a first threshold value.

[0017] And, the first server calculates carbon emissions for each of the plurality of power generation facilities based on the fuel consumption of each of the plurality of power generation facilities; and can overlay information regarding carbon emissions of the second facility among the plurality of power generation facilities onto the area where the second power generation facility is located, which is displayed within the first screen. Effects of the invention

[0019] By various embodiments of the present disclosure, an artificial intelligence-based intelligent energy generation integrated operation system may be provided.

[0020] By various embodiments of the present disclosure, an AI and digital twin-based power generation efficiency optimization and carbon emission reduction system can be provided.

[0021] By various embodiments of the present disclosure, a digital twin-based power plant safety and fault response system combined with AI predictive maintenance and RTLS can be provided.

[0022] By various embodiments of the present disclosure, a power plant worker safety management system fused with AI image analysis and RTLS can be provided.

[0023] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0025] FIG. 1 is a drawing for illustrating an artificial intelligence-based intelligent energy generation integrated operation system according to one embodiment of the present disclosure. FIG. 2 is a drawing for explaining the configuration of a first server according to one embodiment of the present disclosure. FIG. 3 is a diagram illustrating a method for controlling an artificial intelligence-based intelligent energy generation integrated operation system according to one embodiment of the present disclosure. Specific details for implementing the invention

[0026] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure is complete and to fully inform those skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

[0027] The terms used herein are for describing the embodiments and are not intended to limit the disclosure. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the components mentioned.

[0028] Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more thereof. Although terms such as "first," "second," etc., are used to describe various components, they are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of this disclosure.

[0029] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0030] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to easily describe the relationship between one component and another, as illustrated in the drawings. Spatially relative terms should be understood as encompassing the different directions of the components during use or operation, in addition to the directions depicted in the drawings.

[0031] For example, if a component depicted in a drawing is inverted, a component described as being "below" or "beneath" another component may be placed "above" the other component. Therefore, the exemplary term "below" may encompass both the downward and upward directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation.

[0032] Below, the AI-based intelligent energy generation integrated operation system will be described in detail with reference to the drawings.

[0033] In describing the present disclosure, an artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values ​​and performs neural network operations through operations between the results of operations of a previous layer and the plurality of weights. The plurality of weights possessed by the plurality of neural network layers may be optimized by the learning results of the artificial intelligence model. For example, the plurality of weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a Deep Neural Network (DNN), such as a Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, but is not limited to the examples described above.

[0034] FIG. 1 is a diagram illustrating the configuration of an artificial intelligence-based intelligent energy generation integrated operation system according to one embodiment of the present disclosure.

[0035] As illustrated in FIG. 1, an artificial intelligence-based intelligent energy generation integrated operation system (1000) may include a first server (100), a terminal device (200) used by an administrator, terminal devices (300-1, 300-2, ..., 300-N) used by each of a plurality of workers, and a first power plant (400).

[0036] In describing the present disclosure, the terminal device (200) used by the administrator and the terminal devices (300-1, 300-2, ..., 300-N) used by each of the plurality of workers may be implemented as a smartphone, PC, laptop, wearable device, server device, etc., but are not limited thereto. Each of the terminal device (200) used by the administrator and the terminal devices (300-1, 300-2, ..., 300-N) used by the plurality of workers may be implemented as various types of electronic devices.

[0037] In describing the present disclosure, the term "manager" may collectively refer to a person who manages a power plant and / or a plurality of workers working within the power plant. The term "worker" may collectively refer to a person who operates, controls, manages, and repairs various power generation facilities, etc., within the power plant.

[0038] In addition, the first power plant (400) in FIG. 1 may include various power generation facilities, sensors and / or camera devices, etc. within the first power plant. For example, the power generation facilities may include a power turbine, a generator, a transformer, a boiler, etc. The power turbine (and / or generator) may include not only a thermal power generation turbine but also a solar / wind power generation turbine, etc. Each sensor may include a humidity sensor, a hazardous gas detection sensor (e.g., a sensor that detects hazardous gas concentration, etc.), a temperature sensor, a pressure sensor, etc., but is not limited thereto. In addition, the camera device may acquire image / video data of the installed area in real time.

[0039] Each component of the first power plant (400) may include a communication module (e.g., a wireless communication module and / or a wired communication module). For example, each component of the first power plant (400) may periodically and / or in real time transmit acquired data to the first server (100) through the communication module.

[0040] The first server (100) can create and update a digital twin platform for the operation, control, and / or monitoring of the first power plant (400) based on various data received from the first power plant (400).

[0041] Here, the digital twin platform refers to a platform (or an application that can access / experience said platform) that replicates physical objects (e.g., power generation equipment, sensors and / or camera devices) and / or processes within the first power plant (400) in digital space. As an example, the digital twin platform may be implemented in the form of a 3D map that can view physical objects and / or various sensing data within the first power plant (400).

[0042] A terminal device (200) used by an administrator and / or a terminal device (300-1, 300-2, ..., 300-N) used by multiple workers can verify and / or control physical objects and / or processes within the first power plant (400) by accessing the digital twin platform provided by the first server (100).

[0043] When the first server (100) performs / applies a specific operation and / or function on the digital twin platform, the terminal device (200) used by the administrator and / or the terminal devices (300-1, 300-2, ..., 300-N) used by multiple workers can display the digital twin platform screen on which the specific operation and / or function is performed / applied. That is, the digital twin platform controlled / managed by the first server (100) can also be linked to the terminal device (200) used by the administrator and / or the terminal devices (300-1, 300-2, ..., 300-N) used by multiple workers.

[0044] In describing the present disclosure, each of the terminal device (200) used by an administrator and the terminal devices (300-1, 300-2, ..., 300-N) used by a plurality of workers may be implemented as a smartphone, PC, laptop, wearable device, server device, etc., but is not limited thereto. Each of the terminal device (200) used by an administrator and the terminal devices (300-1, 300-2, ..., 300-N) used by a plurality of workers may be implemented as various types of electronic devices.

[0045] FIG. 2 is a drawing for explaining the configuration of a first server according to one embodiment of the present disclosure.

[0046] The first server (100) illustrated in FIG. 2 may include a memory (110), a communication module (120), a display (130), an input module (140), and a processor (150).

[0047] However, the configuration illustrated in FIG. 2 is an illustrative diagram for implementing embodiments of the present disclosure, and appropriate hardware and software configurations that are obvious to a person skilled in the art may be additionally included in the first server (100).

[0048] The memory (110) can store one or more instructions for the processor (150) to perform various operations. The memory (110) can store data supporting various functions of the first server (100), a program for the operation of the processor (150), and input / output data.

[0049] The memory (110) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk.

[0050] The communication module (120) may include one or more components including a circuit that enables communication with an external device. For example, the communication module (120) may include at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0051] The display (130) displays (outputs) information processed by the first server (100). For example, the display (130) may display execution screen information of an application running on the first server (100), or UI (User Interface) and GUI (Graphic User Interface) information based on such execution screen information.

[0052] The input module (140) refers to a component for authorizing various input data or / and input interactions (e.g., touch, swipe, etc.) to the first server (100).

[0053] The processor (150) can provide a method for creating and managing digital twin content based on an artificial intelligence algorithm by executing one or more instructions stored in memory (110). That is, the processor (150) can control overall operation and function using each component of the server (100).

[0054] Specifically, the processor (150) may be implemented as a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the first server (100), and at least one processor that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0055] In addition, the processor (150) may control one or more of the components described above in combination to implement various embodiments according to the present disclosure described in FIG. 3 below on the first server (100). That is, the operation of the first server (100) described with reference to FIG. 3 may include operations performed and controlled by the processor (150).

[0056] FIG. 3 is a diagram illustrating a method for controlling an artificial intelligence-based intelligent energy generation integrated operation system according to one embodiment of the present disclosure.

[0057] The first server can create and update a digital twin platform for the operation of the first power plant based on a first database related to a plurality of power generation facilities included in the first power plant, first sensing data obtained through at least one sensor, and a plurality of images obtained from a plurality of camera devices (S310).

[0058] First, the first server can obtain map information of the first power plant (from a terminal device used by the administrator).

[0059] For example, map information may include i) a floor plan (or / and floor plan) for each floor, ii) an indoor map image, iii) an RGB image for each floor, iv) a depth map, v) a LiDAR point cloud, and / or vi) camera internal / external parameters that acquired the RGB image, depth map or / and LiDAR point cloud for each floor, etc.

[0060] The blueprints, indoor maps, depth maps, RGB images, etc. for each floor may include, record, or display the location of each power generation facility / sensor / camera device. The first server may generate a 3D map corresponding to the first power plant through the blueprints (or / and floor plans) or / and indoor maps for each floor.

[0061] For example, the first server can input map information of the first power plant into the second AI model to obtain a 3D map corresponding to the first power plant. Here, the second AI model may be composed of a multi-stage encoder and decoder structure designed to process multi-modal input data. The second AI model may be trained by the first server, but is not limited thereto.

[0062] Specifically, the second AI model comprises: 1) an input interface (e.g., input layer) that takes as input floor plans and interior maps (e.g., vector / raster), multi-view RGB images, depth maps or / and LiDAR point clouds for each floor; 2) a feature extractor that processes the input data received through the input interface (e.g., a CNN-based image encoder and a vector encoder for interior maps); 3) a pose estimation module (e.g., PnP / SLAM-assisted or learning-based PoseNet) that estimates or matches camera poses using camera intra-external parameters and a reference coordinate system provided by the administrator (e.g., floor blueprint reference points); 4) a module that combines depth and features between views through a multi-view fusion module (e.g., cost volume-based MVS or Transformer-based attention fusion); 5) a volumetric fusion / point cloud reconstruction module (TSDF / occupancy network or PointNet-based decoder); and / or 6) surface extraction (e.g., Marching Cubes) and semantic tagging (facility, sensor, camera position). It may include an output head for identification.

[0063] For example, training of the second AI model can be performed as supervised learning using pairs of input data (e.g., floor plans, multi-view images, depth / LiDAR scans, camera parameters) and ground truth 3D references (e.g., actual meshes and point clouds). For example, the training operation of the second AI model may include operations that minimize depth loss (L1 / L2), point cloud similarity (Chamfer distance), occupancy probability cross-entropy, semantic classification loss, and photometric consistency auxiliary loss. Additionally, generalization performance may be improved by utilizing data augmentation that mixes synthetic data and actual scan data and applies lighting, noise, and viewpoint transformations.

[0064] The 3D map acquisition process can be performed in a batch or incremental manner. For example, the second AI model may be trained to perform operations such as (a) preprocessing of input data (e.g., map information of the first power plant, etc.) and coordinate system normalization, (b) camera pose matching, (c) frame-by-frame feature extraction and single / multiple view depth estimation, (d) generation of a dense point cloud through multi-view fusion, (e) output of a consistent occupancy / surface map through TSDF-based volumetric integration, (f) mesh generation and semantic label projection, (g) ICP matching with the plan reference coordinate system and uncertainty filtering, and (h) generation and storage of a 3D map including metadata (e.g., facility location by floor, sensor index, creation time, uncertainty).

[0065] In addition, the first server can acquire the first database from a plurality of power generation facilities periodically or / and in real time. Here, the first database may include at least one of the operating speed, power generation amount, fuel consumption, power generation efficiency, internal pressure, or management history of each of the plurality of power generation facilities.

[0066] Specifically, each of the plurality of power generation facilities can detect at least one of operating speed, power generation amount, fuel consumption, power generation efficiency, internal pressure, or management history through a built-in sensor (e.g., pressure sensor, speed detection sensor, etc.) and / or a processor. Each of the plurality of power generation facilities can transmit at least one of the detected operating speed, power generation amount, fuel consumption, power generation efficiency, power trading unit price, internal pressure, or management history to a first server in real time or / and periodically.

[0067] The first server can map the first database onto a 3D map corresponding to the first power plant. Mapping the first database onto a 3D map may mean setting the first database to be viewable on a screen containing the 3D map. For example, the first server can extract / identify the first database corresponding to the first facility among multiple facilities. The first server can map the first database corresponding to the first power plant to a 3D model corresponding to the first power plant within the 3D map.

[0068] In addition, the first server can acquire sensing data from at least one sensor (e.g., humidity sensor, hazardous gas detection sensor, temperature sensor, pressure sensor) installed within the first power plant. At least one sensor can transmit the acquired sensing data and identification information for each sensor to the first server periodically and / or in real time.

[0069] At this time, the first server may store in advance a sensor identification information database in which location information for at least one sensor is mapped. For example, the first server may identify location information for each sensor corresponding to the identification information for each sensor through the sensor identification information database.

[0070] For example, when a temperature sensing value and identification information of the first temperature sensor are obtained from the first temperature sensor, the first server can identify the location of the first temperature sensor mapped to the identification information of the first temperature sensor through a sensor identification information database. Then, the first server can map the obtained temperature sensing value to an area corresponding to the location of the first temperature sensor in a 3D map.

[0071] Accordingly, when an area corresponding to the location of the first temperature sensor is selected (e.g., by clicking, touching, etc.) within the first screen representing the digital twin platform displayed on the terminal device used by the manager and / or operator, the temperature sensing value sensed through the first temperature sensor may be displayed on the first screen.

[0072] Additionally or alternatively, the first server can acquire images of each power generation facility through a plurality of camera devices. The first server can acquire 3D modeling data corresponding to each power generation facility by applying a 3D conversion algorithm to the images of each power generation facility.

[0073] Here, the 3D conversion algorithm may include a modeling algorithm that converts an object contained within a 2D image into 3D. Specifically, the first server may extract feature information of the first power generation facility (e.g., shape, depth, contour, etc. of the first power generation facility) from an image of the first power generation facility obtained from a specific camera device.

[0074] The first server can extend features extracted from a 2D image of the first facility into coordinates and surfaces in a three-dimensional space. The process of the 3D transformation algorithm described above may include recognizing boundary lines (edges), feature points, and texture information from the 2D image, and then restoring the 3D structure based on this.

[0075] The first server can apply / map the acquired 3D modeling data onto a 3D map. For example, the first server can input / apply 3D modeling data corresponding to the first power generation facility onto an area of ​​the 3D map where the first power generation facility is located. Accordingly, a terminal device used by an operator and / or manager can view a 3D model corresponding to the first power generation facility through the 3D map.

[0076] A digital twin platform can be created by applying / mapping 3D modeling data based on a first database obtained from a plurality of facilities, first sensing data obtained from at least one sensor, and a plurality of images onto a 3D map.

[0077] The first server can update the first database, first sensing data, and / or multiple images acquired in real-time or / and periodically on the digital twin platform. Accordingly, operators and / or managers can monitor, analyze, and / or simulate distributed data and / or facilities within the first power plant from various angles through the digital twin platform.

[0078] The first server can monitor whether a dangerous situation event occurs for each of the multiple power generation facilities based on the first database and the first sensing data (S320).

[0079] Specifically, the first server can obtain a risk index for each of the multiple power generation facilities by inputting a first database and first sensing data related to each of the multiple power generation facilities into a first AI model.

[0080] For example, the first server can configure set data by power generation facilities by classifying the first database and the first sensing data by multiple power generation facilities. The first server can map power generation facility index information to each set data composed of the first database and the first sensing data. The first AI model can be trained to identify the power generation facility associated with the currently input set data through the power generation facility index mapped to the input set data.

[0081] For example, the first AI model can be trained to obtain a risk level through the difference value (i.e., deviation value) between each of the first database of the first power generation facility (e.g., operating speed, power generation amount, fuel consumption, power generation efficiency, and internal pressure, etc.) and the first sensing data (e.g., temperature, pressure, humidity, etc.) and the corresponding reference value.

[0082] Specifically, the set data (X) of the first power generation facility is {x1, x2, x3, ..., x n It is called}. As described above, each component of the set data can be composed of the components of the first database and the first sensing data, respectively. The set of reference values ​​(B) corresponding to each component of the set data is {b1, b2, b3, ..., b n It can be defined as}.

[0083] For example, if x1 is the operating speed of the first power generation facility, b1 may be the specified operating speed of the first power generation facility. And, if x2 is the temperature inside the first power generation facility, b2 may be the specified temperature of the first power generation facility.

[0084] The method for calculating the risk value (S1) of the first power generation facility can be implemented according to Equation 1. In Equation 1, w i can mean the weight (or importance) applied to the i-th item.

[0085]

[0086] The weight applied to the i-th item may be set / determined differently for each power generation facility. For example, priority data of data items for each power generation facility may be transmitted to the first server from a terminal device used by an administrator. For example, if information indicating that the priority of the operating speed among the data items related to the first power generation facility is the highest is received from the terminal device used by the administrator, the first server may determine the weight corresponding to the operating speed of the first power generation facility to be the largest value.

[0087] That is, the first AI model can be trained to calculate risk levels for each power generation facility according to mathematical formula 1.

[0088] The first server can monitor whether a risk situation event occurs for each of the multiple power generation facilities by monitoring whether the risk index of each of the multiple power generation facilities exceeds a first threshold. For example, the fact that the risk index of the first power generation facility exceeds the first threshold may mean that the probability of a safety accident occurring in relation to the first power generation facility has exceeded a reference value.

[0089] For example, based on the risk index of the first power generation facility among multiple power generation facilities exceeding a first threshold, the first server may determine that a first risk situation event related to the first power generation facility has been detected.

[0090] Based on the detection of a first dangerous situation event related to a first power generation facility among multiple power generation facilities, the first server can identify a first worker related to the first dangerous situation event and transmit information related to the first dangerous situation event to a first terminal device used by the identified first worker (S330).

[0091] For example, information related to the first hazardous situation event may include the type of the first hazardous situation event, the type and location of the first power generation facility, the management history of the first power generation facility, and standard manual information for resolving the first hazardous situation event.

[0092] Specifically, when the risk index of the first power generation facility exceeds the first threshold, the first server can obtain a value related to the data item / type used / calculated when obtaining the risk value (S1) of the first power generation facility from the first AI model. The server can identify the type of the first risk situation event through the deviation value by data item / type used when obtaining the risk value (S1) of the first power generation facility.

[0093] For example, if the deviation value between the temperature value of the first power generation facility and the regulated temperature value is greater than the deviation value of the remaining data items / types (i.e., the deviation value related to temperature is the largest among all data items / types), the first server may determine that a temperature-related hazardous situation event has occurred on the first power generation facility.

[0094] In addition, the first server can store a standard manual database for resolving multiple types of hazardous situation events. The first server can identify a standard manual corresponding to the type of the first hazardous situation event of the first power generation facility identified from the standard manual database.

[0095] In addition, the first server can manage power generation facility types and management history, etc., for each of the multiple power generation facilities. Accordingly, the first server can identify the type and management history of the first power generation facility where the first risk situation event occurred.

[0096] The first server can store information about multiple workers managing the first power generation facility in advance. The first server can identify the location of each of the multiple workers through a terminal device or / and a communication tag device (e.g., an RFID tag device, a BLE (Bluetooth Low Energy) tag device, a UWB (Ultra-Wideband) tag device and / or a Wi-Fi tag device) used by each of the multiple workers.

[0097] The first server can identify the first worker among the multiple workers who is currently located closest to the first power generation facility based on the location of each of the multiple workers. The first server can transmit information related to the first hazardous situation event to the first terminal device.

[0098] The first terminal device used by the first operator can display / provide information related to the first dangerous situation event on the first screen representing the digital twin platform (S340).

[0099] Specifically, the first terminal device may display a first screen representing a digital twin platform provided by the first server. The first terminal device may identify a first 3D (dimension) model corresponding to a first power generation facility displayed within the first screen based on information related to a first dangerous situation event. The first terminal device may overlay a second screen (e.g., a UI screen containing information related to the first dangerous situation event) containing information related to the first dangerous situation event on an area of ​​the first screen where the first 3D model is located.

[0100] That is, the first operator can check information about a risk occurrence event currently occurring on the first power generation facility through the second screen via the first terminal device.

[0101] Additionally, the first terminal device used by the first operator can execute a camera application to photograph the first power generation facility. That is, if the first power generation facility is included in the shooting screen of the first terminal device, the first terminal device can overlay standard manual information for resolving the first dangerous situation event on the shooting screen including the first power generation facility.

[0102] Additionally, the first server can identify the movement path of the first worker through at least one of the first terminal device or the communication tag device worn by the first worker. Furthermore, the first server can overlay the movement path of the first worker onto the first screen. Accordingly, the second terminal device used by the administrator can display the first screen of the digital twin platform on which the movement path of the first worker is overlaid by the server.

[0103] Additionally or alternatively, the first server can calculate carbon emissions for each of the multiple power generation facilities based on the fuel consumption of each of the multiple power generation facilities. The first server can overlay information regarding the carbon emissions of the second power generation facility among the multiple power generation facilities onto the area where the second power generation facility (e.g., a 3D model corresponding to the second power generation facility) displayed within the first screen is located.

[0104] Additionally or alternatively, if the total sum of carbon emissions of each of the multiple power generation facilities exceeds a second threshold, the first server can identify at least one power generation facility among the multiple power generation facilities that has the highest carbon emissions relative to the amount of power generated.

[0105] At this time, the first server may transmit a message requesting that the operating time of at least one power generation facility be reduced by a predefined value to a second terminal device used by an administrator.

[0106] Additionally or alternatively, the first server may obtain a first carbon emission and a first power production that are reduced as the operating time of at least one power generation facility is reduced by a first time. The first server may identify a first time for producing the first power production through a specific power generation facility that has the lowest carbon emission relative to the power generation. The first server may transmit a message to a second terminal device used by an administrator proposing to operate the specific power generation facility additionally during the first time.

[0107] Additionally or alternatively, the first server may input images acquired from each of the plurality of cameras into the third AI model to acquire information related to objects existing in the area corresponding to each of the plurality of cameras (e.g., type, state, etc. of the object).

[0108] For example, the third AI model may be trained to extract a region where at least one object is located among a plurality of images, and to extract feature data for at least one object from the extracted region. In this case, the third AI model may include a CNN model, but is not limited thereto. The third AI model may be trained to output the type of object within the input image data and the state information of the object from the extracted feature data. The third AI model may be trained using a supervised learning method based on training data containing a plurality of correct objects and the correct states of the objects.

[0109] For example, if the type of object detected on the first image among multiple images is a specific person, the object state information output by the third AI model may include information indicating whether the specific person is wearing safety equipment, whether the specific person's face image is an image stored in a pre-registered / authorized face image database, or / and whether the specific person's pose corresponds to a pre-registered dangerous pose (e.g., a fallen pose).

[0110] That is, when the first server inputs multiple images into the third AI model, if the type of object detected on the first image among the multiple images is a specific person, the third AI model can be trained to additionally output a state related to the specific person.

[0111] For example, if a specific person is not wearing safety equipment, if the specific person's face image is not an image stored in a pre-registered / authorized face image database, or / and if the specific person's pose corresponds to a pre-registered dangerous pose, the first server may transmit information about the specific person to a second terminal device used by an administrator.

[0112] Additionally or alternatively, if a specific person's face image is not stored in a pre-registered / authorized face image database, the first server may transmit a warning message containing the specific person's face image and / or a location mapped to the first image to a third terminal device used by the security agency. The location mapped to the first image may correspond to the area captured by the camera that captured the first image. Since the first server stores the area captured by each camera in advance, the first server can identify the location mapped to the first image in advance.

[0113] Additionally or alternatively, until information regarding the identity of a specific person is received from a second terminal device used by an administrator and / or a third terminal device used by a security agency, the first server may identify the movement path of a specific person through a plurality of camera devices and upload the identified movement path of the specific person onto a first screen representing a digital twin platform. Furthermore, the first server may identify a second worker located closest to the specific person among a plurality of workers and transmit information regarding the specific person to the terminal device used by the second worker.

[0114] Additionally or alternatively, if the hazardous gas concentration detected by the first hazardous gas detection sensor among at least one sensor exceeds a reference value, the first server can identify a first location equipped with the first hazardous gas detection sensor. The first server can identify a third worker located within a predefined area based on the identified first location among a plurality of workers. The first server can transmit a message indicating that the hazardous gas concentration has been detected to a third terminal device used by the third worker.

[0115] In addition, the first server can identify the first air conditioning equipment closest to the first location among multiple air conditioning equipment within the first power plant and transmit a control signal to the first air conditioning equipment to increase the operating speed to the highest level. The first server can display an indicator on the first screen indicating that the hazardous gas concentration at the first location has exceeded a reference value. Accordingly, the operator and / or manager can confirm that the hazardous gas concentration at the first location has exceeded the reference value through the first screen linked via their respective terminal devices.

[0116] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0117] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0118] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively.

Claims

Claim 1 A plurality of power generation facilities installed within a first power plant; at least one sensor and a plurality of camera devices mounted within the first power plant; a second terminal device used by an administrator; and a first server, wherein the first server: generates and updates a digital twin platform for the operation of the first power plant based on a first database related to the plurality of power generation facilities, first sensing data acquired through the at least one sensor, and a plurality of images acquired from the plurality of camera devices; and monitors whether a dangerous situation event occurs for each of the plurality of power generation facilities based on the first database and the first sensing data; Based on the detection of a first risk situation event related to a first power generation facility among the plurality of power generation facilities, a first worker related to the first risk situation event is identified, and information related to the first risk situation event is transmitted to a first terminal device used by the identified first worker, wherein the information related to the first risk situation event includes: the type of the first risk situation event, the type of the first power generation facility, the management history of the first power generation facility, and standard manual information for resolving the first risk situation event, and the first terminal device identifies a first 3D (dimension) model corresponding to the first power generation facility displayed within a first screen representing the digital twin platform based on the information related to the first risk situation event; and overlay a second screen containing information related to the first dangerous situation event on the area where the first 3D model is located, and the first terminal device: overlays standard manual information for resolving the first dangerous situation event on the shooting screen displayed through a camera application based on the first power generation facility being included on the shooting screen, and the first server: calculates carbon emissions for each of the plurality of power generation facilities based on the fuel consumption of each of the plurality of power generation facilities;If the total sum of carbon emissions of each of the plurality of power generation facilities exceeds a second threshold, at least one power generation facility among the plurality of power generation facilities has the highest carbon emissions relative to power generation; a message requesting that the operating time of the at least one power generation facility be reduced by a predetermined value is transmitted to the second terminal device; a first carbon emissions and a first power production amount that are reduced as the operating time of the at least one power generation facility is reduced by a first time are obtained; and a message suggesting that a specific power generation facility with the lowest carbon emissions relative to power generation be operated during the first time is transmitted to the second terminal device, and the first server: if the concentration of harmful gas detected by a harmful gas detection sensor among the at least one sensor exceeds a reference value, a first location where the harmful gas detection sensor is installed; a third worker among a plurality of workers within the first power plant is located within a predetermined area based on the first location; a message indicating that harmful gas has been detected is transmitted to a third terminal device used by the third worker; and a first air conditioning facility among a plurality of air conditioning facilities within the first power plant is the first air conditioning facility closest to the first location;and transmits a control signal to the first air conditioning equipment to increase the operating speed of the first air conditioning equipment to a final level, and the first server inputs a plurality of images acquired from each of the plurality of cameras into a third AI model to obtain information related to an object existing in an area corresponding to each of the plurality of cameras, and when the type of object detected on the first image among the plurality of images is a specific person, the information related to the object output by the third AI model includes information indicating whether the specific person is wearing safety equipment, whether the face of the specific person is an image stored in a pre-registered face image database, and whether the pose of the specific person corresponds to a pre-registered dangerous pose, and the first server transmits information about the specific person to the second terminal device when the specific person is not wearing safety equipment, when the face image of the specific person is an image not stored in the pre-registered face image database, or when the pose of the specific person corresponds to a pre-registered dangerous pose; and identifies the movement path of the specific person through the plurality of camera devices until information about the identity of the specific person is received from the second terminal device; and overlay the movement path of the identified specific person on the first screen, and the first server: overlays the movement path of the first worker on the first screen through at least one of the first terminal device or the communication tag device worn by the first worker;The system comprises: the second terminal device: displaying the first screen overlaid with the movement path of the first worker; the first database: including the operating speed, power generation amount, fuel consumption, power trading unit price, power generation efficiency, internal pressure, and management history of each of the plurality of power generation facilities; the first server: inputting the first database and the first sensing data into a first artificial intelligence (AI) model according to a predefined period to obtain a risk index for each of the plurality of power generation facilities; and determining that a first risk situation event related to the first power generation facility is detected based on the risk index of the first power generation facility among the plurality of power generation facilities exceeding a first threshold value, wherein the magnitude of the weight applied to each component of the first database for the first AI model to calculate the risk index of the first power generation facility is determined based on a priority set by the manager. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A system according to claim 1, wherein the first server: calculates carbon emissions for each of the plurality of power generation facilities based on the fuel consumption of each of the plurality of power generation facilities; and overlays information regarding carbon emissions of the second power generation facility among the plurality of power generation facilities onto the area where the second power generation facility is located, which is displayed within the first screen.

Images