Methods for providing real-time manufacturing safety services based on intelligent industrial safety technology

Abstract

The present invention relates to a method for providing real-time manufacturing safety services based on intelligent industrial safety technology, which is performed by a computing device. The method for providing real-time manufacturing safety services based on intelligent industrial safety technology may include: collecting environmental data from a composite sensor module provided inside a manufacturing facility; collecting state data from a state sensor module held by a worker working in said manufacturing facility; constructing a virtual environment inside the manufacturing facility corresponding to said environmental data and said state data using said digital twin; training an artificial intelligence-based prediction model using said environmental data and said state data; and predicting risk information inside said manufacturing facility using said artificial intelligence-based prediction model.

Description

Technology Field

[0001] The present invention relates to a method for performing safety monitoring in the manufacturing industry. In particular, the present invention relates to a technology for performing safety monitoring by utilizing a digital twin. Background Technology

[0002] The number of injured workers and fatalities caused by industrial accidents is increasing every year, and the resulting economic losses are also rising. Factors inducing accidents are expected to continue increasing due to changes in industrial structure and the employment environment, such as the rise in vulnerable groups including irregular workers, foreign workers, the elderly, and women, as well as the increase in subcontracting by large corporations to small businesses. In particular, in the manufacturing sector, accidents caused by non-compliance with basic safety regulations account for more than half of all industrial accidents.

[0003] Despite the current enforcement of the Serious Crimes Act, accidents caused by human error are increasing in the manufacturing industry, placing a heavy burden on business owners; therefore, the introduction of a new system to prevent such incidents in advance is necessary.

[0004] The technology forming the background of the present invention is disclosed in Korean Published Patent Application No. 10-2012-0136157. The problem to be solved

[0005] The present invention aims to solve the problems of the aforementioned prior art by providing a real-time manufacturing safety service that utilizes a digital twin to predict hazardous working conditions occurring within a manufacturing facility and analyze the wearing of safety equipment by workers.

[0006] However, the technical problems that the embodiments of the present invention aim to solve are not limited to the technical problems described above, and other technical problems may exist. means of solving the problem

[0007] As a technical means for achieving the above-mentioned technical task, a method for providing a real-time manufacturing safety service based on intelligent industrial safety technology, performed by a computing device according to an embodiment of the present invention, may include: a step of collecting environmental data from a composite sensor module provided inside a manufacturing facility; a step of collecting state data from a state sensor module held by a worker working in said manufacturing facility; a step of constructing a virtual environment inside the manufacturing facility corresponding to said environmental data and said state data using a digital twin; a step of training an artificial intelligence-based prediction model using said environmental data and said state data; and a step of predicting risk information inside said manufacturing facility using said artificial intelligence-based prediction model.

[0008] Additionally, the step of constructing a virtual environment inside a manufacturing facility corresponding to the environment data and the state data using the digital twin may include: a step of acquiring three-dimensional facility assets to map physical facilities inside the manufacturing facility to the digital twin; and a step of creating a three-dimensional avatar corresponding to the worker.

[0009] In addition, the above method may further include a step of monitoring the safety status of a worker in real time based on the environment data.

[0010] In addition, the step of monitoring the safety status of a worker in real time based on the above environmental data may include the step of monitoring at least one of the safety status of the worker wearing protective equipment in real time, the worker status, or the risk status based on the above environmental data.

[0011] In addition, the above method may further include the step of providing work risk notification information to a state sensor module held by the worker based on the risk prediction information.

[0012] The above-described means for solving the problem are merely exemplary and should not be interpreted as intended to limit the invention. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and the detailed description of the invention. Effects of the invention

[0013] According to the means for solving the problem of the present invention described above, by utilizing a digital twin to predict hazardous situations in the working environment occurring inside a manufacturing facility and analyzing the wearing of safety equipment by workers, it is possible to predict the frequency of accidents and the severity of accidents that may occur inside the manufacturing facility and prevent accidents.

[0014] However, the effects obtainable from the present invention are not limited to those described above, and other effects may exist. Brief explanation of the drawing

[0015] FIG. 1 is a block diagram of a computing device for providing real-time manufacturing safety services based on intelligent industrial safety technology according to one embodiment of the present invention. FIG. 2 is a diagram schematically illustrating the operation of building a server for real-time data synchronization based on a digital twin according to an embodiment of the present invention. FIG. 3 is a schematic diagram showing the internal environment and equipment configuration of a digital twin-based manufacturing facility according to one embodiment of the present invention. FIG. 4 is a schematic diagram showing the user interface of a safety monitoring service according to one embodiment of the present invention. FIG. 5 is a schematic diagram showing the user interface of a mobile application for a worker according to one embodiment of the present invention. FIG. 6 is a schematic flowchart of a method for providing real-time manufacturing safety services based on intelligent industrial safety technology according to one embodiment of the present invention. Specific details for implementing the invention

[0016] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0017] Throughout the specification of the present invention, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected," but also cases where they are "electrically connected" or "indirectly connected" with other elements interposed between them.

[0018] Throughout the specification of the present invention, when a member is described as being located "on," "on the upper," "on the top," "under," "on the lower," or "on the bottom" of another member, this includes not only cases where a member is in contact with another member, but also cases where another member exists between the two members.

[0019] Throughout the specification of the present invention, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0020] Throughout the specification of the present invention, some of the operations or functions described as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0021] Throughout the specification of the present invention, the term "at least one" may be defined as a term including both singular and plural forms, and it will be obvious that even if the term "at least one" is not present, each component may exist in a singular or plural form and may mean singular or plural. Furthermore, whether each component is provided in a singular or plural form may be changed according to the embodiment.

[0022] FIG. 1 is a block diagram of a computing device for providing real-time manufacturing safety services based on intelligent industrial safety technology according to one embodiment of the present invention.

[0023] Referring to FIG. 1, the computing device (100) may include a processor (110), a memory unit (120), and a network unit (130). However, the configuration of the computing device (100) is not limited thereto.

[0024] According to one embodiment of the present invention, the processor (110) may include a processor for data analysis and deep learning, such as a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU). The processor (110) may process a plurality of data stored in a memory unit (120) or a plurality of data obtained from a network unit (130).

[0025] According to one embodiment of the present invention, the memory unit (120) may include at least one storage medium among a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a ROM, a RAM, and a flash memory. However, the memory unit (120) is not limited thereto.

[0026] According to one embodiment of the present invention, the network unit (130) may include a 3GPP (3rd Generation Partnership Project) network, an LTE (Long Term Evolution) network, a WIMAX (World Interoperability for Microwave Access) network, the Internet, a LAN (Local Area Network), a Wireless LAN (Wireless Local Area Network), a WAN (Wide Area Network), a PAN (Personal Area Network), a Bluetooth network, a NFC (Near Field Communication) network, a satellite broadcasting network, an analog broadcasting network, a DMB (Digital Multimedia Broadcasting) network, etc., but is not limited thereto and may include various wired / wireless communication networks.

[0027] According to one embodiment of the present invention, a computing device (100) can collect environmental data (10) from a composite sensor module installed inside a manufacturing facility. For example, the composite sensor module may include a vibration sensor, a gas sensor, a concrete curing sensor, a chemical detection sensor, a carbon dioxide (CO2) sensor, a fire and smoke detection sensor, a motion detection sensor, a voice and sound detection sensor, etc. Additionally, the composite sensor module may include a ceiling-mounted composite sensor module such as a vision sensor, a LiDAR (virtual fence), an air environment analysis module, and a thermal imaging module. However, the composite sensor module installed inside the manufacturing facility is not limited to these and may include various sensor modules.

[0028] According to one embodiment of the present invention, a computing device (100) can collect state data (20) from a state sensor module held by a worker working in a manufacturing facility. For example, the state sensor module may include a tilt sensor, a gyroscope sensor, a vibration sensor, an impact sensor, an air environment sensor, a speaker, and a microphone included in a safety helmet. Additionally, the sensor module may include a temperature sensor, a humidity sensor, a carbon dioxide sensor, a motion detection sensor, a GPS and location sensor, an impact and vibration detection sensor, a voice and sound detection sensor, etc., included in a safety vest. Additionally, it may include a motion detection sensor, a GPS and location sensor, an impact and vibration detection sensor, etc., included in safety shoes. However, the sensors included in the safety helmet, safety vest, and safety shoes held (worn) by the worker are not limited to these, and various state sensor modules may be included.

[0029] FIG. 2 is a diagram schematically illustrating the operation of building a server for real-time data synchronization based on a digital twin according to an embodiment of the present invention, and FIG. 3 is a diagram schematically illustrating the internal environment and equipment configuration of a digital twin-based manufacturing facility according to an embodiment of the present invention.

[0030] According to one embodiment of the present invention, a computing device (100) can construct a virtual environment inside a manufacturing facility corresponding to environmental data and state data by utilizing a digital twin. Additionally, the computing device (100) can acquire three-dimensional facility assets to map physical facilities inside the manufacturing facility to the digital twin. First, the computing device (100) can collect environmental data (10) and state data (10) inside the actual manufacturing facility to construct a virtual environment inside the manufacturing facility. The computing device (100) can transmit and store the collected environmental data (10) and state data (20) to a data server to synchronize them in real time. For example, the computing device (100) can construct a data server for real-time data synchronization by utilizing a digital twin. Referring to FIG. 2 as an example, the computing device (100) can store the environmental data (10) and state data (20) in a socket data server. Additionally, the computing device (100) can perform data synchronization of environment data and state data stored in the socket data server to the database server, and can perform data synchronization of environment data and state data acquired in real-time to the Node.js-based socket server. For reference, a Node.js-based socket server refers to a socket communication server built using the Node.js framework. A socket server is a type of server that enables bidirectional communication between a client and a server. This server exchanges data with the client in real-time and is mainly used in fields such as web applications, games, and chat applications. In other words, the computing device (100) can build a Node.js-based server for linking collected data based on the composite sensor module within the digital twin and implement Socket.on() reception and response functions. Additionally, the computing device (100) can implement a C#-based Socket.The emit() data request function module can be implemented. Additionally, environment data and state data are stored in a database (DB) server via a socket server, and the computing device (100) can execute the Socket.emit() data request function targeting a Node.js-based server.

[0031] Additionally, referring to FIG. 3, the computing device (100) can create (build) a virtual environment, which is a digital twin model, based on collected environment data (10) and state data (20) (S100). Additionally, the computing device (100) can perform 3D avatar modeling and rigging operations for worker representation (S200). Additionally, the computing device (100) can place 3D assets and 3D avatars on the built virtual environment (S300). For example, the virtual environment is a virtual replica of an actual manufacturing facility and can reflect environment data and state data in real time. The virtual environment can reflect the structure, equipment, processes, assets, and environment of the manufacturing facility. Additionally, the computing device (100) can update the virtual environment whenever the actual environment data and state data change. As a result, the virtual environment can be kept up to date by reflecting changes inside the actual manufacturing facility. Additionally, the computing device (100) can create a 3D avatar corresponding to the worker. For example, the computing device (100) can generate different three-dimensional avatars corresponding to the worker ID. The worker ID may include information such as an assembly worker, a machine operator, a quality inspector, an inventory manager, a packaging and logistics worker, an equipment and maintenance worker, etc. The computing device (100) can generate an assembly worker as a first avatar, a machine operator as a second avatar, and a third avatar as a quality inspector avatar, etc. Additionally, the computing device (100) can utilize a digital twin to move the three-dimensional avatar in a virtual space based on state data collected from a specific worker. By constructing a virtual environment and placing the three-dimensional avatar in the virtual space, the computing device (100) can more quickly identify dangerous situations and provide accurate notification information to workers located in dangerous areas.For example, the computing device (100) can perform structural design for configuring the internal environment of a digital twin-based manufacturing facility. Additionally, the computing device (100) can configure the list of internal environments and equipment objects for the manufacturing facility. Additionally, the computing device (100) can collect and build 3D facility assets for configuring the digital twin-based manufacturing facility. Additionally, the computing device (100) can perform 3D avatar modeling and rigging work for worker representation. For reference, 3D avatar rigging is a process of applying bones, controls, and animations to a 3D character model to make the model move and interact. Additionally, the computing device (100) can implement and apply 3D avatar and facility animations to provide visual effects. Additionally, the computing device (100) can implement particle, sound, and effect effects to enhance visibility. Additionally, the computing device (100) can implement a digital twin initialization script based on manufacturing facility data and implement a modular script for providing data-based digital twin rendering.

[0032] According to one embodiment of the present invention, a computing device (100) can train an artificial intelligence-based prediction model by utilizing the environment data and the state data. Additionally, the computing device (100) can predict risk information within a manufacturing facility by utilizing the artificial intelligence-based prediction model. Meanwhile, the computing device (100) can provide work risk notification information to a state sensor module held by the worker based on the risk prediction information. For example, the state sensor module held by the worker may include a sensor module equipped in a safety vest, safety helmet, safety shoes, etc. Additionally, the computing device (100) may provide work risk notification information to a user terminal held by the worker based on the risk prediction information. For example, the computing device (100) may detect abnormal signs or abnormal movements based on a prediction model that has learned patterns between normal working states and abnormal states by utilizing machine learning and deep learning models. For example, the computing device (100) can predict the worker's behavior pattern corresponding to the worker's ID. For example, if the ID of the first worker is an assembly worker, the movement behavior pattern of the worker moving only from the entrance to the assembly work area can be predicted. Additionally, if the ID of the first worker is an assembly worker, a work behavior pattern for performing assembly work (e.g., the action of assembling various parts) can be predicted. The computing device (100) can provide risk alert information if the first worker performs an action other than the predicted behavior pattern based on environmental data and state data. For example, if the first worker performs an action other than the predicted behavior pattern, it may include an action of leaving the assembly work area, which is the first workplace, or an action of performing a behavior pattern other than the work behavior pattern for performing assembly work (e.g., the action of operating a machine).

[0033] Additionally, the computing device (100) can predict risk information inside the manufacturing facility by utilizing location information of a 3D avatar in a virtual space. The location information of the 3D avatar can be adjusted based on state data. In other words, the 3D avatar in the virtual space corresponds to the location information of a worker located inside the actual manufacturing facility. The computing device (100) can provide work risk notification information when a 3D avatar is located within a preset area with a preset number or more. Additionally, the computing device (100) can provide work risk notification information when a 3D avatar is located within a preset area with a preset number or more based on an asset.

[0034] According to one embodiment of the present invention, a computing device (100) can set a risk index for each asset by considering a plurality of assets provided inside a manufacturing facility and generate a probability map based thereon. The risk index inside the manufacturing facility can be set based on an area where facility assets, including machinery, equipment, pumps, valves, sensors, process lines, etc., are provided. For example, in the case of a refrigerator rail process in the manufacturing facility, a first risk index can be set in the area where the large press is located, considering that risk factors such as crane collision, coil jamming, and forklift collision may occur at the large press. Additionally, a second risk index can be set in the area where the small press is located, considering that risk factors such as jamming accidents and forklift collisions may occur at the small press. Additionally, a third risk index can be set in the area where the small press is located, considering that risk factors such as material and coil jamming accidents and forklift collisions may occur in the assembly process. The computing device (100) can generate a composite risk probability map by fusing probability maps generated based on risk indices set based on multiple facility assets. The computing device (100) can build a more detailed risk level by fusing probability maps generated based on areas equipped with multiple facility assets to generate a composite risk probability map. For example, if a large presso and a small presso are located in close proximity, the probability of a forklift collision is relatively high, so feedback such as adding surveillance equipment to the area can be provided. Additionally, the computing device (100) can map the composite risk probability map to a virtual environment built using a digital twin and provide risk alert information by taking into account the movement of the worker.For example, the computing device (100) may determine a risk area by mapping a composite risk probability map to a virtual environment, and may provide risk notification information when a worker is located in the risk area by considering the worker's location information included in the state data.

[0035] FIG. 4 is a schematic diagram showing the user interface of a safety monitoring service according to one embodiment of the present invention.

[0036] According to one embodiment of the present invention, a computing device (100) can monitor the safety status of a worker in real time based on environmental data and status data. For example, the computing device (100) can monitor at least one of the safety status of the worker wearing protective equipment, the worker status, or the risk status in real time based on environmental data. For example, the computing device (100) can monitor at least one of the safety status of the worker wearing protective equipment, the worker status, or the risk status in real time based on environmental data from at least one of a vision sensor, a LiDAR (virtual fence), an air environment analysis module, and a thermal imaging module using a ceiling-type composite sensor module. For example, the computing device (100) can monitor the worker's movements and work environment by utilizing a camera and computer vision technology. The computing device (100) can detect the worker's posture, movements, whether safety equipment is being worn, and risk factors by utilizing a deep learning-based model. In addition, the computing device (100) can detect dangerous situations by analyzing status data collected from wearable devices and sensors (e.g., safety helmet, safety vest, safety shoes, etc.) worn by the worker. For example, worker movements and the working environment can be monitored by monitoring impact, fall, humidity, gas concentration, and vibration sensor data.

[0037] According to one embodiment, the computing device (100) may monitor environmental noise and dangerous situations for workers by analyzing voice data acquired through a microphone included in a safety helmet. Additionally, the computing device (100) may acquire real-time text data based on voice data acquired in real time by utilizing a Real-Time STT (RT-STT) model. Based on the real-time text data, the computing device (100) may determine whether keywords and words related to dangerous situations are included. For example, keywords and words related to dangerous situations may include "fire," "explosion," "accident," "help me," "danger," etc. The computing device (100) may determine whether words related to dangerous situations are included in the text data by using natural language processing (NLP) technology on the real-time text data. Furthermore, the computing device (100) may monitor environmental noise and dangerous situations for workers by further considering information related to emotions or tones included in the voice data. For example, even if voice data such as "Be careful, it is dangerous" is collected in a neutral voice simply to prevent it, the computing device (100) can determine that the situation is a dangerous situation because the real-time text data contains keywords related to a dangerous situation corresponding to "danger." Taking this into consideration, the computing device (100) can analyze information related to the sentiment or tone of the voice data corresponding to the real-time text data and determine whether the situation is a dangerous situation.In other words, when voice data corresponding to an urgent voice saying "Be careful, it is dangerous!!" is acquired, the computing device (100) may utilize an RT-STT (Real Time STT) model to acquire real-time text data based on the voice data acquired in real time and perform a first analysis, and if keywords related to the dangerous situation are included, may secondarily analyze information related to the emotion or tone of the voice data to monitor the dangerous situation of the worker. However, the above description is merely one embodiment and is not limited thereto.

[0038] Referring to FIG. 4, the computing device (100) can provide monitoring information such as the status of workers wearing protective equipment, the status of workers, and the status of threats based on composite sensor module data in real time. Additionally, the computing device (100) can provide status analysis information based on worker risk ranking, threat criticality information based on statistics by date, and feedback information based on risk priority statistics by task. Additionally, the computing device (100) can provide criticality information based on risk information such as the status of workers wearing protective equipment and the status of workers. Furthermore, the computing device (100) can manage and provide information on the history of work threats and notifications occurring as work progresses in the manufacturing facility. Additionally, the computing device (100) can provide feedback on work risk assessment based on the work status and design information for a digital twin-based manufacturing facility safety inspection service.

[0039] FIG. 5 is a schematic diagram showing the user interface of a mobile application for a worker according to one embodiment of the present invention.

[0040] Referring to FIG. 5 for an example, the computing device (100) can output information regarding the worker's attire status through the user interface of the worker's mobile application, categorized into safety helmets, gloves, safety vests, safety shoes, and other equipment (for example, developed to allow setting attire standards for different attire statuses for each process). Additionally, the computing device (100) can provide information such as a manager call, Bluetooth connection status, navigation to each function (notices, notification history, emergency stop), worker information, and today's work information on the main screen of the user interface of the worker's mobile application. Furthermore, the computing device (100) can provide a safety inspection checklist, feedback on preventing dangerous situations, self-risk assessment, and work manual through the top-left menu button of the user interface of the worker's mobile application. Additionally, the computing device (100) can provide work precautions (personal) to the worker regarding precautions for today's work based on dangerous situations that occurred in previous work. Furthermore, the computing device (100) can identify and output the frequency of dangerous situations occurring for the worker today regarding the worker's status through the user interface of the worker's mobile application. Additionally, the computing device (100) analyzes the wearing of manufacturing safety equipment in relation to the worker's attire and outputs results for each worker. If the attire is not recognized or if the attire is not suitable for work, a voice notification message can be output to the worker. Furthermore, the computing device (100) provides announcements to facilitate smooth communication between the manager and the worker through the worker's mobile application. The types of announcements are classified into general, important, and urgent, and important and urgent posts can be implemented so that only the manager can write them. Additionally, the computing device (100) can visualize and display posts that have not yet been viewed individually for each worker and output them aligned at the top along with important and urgent posts.In addition, the computing device (100) provides a post search function to facilitate finding posts, and can create, save, and print worker safety inspection checklists, self-risk assessments, and work manuals.

[0041] According to one embodiment of the present invention, the computing device (100) may be a device that can be implemented, for example, in the form of a program or application (app) installed on a user terminal. Alternatively, the method of providing real-time manufacturing safety services based on intelligent industrial safety technology provided through the computing device (100) may be implemented in the form of a program or application and provided to the user through the user terminal. However, it is not limited thereto, and as another example, the computing device (100) may be provided in the form of a server capable of transmitting and receiving data with the user terminal. The computing device (100) provided in the form of a server may control the operation (for example, screen display) of the user terminal connected to the program or app provided by the computing device (100). The computing device (100) may provide the monitoring service described in FIG. 4 and the mobile application described in FIG. 5 to the user terminal.

[0042] For example, a user terminal may refer to a terminal possessed by a user who uses a computing device (100). The user may be referred to as a user, an administrator, etc., and may be an administrator who manages the operation of the manufacturing environment. The user may use the service with or without installing the program or app by using the user terminal, and may also use the service by accessing the program or app to sign up or without signing up. User terminals may include, but are not limited to, all types of wired and wireless communication devices such as, for example, PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (WCode Division Multiple Access), Wibro (Wireless Broadband Internet) terminals, smartphones, smartpads, tablet PCs, laptops, wearable devices, desktop PCs, etc.

[0043] Below, we will briefly examine the operation flow of the present invention based on the details described above.

[0044] FIG. 6 is a schematic flowchart of a method for providing real-time manufacturing safety services based on intelligent industrial safety technology according to one embodiment of the present invention.

[0045] A method for providing real-time manufacturing safety services based on intelligent industrial safety technology illustrated in FIG. 6 can be performed by the computing device (100) described above. Therefore, even if details are omitted below, the description of the computing device (100) can be equally applied to the description of a method for providing real-time manufacturing safety services based on intelligent industrial safety technology.

[0046] Step S10 is a step of collecting environmental data from a composite sensor module installed inside a manufacturing facility.

[0047] Step S20 is a step of collecting status data from a status sensor module held by a worker working at the manufacturing facility.

[0048] Step S30 is a step of constructing a virtual environment inside a manufacturing facility corresponding to the environment data and the state data using a digital twin.

[0049] Step S40 is a step of analyzing data collected in the constructed virtual environment to train an artificial intelligence-based prediction model.

[0050] Step S50 is a step of predicting internal risk information of the manufacturing facility using the artificial intelligence-based prediction model.

[0051] The above method may include a step of monitoring the safety status of a worker in real time based on the environment data.

[0052] Additionally, the above method may include the step of providing work risk notification information to a state sensor module held by the worker based on the risk prediction information.

[0053] In the description above, steps S10 and S50 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Additionally, some steps may be omitted as necessary, and the order between steps may be changed.

[0054] A method for providing real-time manufacturing safety services based on intelligent industrial safety technology according to one embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

[0055] In addition, the method of providing real-time manufacturing safety services based on the aforementioned intelligent industrial safety technology can also be implemented in the form of a computer program or application executed by a computer stored on a recording medium.

[0056] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0057] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

Claims

Claim 1 A method for providing real-time manufacturing safety services based on intelligent industrial safety technology performed by a computing device, comprising: a step in which the computing device collects environmental data from a composite sensor module installed inside a manufacturing facility; a step in which the computing device collects state data from a state sensor module held by a worker working in said manufacturing facility; a step in which the computing device constructs a virtual environment inside the manufacturing facility corresponding to said environmental data and said state data using a digital twin; and a step in which the computing device trains an artificial intelligence-based prediction model using said environmental data and said state data. The computing device includes the step of predicting risk information within a manufacturing facility by utilizing the artificial intelligence-based prediction model; wherein, when constructing the virtual environment, the computing device acquires 3D facility assets to map physical facilities within the manufacturing facility to the digital twin, generates a 3D avatar corresponding to the worker, places the generated 3D avatar on the virtual environment, sets a risk index for each facility asset by considering a plurality of facility assets provided within the manufacturing facility, sets the risk index based on an area equipped with facility assets including machinery, equipment, pumps, valves, sensors, and process lines, generates a probability map based on the set risk index, and, when the manufacturing facility includes a refrigerator rail process, sets a first risk index in the area where the large press is located by considering that risk factors including crane collision, coil jamming, and forklift collision may occur at the large press, and risk factors including jamming accidents and forklift collision may occur at the small press Considering the situation, a second risk index is set in the area where the above-mentioned small press is located, and material and coil pinching accidents in the assembly process,Considering that a situation may arise where risk factors, including forklift collisions, may occur, a third risk index is established in the area where the assembly process is located; subsequently, to construct a subdivided risk level, a composite risk probability map is generated by fusing a probability map created based on risk indices established based on multiple facility assets; based on the composite risk probability map, feedback is provided to add monitoring equipment to the area where a large press and a small press are located in close proximity within a certain distance, as the probability of a forklift collision occurring is relatively higher when they are not located in close proximity; a risk area is determined by mapping the composite risk probability map to a virtual environment constructed using a digital twin; risk alert information is provided considering the movement of the worker, provided when the worker is located in the risk area considering the worker's location information included in the status data; the worker's safety status in real time is monitored based on the environment data and status data, and regarding the safety status, at least one of the worker's protective equipment wearing status, worker status, and risk status is monitored; and the worker's movements and work environment are monitored using cameras and computer vision technology. Utilizing a deep learning-based model to detect the worker's posture, movement, safety equipment usage, and risk factors; analyzing state data collected from wearable devices and sensors corresponding to the safety helmet, safety vest, and safety shoes worn by the worker, such as impact, fall, humidity, gas concentration, and vibration sensor data, to monitor the worker's movements and work environment and detect hazardous situations; analyzing voice data acquired from the microphone included in the safety helmet to monitor environmental noise and hazardous situations for the worker; and utilizing an RT-STT (Real Time STT) model to acquire real-time text data based on voice data acquired in real time,A method comprising: using natural language processing technology on acquired real-time text data to determine, through a primary analysis, whether keywords and words related to hazardous situations, including fire, explosion, accident, "please help," and danger, are included within the acquired real-time text data; further analyzing and considering information related to the sentiment or tone of voice data corresponding to the real-time text data to monitor environmental noise and hazardous situations for workers and to determine whether a hazardous situation exists; wherein, when keywords and words related to hazardous situations are included within the real-time text data during the primary analysis, the hazardous situation for workers is monitored by a secondary analysis of information related to the sentiment or tone of voice data corresponding to the real-time text data; subsequently, providing monitoring information including the worker's protective equipment wearing status, worker status, and hazardous situation in real-time; additionally, providing status analysis information by worker risk ranking, criticality information based on risk information based on daily statistics, and feedback information based on risk priority statistics by task; providing work risk and notification occurrence history information according to the progress of manufacturing facility work; providing work risk assessment feedback based on work status; and providing design information for a digital twin-based manufacturing facility safety inspection service. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A method according to claim 1, further comprising the step of providing work risk notification information to a state sensor module held by the worker based on the risk prediction information.

Images