KR20230103081A - Safety management system for shipyard and ship based on artificial intelligence - Google Patents

Abstract

According to the present invention, an artificial intelligence-based safety management system for shipyards and ships includes: a plurality of video capture devices installed within shipyards and ships to capture the interior of the shipyards and ships in real time; and a plurality of sensor devices installed within the shipyards and ships to measure sensor information within shipyards and ships in real time, wherein the safety management system can determine whether workers working in the shipyards and ships are wearing safety equipment and workers' health status based on image information captured by the video capture device, and can determine the remaining lifespan and failure time of mechanical equipment in the shipyard and ship using image information and sensor information measured by the sensor devices.

Description

AI-based safety management system for shipyards and ships {SAFETY MANAGEMENT SYSTEM FOR SHIPYARD AND SHIP BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to an artificial intelligence-based safety management system for shipyards and ships, and more specifically, based on image information captured by an image capturing device installed in a shipyard and ship and sensor information detected or measured by a sensor device. and artificial intelligence-based safety management systems for shipyards and ships that can manage worker safety management and machinery facilities in ships based on artificial intelligence.

Shipyards have many dangerous tasks. In particular, there are many high-altitude work and confined work, and especially work that handles inflammable or explosive materials is more dangerous.

When a crane is hoisting a heavy object, the crane itself may not be able to withstand the load and may collapse, and care should be taken as the heavy object being hoisted may fall unintentionally. In addition, a fall accident may occur in high-altitude work, and an accident such as gas poisoning or suffocation due to hypoxia is highly likely to occur in confined work, so care must be taken.

Recently, the government or international organizations are demanding strict standards for workers' lives and health, and workplaces where industrial accidents occur can suffer from various disadvantages.

Marine energy development companies are also reluctant to place orders for marine equipment or ships in shipyards that have experienced major disasters, so perfect safety management has a great impact on shipbuilders winning orders.

Therefore, safety management is the most important task in order to receive orders for ships and offshore plants, proceed with construction, and deliver them on time while operating a shipyard.

In addition, the coast is an area where most maritime accidents occur, and there is a risk of fatal maritime accidents of ships. Accordingly, when a problem occurs in a ship, help cannot be easily obtained at sea or in the coast, so the risk of leading to a disaster in terms of public safety is very high.

And, above all, since the management philosophy that human life and health have irreplaceable absolute value should form the basis of corporate management, the perception that workers or workers' safety is the best corporate value is widely spread throughout the company. There should be.

Therefore, there is an increasing demand for a safety management system that can perfectly keep workers' safety and inform workers of risk factors in real time.

The present invention has been made to solve the above problems, and based on the image information taken by the image photographing device installed in the shipyard and ship, the artificial musculoskeletal system and safety equipment of the worker can be determined. Its purpose is to provide an intelligence-based safety management system.

An object of the present invention is to provide an artificial intelligence-based safety management system for shipyards and ships that can predict failures of mechanical facilities in the workplace and remaining life based on sensor information detected by sensor devices installed in shipyards and ships.

The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the following description.

An artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention is a video recording device installed in a shipyard and a ship to photograph the inside of a shipyard and a ship in real time, and a plurality of devices installed in a shipyard and a ship in real time And based on the image information captured by the sensor device and the image capture device for measuring sensor information in the ship, determine whether workers working in the shipyard and the ship are wearing safety equipment and the worker's health condition, and determine the image information and the sensor It is possible to determine the remaining life and failure time of mechanical equipment in the shipyard and ship based on sensor information measured by the device.

Other embodiment specifics are included in the detailed description and drawings.

The present invention analyzes the musculoskeletal system of a worker in a workplace based on image information, determines whether or not the worker is wearing safety equipment, and notifies the worker, thereby managing the worker more safely and protecting the manager from accidents that may occur.

The present invention predicts the remaining life and failure time of mechanical equipment in a workplace based on sensor information and manages them, thereby improving manager's convenience and preventing accidents due to machine deterioration.

Effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the present invention.

1 is a diagram schematically showing the configuration of an artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention.
Figure 2 is a diagram schematically showing the detailed configuration of the safety management server of Figure 1.
FIG. 3 is a diagram for explaining the control flow of the safety management server of FIG. 1 .
4 is a diagram for explaining the AI-based safety management flow of shipyards and ships according to an embodiment of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the embodiments taken in conjunction with the accompanying drawings. However, it is understood that the present invention is not limited to the examples presented below, but may be implemented in various different forms, and includes all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. It should be. The embodiments presented below are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the invention to which the present invention belongs. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Various embodiments of the present invention may be implemented as software (eg, a program) including instructions stored in a storage medium readable by a machine (eg, a computer). A device is a device capable of calling a stored command from a storage medium and operating according to the called command, and may include an electronic device (eg, a server) according to the disclosed embodiments. An instruction may include code generated or executed by a compiler or interpreter. The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' only means that the storage medium does not contain a signal and is tangible, but does not distinguish whether data is stored semi-permanently or temporarily in the storage medium.

According to one embodiment, the method according to various embodiments disclosed in the present invention may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product may be distributed in the form of a device-readable storage medium (eg compact disc read only memory (CD-ROM)) or online through an application store (eg Play Store™). In the case of online distribution, at least part of the computer program product may be temporarily stored or temporarily created in a storage medium such as a manufacturer's server, an application store server, or a relay server's memory.

Each component (eg, module or program) according to various embodiments may be composed of a single object or a plurality of objects, and some sub-components among the aforementioned sub-components may be omitted, or other sub-components may be used. It may be further included in various embodiments. Alternatively or additionally, some components (eg, modules or programs) may be integrated into one entity and perform the same or similar functions performed by each corresponding component prior to integration. According to various embodiments, operations performed by modules, programs, or other components are executed sequentially, in parallel, iteratively, or heuristically, or at least some operations are executed in a different order, are omitted, or other operations are added. It can be.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. “Comprises” and/or “comprising” as used in the specification does not exclude the presence or addition of one or more other elements other than the recited elements.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically showing the configuration of an artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention.

Referring to FIG. 1, the artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention includes a safety management server 100, an image capturing device 200, a sensor device 300, and a manager device 400. ) can be made.

The safety management server 100, the video recording device 200, the sensor device 300, and the manager device 400 constituting the artificial intelligence-based safety management system of an intelligent real-time shipyard and ship according to an embodiment of the present invention connect a communication network. can be communicated with each other. Here, the communication network may include a wireless communication network and a wired communication network. In addition, the communication network may be a local area network (eg, Bluetooth, WiFi direct, or infrared data association (IrDA)) or a long-distance communication network (eg, a cellular network, the Internet, or a computer communication network (eg, LAN or WAN)).

The safety management server 100 may provide a safety management monitoring platform capable of managing the inside of a shipyard and/or ship. Here, the safety management monitoring platform may mean a means for using services that can be provided by the safety management server 100, such as a web page provided through a communication network and a smartphone application.

The safety management server 100 receives image information and sensor information from the video recording device 200 and the sensor device 300 through the safety management monitoring platform and analyzes them to provide health information and safety equipment for workers in the shipyard and/or ship. It is possible to determine whether or not it is worn, and to determine whether or not mechanical equipment installed in a shipyard and/or ship is out of order and the degree of deterioration, that is, the remaining life span. At this time, the worker's health information and whether or not to wear safety equipment, whether or not the mechanical equipment is broken, and the remaining life span can be analyzed and identified by pre-stored artificial intelligence algorithms. In this way, information identified by the safety management server 100 may be transmitted to the manager device 400 . In this way, the safety management server 100 informs the worker's health information and whether or not to wear safety equipment through the image capture device 200 and the sensor device 300 to manage the worker in a smart way, and whether or not the mechanical equipment is broken. Accidents that may occur due to deterioration of mechanical equipment can be prevented by identifying and notifying whether or not there is a remaining lifespan.

The image photographing device 200 is a device capable of photographing the inside of a shipyard and/or a ship by installing a plurality of them inside a shipyard and/or inside a ship. The image capture device 200 may be, for example, at least one of a Closed Circuit Television (CCTV), a camera, or a Digital Video Recorder (DVR). A plurality of these image capture devices 200 may be installed inside a shipyard and/or inside a ship. In this way, images taken in real time by the image capturing device 200 may be transmitted to the real time safety management server 100 .

A plurality of sensor devices 300 may be installed inside a shipyard and/or inside a ship to detect failure and degree of deterioration of mechanical facilities inside the shipyard and/or ship. The sensor device 300 may include a plurality of sensors, and the plurality of sensors may be, for example, a vibration sensor, an ultrasonic sensor, or a heat sensor. In this way, sensor information sensed in real time by the sensor device 300 may be transmitted to the safety management server 100 in real time.

The manager device 400 may be a device used by a manager who manages a shipyard and/or a ship. The manager device 400 may use a safety management monitoring platform or may be an installed device. The manager device 400 may provide the safety management server 100 with necessary information related to the shipyard and/or the inside of the ship, and from the safety management server 100, worker information such as the worker's health status and whether safety equipment is worn, and machine Equipment information can be received. Such a manager device 400 may be, for example, a smartphone, a tablet personal computer (PC), a mobile phone, a video phone, an e-book reader, a desktop PC ( desktop PC), laptop PC, netbook computer, workstation, server, personal digital assistant (PDA), portable multimedia player (PMP), MP3 player, mobile medical device, It may include at least one of a camera or a wearable device.

Looking in detail at the configuration of the safety management server 100 among the configurations of the artificial intelligence safety management system for shipyards and ships according to an embodiment of the present invention is shown in FIG. 2 below.

Figure 2 is a diagram schematically showing the detailed configuration of the safety management server of Figure 1.

Referring to FIG. 2, the safety management server 100 of the artificial intelligence safety management system for shipyards and ships according to an embodiment of the present invention includes a communication module 110, a database module 120, and a worker safety analysis module 130. , a machine remaining life prediction module 140, a notification message generating module 150, and a control module 160.

The communication module 110 may transmit/receive data with the image capture device 100 , the sensor device 200 , and the manager device 400 . The communication module 110 may receive image information captured in real time from the image capturing device 100 and sensor information detected in real time from the sensor device 200, and may receive operator information and machine information based on the image information and sensor information. Facility information may be analyzed and grasped, and the identified result may be transmitted to the manager device 400 .

The database module 120 may store information of workers working in the shipyard and ship and information on mechanical facilities installed in the shipyard and ship as a database. More specifically, the database module 120 provides worker information such as worker name, age, career, department, worker's work characteristics, and safety equipment information worn by workers, and mechanical equipment information such as mechanical equipment installation date and mechanical equipment failure history. can be saved. In addition, the database module 120 may store an artificial intelligence algorithm for determining the worker's safety state and health level by the worker safety analysis module 130 and the health of the machine equipment by the machine remaining life prediction module 140. These artificial intelligence algorithms are algorithms that have learned in advance information such as stored worker information, mechanical facility information, history of accidents that have occurred frequently in shipyards and ships, characteristics of workers when their health is poor, and state of mechanical facilities before mechanical facility failure. can

The worker safety analysis module 130 may process and analyze the image based on the image information captured by the image capture device 200 to analyze safety and health information of the worker. More specifically, the worker safety analysis module 130 compares and analyzes the worker's face, body characteristics, and wearing state with the worker information by an artificial intelligence algorithm stored in the database module 120 based on the image information to determine who the worker is. can be specified. Subsequently, the worker safety analysis module 130 compares and analyzes the worker's wearing state with the safety information previously stored by the artificial intelligence algorithm stored in the database module 120 based on the image information to determine whether the worker is wearing safety equipment. there is. In addition, the worker safety analysis module 130 analyzes the worker's work characteristics based on the image information, and analyzes the worker's musculoskeletal system using the analyzed current worker work characteristics and the artificial intelligence algorithm stored in the database module 120 to analyze the health of the worker. information can be grasped. At this time, the worker safety analysis module 240 may analyze the worker's musculoskeletal system from the image information based on the visual artificial intelligence algorithm to analyze the worker's health information and determine whether safety equipment is worn. Here, the visual artificial intelligence algorithm may include a first algorithm for extracting the characteristics and patterns of the worker's working posture, and a second algorithm for predicting energy consumption according to the work posture load analysis and work load based on RULA (Rapid Upper Limb Assessment). there is. Here, RULA is a technique for easily and quickly evaluating workload due to working posture by focusing on the shoulder, wrist, wrist, and neck. In other words, the worker safety analysis module 130 may identify the worker and determine whether or not the worker is wearing safety equipment using the first algorithm, and analyze the worker's musculoskeletal system to determine the worker's health level using the second algorithm. It can be figured out by algorithm.

The remaining machine life prediction module 140 analyzes the image information captured by the image capture device 200 and the sensor information detected by the sensor device 300 to determine the soundness of the machinery and equipment installed in the shipyard and ship, for example. For example, failure diagnosis and life prediction can be performed. More specifically, the remaining machine life prediction module 140 is based on the results measured through the vibration sensor, heat detection sensor, ultrasonic sensor, etc. of the sensor device 300 by an artificial intelligence-based algorithm for failure of mechanical equipment in the industrial site. Diagnosis and life expectancy can be predicted. In addition, the machine remaining life prediction module 140 may also provide a decision-making algorithm for making a decision for machine facility maintenance. In this case, the artificial intelligence-based algorithm for predicting the remaining life of the machine may be a deep learning model-based prognostics and health management (PHM) algorithm. Accordingly, the remaining machine life prediction module 140 may diagnose the life of mechanical facilities installed in a shipyard and a ship, and may determine a time point of failure in advance.

The notification message generation module 150 generates a notification message based on the results identified by the worker safety analysis module 130 and the machine remaining life prediction module 140 and transmits the notification message to the manager device 400 so that the manager can understand it. do. In addition, the notification message generation module 150 may generate a decision message when a decision algorithm is executed after the machine life prediction module 140 completes the machine life prediction and fixing time point. The decision-making message thus generated may be transmitted to the manager device 400 .

The control module 160 may generate a control signal capable of controlling the overall operation of the safety management server 100 . More specifically, the control module 160 controls the worker safety analysis module 130 to determine the health status and safety equipment wearing status of workers in the shipyard and ship when image information is received from the image capture device 200 . can create In addition, the control module 160 is a machine remaining life prediction module to determine the remaining life and failure time of mechanical facilities installed in shipyards and ships when image information from the image capturing device 200 and sensor information from the sensor device 300 are received. A control signal to control 140 may be generated. In addition, the control module 160 informs the operator safety analysis module 130 and the remaining machine life prediction module 140 to generate a notification message when the status or degree of the operator and machine equipment is completed. A control signal for controlling the message generation module 150 may be generated. In addition, the control module 160 may generate a control signal for controlling the communication module 110 so that the notification message generated by the notification message generating module 150 can be transmitted to the manager device 400 .

In this way, the artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention can determine the health status of workers, the wearing status of safety equipment, as well as the remaining life of mechanical equipment and predict the time of failure in advance, making it a smart shipyard. and the management of personnel and machinery on board.

Hereinafter, a control method of a safety management server of an artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention will be described.

FIG. 3 is a diagram for explaining the control flow of the safety management server of FIG. 1 .

Referring to FIG. 3 , according to the control method of the safety management server 100 according to an embodiment of the present invention, the control module 160 of the safety management server 100 includes worker information and machine information stored in the database module 120. Information is learned in advance (S310).

Subsequently, the control module 160 of the safety management server 100 determines whether image information has been received from the image capturing device 200 and whether sensor information has been received from the sensor device 300 (S320).

As a result of the determination, when the control module 160 of the safety management server 100 determines that the image information and the sensor information are received, first, after analyzing the image information received by the worker safety analysis module 130 (S330) , Based on the video analysis result, it is determined whether or not the workers in the shipyard and ship are wearing safety equipment (S340). At this time, whether or not the worker wears the safety equipment can be determined by the first algorithm of the visual artificial intelligence algorithm.

As a result of the determination, when the control module 160 of the safety management server 100 determines that the worker is wearing safety equipment, the worker safety analysis module 130 analyzes the worker's health condition through the transmitted image information (S350). . In this case, the health status of the worker may be analyzed by analyzing the worker's musculoskeletal system to determine the worker's health level, and more specifically, the second algorithm of the visual artificial intelligence algorithm.

On the other hand, the control module 160 of the safety management server 100 generates a notification message for not wearing safety equipment through the notification message generating module 150 when it is determined that the worker is not wearing safety equipment, and the communication module ( 110) to transmit the message generated by the notification message generation module 150 (S360). In the description of the present embodiment, a notification message is generated when the safety equipment is not worn, but is not limited thereto, and the notification message can be controlled to be generated even when the safety equipment is properly worn.

Subsequently, the control module 160 of the safety management server 100 analyzes the worker's musculoskeletal system to determine the health state, controls the notification message for the worker's health state to be generated by the notification message generation module 150, and communicates A worker health status notification message is transmitted to the manager device 400 through the module 110 (S370).

Subsequently, the control module 160 of the safety management server 100 controls the remaining machine life prediction module 140 to analyze image information and sensor information (S380). More specifically, the control module 160 of the safety management server 100 uses an artificial intelligence algorithm, that is, a PHM technique based on deep learning, to determine the state of equipment installed in the shipyard and ship, for example, It is possible to analyze the remaining life and failure time (S390). In addition, the control module 160 of the safety management server 100 controls the notification message generation module 150 to generate a machine facility status notification message, and transmits the machine facility to the manager device 110 through the communication module 110. Causes status notification messages to be sent. At this time, the decision message is also controlled to be generated by the notification message generation module 150 by the decision-making algorithm for maintenance of the machine facility according to the state of the machine facility, and then the decision message is sent by the communication module 110 to the manager device. to be transmitted to (100).

Hereinafter, a safety management method of an AI-based safety management system for shipyards and ships according to an embodiment of the present invention will be described.

4 is a diagram for explaining an artificial intelligence-based safety management method for shipyards and ships according to an embodiment of the present invention.

Referring to FIG. 4, according to the artificial intelligence-based safety management method for shipyards and ships according to an embodiment of the present invention, the artificial intelligence-based safety management system for shipyards and ships is controlled by the safety management server 100 in shipyards and ships. Worker information about workers and machine information about machines installed in shipyards and ships are learned in advance (S401).

Subsequently, when the safety management monitoring platform installed in the manager device 400 is executed, the image capture device 200 takes an image of the shipyard and the inside of the ship (S402), and transmits the captured image to the safety management server 100 (S402). S403).

Then, the safety management server 100 analyzes the image information (S404), and drives a visual artificial intelligence algorithm to determine whether the worker is wearing safety equipment and the worker's health condition (S405).

Subsequently, the safety management server 100 generates a notification message about whether or not the safety equipment is worn (S406), and generates a notification message about the worker's health condition (S407), and transmits the generated notification message to the manager device 400. send. Subsequently, the manager device 400 checks the transmitted notification message (S409).

On the other hand, the sensor device 300, the image capture device 200 measures or detects the state of machinery in the shipyard and ship (S410), and transmits the measured sensor information to the safety management server 100 (S411).

Next, the safety management server 100 analyzes the image information captured by the image capturing device 200 and the sensor information detected or measured by the sensor device 300 (S412), and drives an artificial intelligence algorithm (S413). ) Estimating the remaining life and failure time of mechanical equipment installed in the shipyard and ship, and generating a notification message for this (S414).

Subsequently, the safety management server 100 transmits a notification message about the remaining life and failure time of the machine to the manager device 400 (S415), and the manager device 400 checks the transmitted notification message (S416) .

Subsequently, the safety management server 100 drives a decision-making algorithm for machine facility maintenance (S417), generates a decision-making message (S418), and transmits the generated decision-making message to the manager device 400 (S419). .

Then, after checking the decision message, the manager device 400 determines a decision on machine facility maintenance (S420), and transmits the decision message back to the safety management server 100 (S421) to maintain the machine facility. make up for it to be made.

The artificial intelligence-based safety management system for shipyards and ships according to various embodiments of the present invention can be described as follows.

An artificial intelligence-based safety management system for shipyards and ships according to an embodiment of the present invention is a video recording device installed in a plurality of shipyards and ships to photograph the inside of shipyards and ships in real time. , Whether or not workers working in shipyards and ships are wearing safety equipment based on image information captured by sensor devices and image capture devices that measure sensor information in shipyards and ships in real time and are installed in shipyards and ships. It is possible to determine the state of health of the shipyard, and to determine the remaining life and failure time of the shipyard and in-ship machinery based on image information and sensor information measured by the sensor device.

According to another feature of the present invention, the safety management server analyzes the communication module for receiving image information and sensor information, a database module for storing worker information and machine information installed in shipyards and ships, and image information for workers working in shipyards and ships. Based on the visual AI algorithm, a worker safety analysis module that identifies whether the worker is wearing safety equipment and the health status of the worker, analyzes image information and sensor information, and based on the artificial intelligence algorithm, determines the remaining life of the machine and the point of failure. It may include a control module that generates a control signal for controlling the operation of a prediction module for predicting the remaining life of the machine and a safety management server.

According to another feature of the present invention, the visual artificial intelligence algorithm extracts the characteristics and patterns of the worker's working posture from the image information to determine whether the worker is wearing safety equipment, and RULA (Rapid Upper Limb Assessment) from the image information It may include a second algorithm for determining the health state of the worker by predicting energy consumption according to the work posture load analysis based on the work posture and the work load.

According to another feature of the present invention, the artificial intelligence algorithm is a deep learning model-based PHM (Prognostics and Health Management) algorithm and maintenance of mechanical equipment for predicting the remaining life and failure point of mechanical equipment by analyzing image information and sensor information It may include decision-making algorithms for remuneration.

According to another feature of the present invention, the safety management server determines whether or not the worker is wearing safety equipment identified by the worker safety analysis module and the health status of the worker, and the remaining life of the machine predicted by the remaining machine life prediction module and the time of failure. It may further include a notification message generation module for generating a notification message and a decision message for maintenance of mechanical equipment.

Although the embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be variously modified without departing from the technical spirit of the present invention. . Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

100: safety management server
110: communication module
120: database module
130: worker safety analysis module
140: Machine remaining life prediction module
150: notification message generation module
160: control module
200: video recording device
300: sensor device
400: manager device

Claims (5)

A plurality of image capturing devices installed in a shipyard and a ship to photograph the inside of the shipyard and a ship in real time;
a plurality of sensor devices installed in the shipyard and ship to measure sensor information in the shipyard and ship in real time; and
Based on the image information captured by the image capture device, it is determined whether workers working in the shipyard and ship are wearing safety equipment and the health condition of the worker, and the image information and the sensor information measured by the sensor device An artificial intelligence-based safety management system for shipyards and ships that identifies the remaining life and failure time of mechanical equipment in the shipyard and ship by The method of claim 1, wherein the safety management server,
a communication module receiving the image information and the sensor information;
A database module for storing information on workers working in the shipyard and ship and information on machines installed in the shipyard and ship;
a worker safety analysis module that analyzes the image information and determines whether the worker wears safety equipment and the worker's health condition based on a visual artificial intelligence algorithm;
a machine remaining life prediction module that analyzes the image information and the sensor information and predicts the remaining life and failure time of the machine based on an artificial intelligence algorithm; and
An artificial intelligence-based safety management system for shipyards and ships, characterized in that it comprises a; control module for generating a control signal for controlling the operation of the safety management server. The method of claim 2, wherein the visual artificial intelligence algorithm,
a first algorithm for determining whether the worker wears safety equipment by extracting characteristics and patterns of the worker's working posture from the image information; and
A second algorithm for determining the health condition of the worker by predicting the energy consumption according to the work posture load analysis based on RULA (Rapid Upper Limb Assessment) and the work load from the image information Shipyard and ship, characterized in that it includes AI-based safety management system. The method of claim 2, wherein the artificial intelligence algorithm,
a deep learning model-based prognostics and health management (PHM) algorithm for predicting the remaining life and failure time of the mechanical equipment by analyzing the image information and the sensor information; and
An artificial intelligence-based safety management system for shipyards and ships, characterized in that it includes a decision-making algorithm for maintenance of the mechanical equipment. The method of claim 2, wherein the safety management server,
A notification message about whether the worker safety equipment is worn and the health condition of the worker identified by the worker safety analysis module, the remaining life of the machine predicted by the remaining life of the machine and the time of failure, and the maintenance of the machine equipment An artificial intelligence-based safety management system for shipyards and ships, characterized in that it further comprises; notification message generation module for generating a decision-making message for.

Images