Control and predictive maintenance system for upper deck house fans

Abstract

Control and predictive maintenance technology for an upper deck house fan is provided. A method according to one embodiment of the present disclosure may be performed by an electronic device. The method may include the steps of: acquiring a detection signal from a sensor module of a house fan attached to the upper deck of a ship during the shipbuilding process; identifying the attachment location of the house fan based on a GPS signal included in the detection signal; analyzing the operating state of the house fan based on a current signal included in the detection signal; and providing a control interface for the house fan based on the attachment location and the operating state.

Description

Technology Field

[0001] The present disclosure relates to control and predictive maintenance technology for upper deck house fans. Background Technology

[0002] Despite being a large-scale industry, shipyards still rely heavily on human labor for resource management. This reveals limitations in terms of operational efficiency and safety, and there is a need for efforts to automate and optimize resource management by incorporating advanced technologies, particularly IoT. Such technological advancements can play a crucial role in increasing productivity and improving the working environment in shipyards.

[0003] In the shipbuilding process, house fans are used as important equipment to improve the working environment by circulating air inside the ship. House fans maintain the quality of the internal air and help workers work in a more comfortable environment. However, most house fans are currently operated manually, which requires continuous intervention from the operator. This manual operation method not only reduces work efficiency but also acts as a factor that increases the burden on the workers.

[0004] In particular, manually operating house fans can pose a significant risk to workers when weather conditions deteriorate. For instance, in adverse weather conditions such as strong winds or heavy rain, the likelihood of safety accidents increases as workers must directly operate the equipment. This issue undermines the safety of the working environment and negatively impacts the overall operational efficiency of the shipyard. The problem to be solved

[0005] The object of the present disclosure is to provide a control and predictive maintenance system for an upper deck house fan that can effectively manage and maintain the fan operation status of a ship. means of solving the problem

[0006] In one embodiment of the present disclosure, a method performed by an electronic device may be provided. The method may include the steps of: acquiring a detection signal from a sensor module of a house fan attached to the upper deck of a ship during the shipbuilding process; identifying the attachment location of the house fan based on a GPS signal included in the detection signal; analyzing the operating state of the house fan based on a current signal included in the detection signal; and providing a control interface for the house fan based on the attachment location and the operating state. The control interface may be an interface implemented as a digital map that visually displays the attachment location and the operating state.

[0007] In one embodiment of the present disclosure, the method may be a module in which the upper deck of the vessel is attached with a first house fan and a second house fan distinct from the first house fan, wherein the first house fan includes a first sensor module and the second house fan includes a second sensor module, and the first sensor module and the second sensor module each transmit the detection signal through a wireless communication module based on a unique identifier. The step of identifying the attachment location may include the step of distinguishing the first house fan and the second house fan based on the unique identifier and identifying the attachment location based on each GPS signal. The step of providing the control interface may include the step of providing a control interface capable of individual operation control for the first house fan and the second house fan.

[0008] In one embodiment of the present disclosure, the step of analyzing the operating state may include the step of analyzing the operating state based on pattern analysis of the current signal based on an artificial intelligence model. The artificial intelligence model may be a model learned based on a combination of first type learning data having an abnormal state pattern and second type learning data having a normal state pattern. The step of analyzing the operating state based on the analysis of the artificial intelligence model may include the step of generating frequency domain data by performing a Fast Fourier Transform on the current signal, the step of extracting a feature vector including the magnitude and distribution of frequency components from the frequency domain data, and the step of determining the operating state by inputting the feature vector into the artificial intelligence model.

[0009] In one embodiment of the present disclosure, the sensor module may further include a vibration sensor for detecting vibration of the house fan. The detection signal may further include a vibration signal detected by the vibration sensor. The step of analyzing the operating state may include the step of analyzing the operating state based on a combination of the current signal and the vibration signal.

[0010] In one embodiment of the present disclosure, the control interface may display an icon representing the house fan in a first color on the digital map when the operating state is normal, and may display it in a second color distinct from the first color when the operating state is abnormal. In response to a user selection of the icon corresponding to the house fan displayed on the digital map, a detailed information window including identification information of the house fan, a real-time current value, and an accumulated operating time may be displayed. The control interface may be configured to receive power control inputs for the house fan through the detailed information window.

[0011] In one embodiment of the present disclosure, the artificial intelligence model may be a model trained to classify the abnormal state into any one of a plurality of defect types, including bearing defects, motor winding defects, and blade imbalances, based on the pattern of the current signal. The method may further include the step of generating an alarm message when the abnormal state is determined by the artificial intelligence model. The alarm message may include a unique identifier of the house fan, an attachment location on the digital map, the type of defect, and a pre-set action according to the type of defect.

[0012] In one embodiment of the present disclosure, the step of analyzing the operating state may include: performing a Fast Fourier Transform on the current signal to generate first frequency domain data and extracting a first feature vector from the first frequency domain data; performing a Wavelet Transform on the vibration signal to generate second frequency domain data and extracting a second feature vector from the second frequency domain data; combining the first feature vector and the second feature vector to generate a fused feature vector; and inputting the fused feature vector into an artificial intelligence model to analyze the operating state.

[0013] In one embodiment of the present disclosure, the digital map may be a 3D map implemented based on three-dimensional design data of the vessel. The method may further include the steps of transmitting a work instruction for a specific house fan to a worker's terminal, and, in response to the worker's terminal's confirmation of the work instruction, highlighting an icon corresponding to the specific house fan on the 3D map and superimposing and displaying navigation information on the 3D map that guides the shortest path from the worker's current location to the attachment location of the specific house fan.

[0014] In one embodiment of the present disclosure, the method may further include the steps of: matching the detection signal, the attachment location, and the operating state with a unique identifier and timestamp of the house fan and storing them in a time-series database; and analyzing the performance degradation trend of the house fan and predicting the remaining effective life based on the cumulative operating time of the house fan and the history of changes in the operating state stored in the time-series database. The control interface may visually display the performance degradation trend and the remaining effective life.

[0015] An apparatus according to one embodiment of the present disclosure may be combined with hardware and controlled by a computer program stored on a medium to execute the method of any one of the methods described above. Effects of the invention

[0016] According to one embodiment of the present disclosure, detection signals are acquired from a sensor module of a house fan attached to the upper deck during the shipbuilding process, and the attachment location and operating status of the house fan are analyzed based on these signals, thereby enabling safe monitoring and control of the house fan even when weather conditions deteriorate. According to one embodiment of the present disclosure, by providing a control interface in the form of a digital map that visually displays the attachment location and operating status, the status of the house fan can be intuitively understood and managed efficiently. Furthermore, according to one embodiment of the present disclosure, work efficiency during the shipbuilding process can be improved by accurately identifying the location and operating status of the house fan using GPS signals and current signals. Brief explanation of the drawing

[0017] FIG. 1 illustrates an environment in which a monitoring device according to one embodiment of the present disclosure can be applied. FIG. 2 illustrates an electronic device capable of implementing a monitoring device according to one embodiment of the present disclosure. FIG. 3 illustrates a flowchart showing a method according to one embodiment of the present disclosure. FIG. 4 illustrates a flowchart showing the detailed operation of the identification operation of the attachment location described with reference to FIG. 3. FIG. 5 illustrates a flowchart showing the detailed operation of the provision operation of the control interface described with reference to FIG. 3. FIG. 6 illustrates a flowchart showing the detailed operation of the analysis operation of the operation state described with reference to FIG. 3. FIG. 7 illustrates a flowchart showing the detailed operation of the analysis operation of the operation state described with reference to FIG. 6. FIG. 8 illustrates a flowchart showing the detailed operation of the analysis operation of the operation state described with reference to FIG. 3. FIG. 9 illustrates a flowchart showing the detailed operation of the analysis operation of the operation state described with reference to FIG. 8. FIG. 10 illustrates a flowchart illustrating a method according to one embodiment of the present disclosure. FIG. 11 illustrates a flowchart showing a method according to one embodiment of the present disclosure. FIG. 12 illustrates a flowchart showing a method according to one embodiment of the present disclosure. FIG. 13 illustrates a digital map that may be referenced in various embodiments of the present disclosure. Specific details for implementing the invention

[0018] The various embodiments described in this disclosure are illustrative for the purpose of clearly explaining the technical concept of this disclosure and are not intended to limit it to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments selectively combined from all or part of each embodiment described in this disclosure. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0019] Terms used in this disclosure, including technical or scientific terms, may have the meaning generally understood by a person skilled in the art to which this disclosure pertains, unless otherwise defined. Since such terms may be referred to by various other terms depending on technological development, changes, conventions, and the preferences of skilled persons, the scope of the technical concept of this disclosure is not limited by the meaning of the terms used below.

[0020] Expressions used in this disclosure, such as “comprising,” “may compose,” “possessing,” “possessing,” “having,” and “possessing,” mean that the subject feature (e.g., function, operation, or component, etc.) exists and do not exclude the existence of other additional features. That is, such expressions should be interpreted as open-ended terms implying the possibility of including other embodiments.

[0021] Singular expressions used in this disclosure may include the meaning of the plural form unless otherwise indicated by the context, and this applies likewise to singular expressions described in the claims.

[0022] Ordinal expressions used in this disclosure, such as "first," "second," or "first," "second," etc., are used to distinguish one object from another when referring to a plurality of objects of the same kind, unless otherwise indicated in the context, and do not limit the order or importance of the objects.

[0023] Expressions used in the present disclosure, such as “A, B and C”, “A, B or C”, “at least one of A, B and C”, and “at least one of A, B or C”, may mean each of the listed items or all possible combinations of the listed items. For example, “at least one of A or B” may refer to (i) at least one A, (ii) at least one B, and (iii) at least one A and at least one B.

[0024] The expression “based on” as used in this disclosure is used to describe one or more factors affecting an act or action of a decision or judgment described in the phrase or sentence containing this expression, and this expression does not exclude additional factors affecting said act or action of a decision or judgment.

[0025] As used in the present disclosure, the expression that a certain component (e.g., a first component) is "connected" or "connected" to another component (e.g., a second component) may mean that the certain component is not only directly connected or connected to the other component, but is also connected or connected through a new other component (e.g., a third component).

[0026] As used in this disclosure, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of." This expression is not limited to the meaning of "specifically designed in hardware." For example, a processor configured to perform a specific operation may mean a generic-purpose processor capable of performing that specific operation by executing software, or a special-purpose computer structured through programming to perform that specific operation.

[0027] The expressions “part,” “module,” “model,” etc. used in this disclosure refer to software or hardware components such as FPGAs (Field-Programmable Gate Arrays) and ASICs (Application Specific Integrated Circuits). Here, “part,” “module,” “model,” etc. may be configured to reside in an addressable storage medium and may be configured to operate one or more processors. Accordingly, “part,” “module,” “model,” etc. may include components such as software components, object-oriented software components, class components, and task components, as well as processors, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. Additionally, the functions provided through “part,” “module,” “model,” etc. may be combined into smaller units of “part,” “module,” or “model.”

[0028] As used in this disclosure, the term "Artificial Intelligence (AI)" may refer to a technology that mimics human learning ability, reasoning ability, perceptual ability, etc., and implements them on a computer. Such artificial intelligence may include concepts such as machine learning or symbolic logic.

[0029] As used in this disclosure, the term "Machine Learning (ML)" may refer to a process of training an artificial intelligence model using experience in processing data. As a specific example, machine learning may be a technology that enables an artificial intelligence model to self-classify or learn the features of input data. An artificial intelligence model can analyze input data as a machine learning algorithm, learn based on the results of the analysis, and make judgments or predictions regarding new inputs based on the results of the learning. Unlike the examples provided, any technology that learns to mimic the cognitive and judgmental functions of the human brain (e.g., linguistic understanding, visual understanding, reasoning, prediction, knowledge representation, motion control, etc.) may be understood as falling under the category of machine learning. Examples of machine learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Such machine learning may be performed on the device itself where the artificial intelligence model is executed, or through a separate server or system.

[0030] As used in this disclosure, the term "artificial intelligence model" may refer to a model constructed by extracting and analyzing features from given data and modeling the correlations between the data. The process of constructing the correlations of an artificial intelligence model may be referred to as machine learning. An artificial intelligence model may be composed of one or more neural network layers. Each neural network layer has one or more weights and performs neural network operations through operations between the result of a previous layer's operation and one or more weights. The one or more weights possessed by a neural network layer may be optimized based on the learning results of the artificial intelligence model. As a specific example, one or more weights may be updated during the learning process so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized. Artificial intelligence models may include, for example, CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), or Deep Q-Networks, but are not limited thereto.

[0031] Embodiments of the present disclosure will be described below with reference to the attached drawings. In the attached drawings, identical or corresponding components are given the same reference numerals. Furthermore, in the description of the embodiments below, the description of identical or corresponding components may be omitted. However, even if a description of a component is omitted, it is not intended that such component is not included in any embodiment.

[0032] FIG. 1 illustrates an environment (100) to which a monitoring device (110) according to one embodiment of the present disclosure can be applied.

[0033] Referring to FIG. 1, the environment (100) may include a monitoring device (110), a house fan (120), and a worker terminal (130). The environment (100) may represent an overall environment in which a system for the control and predictive maintenance of the upper deck house fan (120) is implemented during the ship construction process. The monitoring device (110), the house fan (120), and the worker terminal (130) may communicate with each other via a network.

[0034] The monitoring device (110) may be a central control system that monitors and controls the status of the house fan (120). The monitoring device (110) may be implemented as a server computer or a computing system composed of multiple computers. The monitoring device (110) may transmit and receive data to and from the house fan (120) and the worker terminal (130) via a network.

[0035] The monitoring device (110) can acquire a detection signal from a sensor module attached to the house fan (120). The monitoring device (110) can determine the attachment location and operating status of the house fan (120) by analyzing the acquired detection signal. Additionally, the monitoring device (110) can provide a control interface to a worker terminal (130) based on the analysis results.

[0036] The monitoring device (110) can analyze the pattern of the detection signal using an artificial intelligence model. Through this, the monitoring device (110) can diagnose the abnormal condition of the house fan (120) and classify the type of defect. The monitoring device (110) can store the collected data in a time-series database and perform a predictive maintenance function that predicts the remaining effective lifespan of the house fan (120) based on the stored historical data. For example, the monitoring device (110) may be an on-premise server, a cloud-based virtual server, an edge computing device, a distributed server system, a mainframe computer, a workstation, or a personal computer. However, the present disclosure is not limited thereto.

[0037] A house fan (120) may be equipment that circulates air inside a ship during the shipbuilding process. The house fan (120) may be installed at a specific location on the ship, such as the upper deck, to improve the working environment. The house fan (120) may have a structure including a motor, blades, and a housing.

[0038] The house fan (120) may include a sensor module. The sensor module may generate a detection signal by measuring physical quantities related to the operation of the house fan (120). For example, the sensor module may generate a detection signal including a Global Positioning System (GPS) signal, a current signal, and a vibration signal and transmit it to a monitoring device (110).

[0039] In one embodiment of the present disclosure, a plurality of house fans (120) may be installed on the upper deck of a ship. Each house fan (120) may have a unique identifier. A monitoring device (110) may individually identify and manage the plurality of house fans (120) based on the unique identifiers.

[0040] The worker terminal (130) may be an electronic device that provides a user interface for a worker to interact with the monitoring device (110). The worker terminal (130) may include a display and an input device to display visual information and receive user input. The worker terminal (130) may connect to the monitoring device (110) via a network.

[0041] The worker terminal (130) can display a control interface provided by the monitoring device (110). The control interface may be in the form of a digital map that visually displays the attachment location and operating status of the house fan (120). The worker can check the digital map through the worker terminal (130) and perform management tasks such as remotely controlling the power of a specific house fan (120).

[0042] The worker terminal (130) can receive an alarm message from the monitoring device (110) and notify the worker. Additionally, the worker terminal (130) can receive work instructions for a specific house fan (120). In response to the work instructions, the worker terminal (130) can display navigation information on a 3D map that guides the location of the house fan (120) and the shortest path from the current location. For example, the worker terminal (130) may be a smartphone, a tablet computer, a notebook computer, a Personal Digital Assistant (PDA), an industrial terminal, a wearable device, or a smart watch. However, the present disclosure is not limited thereto.

[0043] FIG. 2 illustrates an electronic device (200) capable of implementing a monitoring device (110) according to one embodiment of the present disclosure.

[0044] Referring to FIG. 2, the electronic device (200) may include a processor (210), memory (220), and a communication interface (230). The electronic device (200) may be a hardware configuration that implements the monitoring device (110) described with reference to FIG. 1. The electronic device (200) may perform the function of monitoring and controlling the status of a house fan (120) attached to the upper deck during the shipbuilding process.

[0045] The electronic device (200) can receive a detection signal from a sensor module attached to the house fan (120). The electronic device (200) can analyze the received detection signal to determine the attachment location and operating status of the house fan (120). Additionally, the electronic device (200) can perform the role of providing a control interface to a worker terminal (130) based on the analysis results. For example, the electronic device (200) may be an on-premise server, a cloud server, a desktop computer, a laptop computer, a workstation, an embedded system, or an industrial PC. However, the present disclosure is not limited thereto.

[0046] The processor (210) can control the overall operation of the electronic device (200). The processor (210) can perform various operations according to one embodiment of the present disclosure by executing instructions stored in memory (220). The processor (210) may be implemented as a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or an Application-Specific Integrated Circuit (ASIC), etc.

[0047] The processor (210) can process the detection signal received through the communication interface (230). Specifically, the processor (210) can identify the attachment location of the house fan (120) based on the GPS signal included in the detection signal. Additionally, the processor (210) can analyze the operating status of the house fan (120) based on the current signal included in the detection signal. Based on the analyzed attachment location and operating status, the processor (210) can generate a control interface in the form of a digital map and control the communication interface (230) to transmit the generated control interface to the worker terminal (130).

[0048] In one embodiment of the present disclosure, the processor (210) can analyze the operating state of the house fan (120) by executing an artificial intelligence model. The processor (210) can generate frequency domain data by performing a Fast Fourier Transform (FFT) on a current signal. The processor (210) can extract a feature vector from the generated frequency domain data and input the extracted feature vector into an artificial intelligence model stored in memory (220) to determine whether the operating state is normal or abnormal.

[0049] Memory (220) can store data or programs necessary for the operation of the processor (210). Memory (220) can store an operating system (OS), an application program for performing embodiments of the present disclosure, and various data. For example, memory (220) may be Random Access Memory (RAM), Read-Only Memory (ROM), flash memory, a Hard Disk Drive (HDD), or a Solid State Drive (SSD). However, the present disclosure is not limited thereto.

[0050] The memory (220) can store a pre-trained artificial intelligence model for analyzing the operating status of the house fan (120). The memory (220) can also store detection signals received through the communication interface (230), attachment location information analyzed by the processor (210), and operating status information. This information can be matched with the unique identifier and timestamp of the house fan (120) and stored in the memory (220) in the form of a time-series database.

[0051] The communication interface (230) can serve to enable the electronic device (200) to transmit and receive data with an external device. The communication interface (230) can be connected to a network via a wired or wireless communication method. The communication interface (230) can communicate with the sensor module of the house fan (120) and the worker terminal (130).

[0052] The communication interface (230) can wirelessly receive each detection signal from a plurality of house fans (120). The communication interface (230) can also transmit operation status information and a control interface of the house fans (120) to a worker terminal (130) under the control of the processor (210). For example, the communication interface (230) may support communication technologies such as Wi-Fi, Bluetooth, Zigbee, LoRa, 5G (5th Generation mobile communication), LTE (Long-Term Evolution), or Ethernet. However, the present disclosure is not limited thereto.

[0053] FIG. 3 illustrates a flowchart showing a method (S300) according to one embodiment of the present disclosure.

[0054] Referring to FIG. 3, the method (S300) can be performed by a monitoring device (110).

[0055] In step S310, the monitoring device (110) can obtain a detection signal from the sensor module of the house fan (120). The monitoring device (110) can receive a signal from the house fan (120) attached to the upper deck of the ship during the shipbuilding process. The sensor module can detect and generate data related to the operation of the house fan (120). The detection signal can be transmitted to the monitoring device (110) via a wireless communication module. For example, the detection signal may be a Global Positioning System (GPS) signal, an electric current signal, a vibration signal, a temperature signal, a humidity signal, a noise signal, and a pressure signal. However, the present disclosure is not limited thereto.

[0056] In step S320, the monitoring device (110) can identify the attachment location of the house fan (120) based on the GPS signal included in the detection signal. The monitoring device (110) can analyze the GPS coordinates received from the sensor module. The monitoring device (110) can determine the physical location of the house fan (120) on the digital map of the vessel through the analyzed coordinates. The monitoring device (110) can individually identify multiple house fans (120) by matching the unique identifier of each house fan (120) with the GPS signal. The monitoring device (110) can track the location of the identified house fan (120).

[0057] In step S330, the monitoring device (110) can analyze the operating status of the house fan (120) based on the current signal included in the detection signal. The monitoring device (110) can analyze the pattern, magnitude, frequency, etc. of the current signal. The monitoring device (110) can determine whether the house fan (120) is operating normally or if an abnormal state has occurred based on the analysis results. For example, the monitoring device (110) can detect minute changes in the current signal using an artificial intelligence model. The monitoring device (110) can determine an abnormal state based on the detected changes.

[0058] In step S340, the monitoring device (110) can provide a control interface for the house fan (120) based on the attachment location and operating status. The monitoring device (110) can combine the attachment location information identified in step S320 and the operating status information analyzed in step S330. The monitoring device (110) can generate an interface that visually represents the combined information. The monitoring device (110) can transmit the generated interface to a worker terminal (130).

[0059] In one embodiment of the present disclosure, the control interface may be an interface implemented as a digital map that visually displays the attachment location and operating status. The digital map may be generated based on the drawing data of the vessel. The digital map may display the location of each house fan (120) in the form of an icon.

[0060] In one embodiment of the present disclosure, the control interface may display an icon representing the house fan (120) in a first color on a digital map when the operating state is normal. The control interface may display an icon representing the house fan (120) in a second color that is distinct from the first color when the operating state is abnormal. An operator may select an icon corresponding to the house fan (120) displayed on the digital map. In response to the operator's selection, the control interface may display a detailed information window including identification information of the house fan (120), a real-time current value, and an accumulated operating time. The control interface may receive power control input for the house fan (120) through the detailed information window.

[0061] FIG. 4 illustrates a flowchart showing the detailed operation (S400) of the identification operation (S320) of the attachment location described with reference to FIG. 3.

[0062] Referring to FIGS. 1 to 4, the detailed operation (S400) of the identification operation (S320) of the attachment location can be performed by the monitoring device (110).

[0063] In step S410, the monitoring device (110) can distinguish house fans based on a unique identifier. The monitoring device (110) can identify the attachment location based on each GPS signal. The monitoring device (110) can receive detection signals from multiple house fans (120). A sensor module attached to each house fan (120) may have a unique identifier. The monitoring device (110) can identify a specific house fan (120) through the unique identifier included in the detection signal. The monitoring device (110) can analyze the GPS signal of the identified house fan (120). Through analysis, the monitoring device (110) can determine the exact location on the upper deck of the ship.

[0064] In one embodiment of the present disclosure, a first house fan and a second house fan distinct from the first house fan may be attached to the upper deck of a vessel. The first house fan may include a first sensor module. The second house fan may include a second sensor module. The first sensor module and the second sensor module may each be a module that transmits a detection signal through a wireless communication module based on a unique identifier. The step of identifying the attachment location may distinguish the first house fan and the second house fan based on a unique identifier.

[0065] FIG. 5 illustrates a flowchart showing the detailed operation (S500) of the provision operation (S340) of the control interface described with reference to FIG. 3.

[0066] Referring to FIG. 5, the monitoring device (110) can perform a detailed operation (S500) of the provision operation (S340) of the control interface.

[0067] In step S510, the monitoring device (110) may provide a control interface capable of individual operation control for the house fans. The monitoring device (110) may generate a user interface capable of transmitting independent control commands to each of the plurality of house fans (120). The user may select a specific house fan (120) through the provided control interface. The user may control operations such as turning the power on or off of the selected house fan (120).

[0068] In one embodiment of the present disclosure, a first house fan and a second house fan distinct from the first house fan may be attached to the upper deck of a vessel. The first house fan may include a first sensor module. The second house fan may include a second sensor module. The first sensor module and the second sensor module may each be a module that transmits a detection signal through a wireless communication module based on a unique identifier. The monitoring device (110) may provide a control interface capable of individual operation control for the first house fan and the second house fan.

[0069] FIG. 6 illustrates a flowchart showing a detailed operation (S600) of the analysis operation (S330) of the operation state described with reference to FIG. 3.

[0070] Referring to FIG. 6, the detailed operation (S600) of the analysis operation (S330) of the operation state described with reference to FIG. 3 can be performed by a monitoring device (110).

[0071] In step S610, the monitoring device (110) can analyze the operating state based on pattern analysis of the current signal based on an artificial intelligence model. The monitoring device (110) can analyze time-series data of the current signal received from the house fan (120). The artificial intelligence model can learn complex patterns contained in the current signal to accurately diagnose the state of the house fan (120).

[0072] In one embodiment of the present disclosure, step S610 may include the step of utilizing various types of artificial intelligence models. For example, the artificial intelligence models may be Support Vector Machines (SVM), Random Forests, Gradient Boosting Machines, Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Transformer models. However, the present disclosure is not limited thereto. The monitoring device (110) may select and use an artificial intelligence model that exhibits optimal performance according to the characteristics of the extracted feature vectors.

[0073] FIG. 7 illustrates a flowchart showing a detailed operation (S700) of the analysis operation (S610) of the operation state described with reference to FIG. 6.

[0074] Referring to FIG. 7, the detailed operation (S700) of the analysis operation (S610) of the operation state can be performed by the monitoring device (110).

[0075] In step S710, the monitoring device (110) can generate frequency domain data by performing a Fast Fourier Transform on the current signal. The monitoring device (110) can convert the current signal collected in the time domain into frequency domain data. The process of converting the current signal into frequency domain data can enable the identification and analysis of specific frequency components present in the signal. The monitoring device (110) can efficiently generate frequency domain data using a Fast Fourier Transform (FFT) algorithm. The generated frequency domain data may represent a unique frequency pattern associated with the normal operation or specific fault state of the house fan (120).

[0076] In step S720, the monitoring device (110) can extract a feature vector containing the magnitude and distribution of frequency components from the frequency domain data. The monitoring device (110) can extract statistical features from the frequency spectrum, such as the amplitude of major frequency components, the sum of energies in specific frequency bands, or harmonic distortion rates. The extracted features can be configured in the form of multidimensional vectors to implicitly represent the state of the current signal. The extracted feature vector may have higher computational efficiency than the raw signal data. The extracted feature vector may be a form of data more suitable for the training and inference of an artificial intelligence model.

[0077] In step S730, the monitoring device (110) can determine the operating state by inputting a feature vector into an artificial intelligence model. The monitoring device (110) can provide the extracted feature vector as input to a pre-trained artificial intelligence model. The artificial intelligence model can analyze the pattern of the input feature vector. Through analysis, the artificial intelligence model can classify the current operating state of the house fan (120) into one of several categories, such as normal, caution, or serious defect. Based on the classification result, the artificial intelligence model can finally determine the state of the house fan (120).

[0078] FIG. 8 illustrates a flowchart showing a detailed operation (S800) of the analysis operation (S330) of the operation state described with reference to FIG. 3.

[0079] Referring to FIG. 8, the detailed operation (S800) of the analysis operation (S330) of the operation state described with reference to FIG. 3 can be performed by a monitoring device (110).

[0080] In step S810, the monitoring device (110) can analyze the operating state based on a combination of current signals and vibration signals. The monitoring device (110) can improve the accuracy of the analysis by using two or more types of heterogeneous data together. For example, the current signal may be useful for detecting electrical abnormalities, such as motor winding defects of the house fan (120). The vibration signal may be effective for identifying mechanical defects, such as bearing wear or blade imbalance. The monitoring device (110) can comprehensively diagnose the condition of the house fan (120) by combining data having mutually complementary characteristics.

[0081] In one embodiment of the present disclosure, the sensor module may further include a vibration sensor that detects vibrations of the house fan (120). The detection signal may further include a vibration signal detected by the vibration sensor. The step of analyzing the operating state (S330) may include a step of analyzing the operating state based on a combination of a current signal and a vibration signal. The monitoring device (110) can reduce the possibility of false positives or non-detections that may occur when relying solely on single sensor data. The monitoring device (110) can contribute to establishing an effective maintenance plan by more precisely identifying the root cause of a defect.

[0082] In one embodiment of the present disclosure, step S810 may include the step of extracting first feature data from a current signal and extracting second feature data from a vibration signal. The monitoring device (110) may combine the first feature data and the second feature data to generate a single fused feature data. The generated fused feature data may be used as input to an artificial intelligence model. The artificial intelligence model may analyze the fused feature data to classify the operating status of the house fan (120) as normal, caution, or a specific type of defect. The multi-modal data fusion method may improve the robustness and reliability of the diagnostic model.

[0083] FIG. 9 illustrates a flowchart showing a detailed operation (S900) of the analysis operation (S810) of the operation state described with reference to FIG. 8.

[0084] Referring to FIG. 9, the detailed operation (S900) of the analysis operation (S810) of the operation state can be performed by the monitoring device (110).

[0085] In step S910, the monitoring device (110) can generate first frequency domain data by performing a Fast Fourier Transform on the current signal. The monitoring device (110) can extract a first feature vector from the first frequency domain data. The monitoring device (110) can convert time-series current data obtained from the motor of the house fan (120) into frequency domain data. The monitoring device (110) can identify periodic components present in the current signal through the process of converting to frequency domain data. The first feature vector may be data including the magnitude of the fundamental frequency component related to the rotational speed of the motor, the energy distribution of harmonic components, or the power spectral density of a specific frequency band.

[0086] In step S920, the monitoring device (110) can generate second frequency domain data by performing a wavelet transform on the vibration signal. The monitoring device (110) can extract a second feature vector from the second frequency domain data. The monitoring device (110) can apply the wavelet transform to analyze the vibration signal, which is an abnormal signal whose characteristics change over time. The monitoring device (110) can simultaneously analyze the time information and frequency information of the signal through the wavelet transform. The second feature vector may be data including statistical values ​​of wavelet coefficients across multiple scales, energy information at a specific scale, or entropy values.

[0087] In step S930, the monitoring device (110) can generate a fused feature vector by combining a first feature vector and a second feature vector. The monitoring device (110) can construct a fused feature vector that more accurately represents the condition of the house fan (120) by integrating the features of the electrical signal and the features of the mechanical vibration signal. Through data fusion, the monitoring device (110) can diagnose complex defect conditions that are difficult to identify with single sensor data alone. The monitoring device (110) can generate the fused feature vector by sequentially connecting the two feature vectors. The monitoring device (110) can generate the fused feature vector by combining each feature vector with weights assigned to them.

[0088] In step S940, the monitoring device (110) can analyze the operating state by inputting the fused feature vector into an artificial intelligence model. The monitoring device (110) can determine the current state of the house fan (120) by providing the generated fused feature vector to a pre-trained artificial intelligence model. The monitoring device (110) can analyze the pattern inherent in the fused feature vector through the artificial intelligence model. The artificial intelligence model can classify the state into a normal state, an initial defect state, or a severe defect state through pattern analysis. For example, the artificial intelligence model may be a Support Vector Machine (SVM), a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Transformer, a Generative Adversarial Network (GAN), or a Graph Neural Network (GNN). However, the present disclosure is not limited thereto.

[0089] In one embodiment of the present disclosure, step S930 may include the step of combining features by applying Principal Component Analysis (PCA) to a first feature vector and a second feature vector. The monitoring device (110) can reduce the dimensionality of the data while preserving the information of the two feature vectors. The monitoring device (110) can generate a fused feature vector using the dimensionality-reduced data. The monitoring device (110) can increase the computational efficiency of the artificial intelligence model through Principal Component Analysis. The monitoring device (110) can prevent overfitting through Principal Component Analysis.

[0090] FIG. 10 illustrates a flowchart showing a method (S1000) according to one embodiment of the present disclosure.

[0091] Referring to FIG. 10, the method (S1000) can be performed by a monitoring device (110).

[0092] In step S1010, the monitoring device (110) can generate an alarm message when an abnormal state is determined by an artificial intelligence model. The monitoring device (110) can determine an abnormal state when the operating state of the house fan (120) deviates from a predefined normal range. When an abnormal state is detected, the monitoring device (110) can generate an alarm message to quickly notify the worker of the situation and induce necessary measures. The generated alarm message can be transmitted to a worker terminal (130) or a central control system so that the worker can immediately recognize it.

[0093] In one embodiment of the present disclosure, the artificial intelligence model may be a model trained to classify an abnormal state into one of a plurality of defect types based on the pattern of a current signal. For example, the defect types may be bearing defects, motor winding defects, blade imbalance, gearbox damage, shaft misalignment, poor lubrication, and electrical noise. However, the present disclosure is not limited thereto. The method (S1000) may further include the step of generating an alarm message when an abnormal state is determined by the artificial intelligence model. The alarm message may include a unique identifier of the house fan (120), an attachment location on a digital map, a classified defect type, and pre-set actions according to the defect type. For example, if a blade imbalance defect is detected, the actions may include specific instructions such as 'blade inspection and balancing' or 'immediate shutdown followed by expert inspection'.

[0094] In one embodiment of the present disclosure, step S1010 may include the step of classifying the generated alarm message according to severity. The monitoring device (110) may set an alarm level by analyzing the type and degree of progression of the defect. For example, the alarm level may be divided into stages of 'caution', 'warning', and 'danger'. Depending on each level, the transmission target or display method of the alarm message may vary. An alarm of the 'danger' level may be transmitted as an emergency notification to all relevant worker terminals (130). Additionally, the monitoring device (110) may perform control to automatically cut off the power to the corresponding house fan (120).

[0095] FIG. 11 illustrates a flowchart showing a method (S1100) according to one embodiment of the present disclosure.

[0096] Referring to FIG. 11, the method (S1100) can be performed by a monitoring device (110).

[0097] In one embodiment of the present disclosure, the digital map may be a 3D map implemented based on three-dimensional design data of a ship.

[0098] In step S1110, the monitoring device (110) can transmit a work order for a specific house fan to a worker terminal (130). If the operating status of the house fan (120) is determined to be abnormal, the monitoring device (110) can generate a work order for maintenance or inspection of the house fan (120). The work order may include a unique identifier of the house fan (120). The work order may include the attachment location of the house fan (120). The work order may include the determined type of defect. The work order may include information on recommended actions. The monitoring device (110) can transmit the generated work order via a network to a worker terminal (130) assigned to a responsible worker.

[0099] In step S1120, the monitoring device (110) may respond to confirmation from the worker terminal (130) regarding the work instruction. The monitoring device (110) may highlight an icon corresponding to a specific house fan (120) on a 3D map in accordance with the response. The monitoring device (110) may superimpose navigation information on the 3D map to guide the shortest path from the worker's current location to the attachment location of the specific house fan (120). The worker may accept or confirm the work instruction through the interface of the worker terminal (130). The monitoring device (110) may receive a confirmation signal from the worker terminal (130). Based on the received confirmation signal, the monitoring device (110) may activate a visual guidance function to help the worker find the target house fan (120). Highlighting the icon may include changing the color, size, or flashing effect of the icon.

[0100] In one embodiment of the present disclosure, at step S1120, the monitoring device (110) can obtain the worker's current location information in real time through a Global Positioning System (GPS) sensor or an indoor location measurement system equipped in the worker terminal (130). The monitoring device (110) can track the worker's movement path based on the obtained current location information. The monitoring device (110) can dynamically update the shortest path guidance according to the worker's movement. The monitoring device (110) can display the updated navigation information in real time on a 3D map.

[0101] FIG. 12 illustrates a flowchart showing a method (S1200) according to one embodiment of the present disclosure.

[0102] Referring to FIG. 12, the method (S1200) can be performed by a monitoring device (110).

[0103] In step S1210, the monitoring device (110) can store the detection signal, attachment location, and operation status in a time-series database by matching them with the unique identifier and timestamp of the house fan (120). The monitoring device (110) can organize the data received from each house fan (120) in chronological order. The monitoring device (110) can perform history management by storing the data in the database. The time-series database may be a database specialized in efficiently storing and retrieving data that changes over time. For example, the time-series database may be InfluxDB, Prometheus, TimescaleDB, Amazon Timestream, Azure Time Series Insights, Google Cloud Bigtable, or OpenTSDB. However, the present disclosure is not limited thereto. The data stored may include a unique identifier of the house fan (120), the time the data was collected, a current signal, a vibration signal, GPS (Global Positioning System) coordinates, temperature, humidity, etc.

[0104] In step S1220, the monitoring device (110) can analyze the performance degradation trend of the house fan (120) based on the history of changes in the accumulated operating time and operating state of the house fan (120) stored in a time-series database. The monitoring device (110) can predict the remaining useful life based on the history of changes in the accumulated operating time and operating state of the house fan (120) stored in a time-series database. The monitoring device (110) can track changes in the state of the house fan (120) by analyzing the accumulated time-series data. The monitoring device (110) can identify performance degradation patterns using a statistical analysis model or a machine learning model. For example, the monitoring device (110) can detect a pattern in which the vibration magnitude in a specific frequency band gradually increases over time. The monitoring device (110) can determine the detected pattern as a sign of performance degradation. The prediction of the remaining useful life (RUL) may be an estimate of the time remaining until the house fan (120) fails. The monitoring device (110) can predict the remaining effective lifespan using a regression analysis, survival analysis, or a model based on a Recurrent Neural Network (RNN).

[0105] The control interface can visually display performance degradation trends and remaining effective lifespan. For example, the control interface can display a graph showing the performance degradation trend in a detail window that appears when a specific house fan (120) icon on the digital map (1300) is selected. The control interface can display the remaining effective lifespan in days or hours to help the operator intuitively identify when maintenance is needed. The control interface can change the icon color of the corresponding house fan (120) if the remaining effective lifespan falls below a threshold. The control interface can generate a warning notification to draw visual attention if the remaining effective lifespan falls below a threshold.

[0106] FIG. 13 illustrates a digital map (1300) that may be referenced in various embodiments of the present disclosure.

[0107] Referring to FIG. 13, the digital map (1300) may be a graphical user interface (GUI) that provides a control interface to a user. The digital map (1300) may visually represent the physical layout of the work environment where the ship is being built. The digital map (1300) may be implemented based on drawing data of the ship's upper deck or the entire shipyard. For example, the digital map (1300) may be generated based on a two-dimensional floor plan, three-dimensional design data, satellite imagery, aerial photographs, indoor maps, Building Information Modeling (BIM) data, Geographic Information System (GIS) data, or LiDAR scan data. However, the present disclosure is not limited thereto.

[0108] The digital map (1300) can visually display the attachment locations and operating status of multiple house fans (120). Each house fan (120) can be displayed as an icon on the digital map (1300). The monitoring device (110) can control the digital map (1300) to display an icon in a first color when the operating status of the house fan (120) is normal, and to display an icon in a second color distinct from the first color when it is abnormal. When a user selects a specific icon on the digital map (1300), a detailed information window for the house fan (120) corresponding to the selected icon may be displayed, and the detailed information window may include a unique identifier of the house fan (120), a real-time current value, an accumulated operating time, and a power control button.

[0109] The digital map (1300) may be a 3D map implemented based on the three-dimensional design data of the vessel. The 3D map may provide the worker with more intuitive information about the work environment. The monitoring device (110) may generate work instructions for a specific house fan (120) and transmit the work instructions to the worker terminal (130). When the worker checks the work instructions, the monitoring device (110) may highlight the icon of the corresponding house fan (120) on the digital map (1300) and display overlaid navigation information that guides the shortest path from the worker's current location to the target house fan (120).

[0110] In one embodiment of the present disclosure, a digital map (1300) can visualize and display predictive maintenance information for a house fan (120). For example, the digital map (1300) can display the results of an analysis of the performance degradation trend of each house fan (120) or the results of a prediction of the remaining effective lifespan as a widget in the form of a graph or a gauge. Through the digital map (1300), the user can intuitively identify the maintenance time for each house fan (120). Through this, the manager can efficiently establish a maintenance plan and prevent unexpected equipment failures.

[0111] Although the operations included in the method of the present disclosure have been described in a sequential order according to the flowchart in which the method is illustrated, the operations included in the method of the present disclosure may be executed in any other combination. Furthermore, detailed changes or modifications may be made to the operations included in the method of the present disclosure, and the fact that such operations are included in the flowchart does not imply that they are essential for executing the method of the present disclosure. In one embodiment, at least some of the operations included in the method of the present disclosure may be performed in parallel, iteratively, or heuristically. Additionally, in another embodiment, at least some of the operations included in the method of the present disclosure may be omitted.

[0112] Various embodiments of the present disclosure may be implemented as software on a machine-readable storage medium (MRSM). Additionally, software may be inferred from the various embodiments of the present disclosure by a person skilled in the art to which the present disclosure pertains. For example, the software may be a computer program containing instructions that can be read by a computing device. In one embodiment, the processor of the computing device may execute a called instruction to cause the components of the computing device to perform a function corresponding to that instruction. The storage medium may refer to any type of recording medium in which information that can be read by a device is stored. The storage medium may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical information storage device. In one embodiment, the storage medium may be implemented in a distributed form in a networked computer system, etc. Here, the software may be stored in a distributed manner in a computer system, etc. Additionally, in another embodiment, the storage medium may be a non-transitory storage medium. Non-transient storage media refer to media that exist regardless of whether information is stored semi-permanently or temporarily, and do not include signals that are transmitted transiently.

[0113] A method according to one embodiment of the present disclosure may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., Compact Disc Read Only Memory (CD-ROM)) or distributed online (e.g., download or upload) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., downloadable app) may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0114] Although the technical concept according to the present disclosure has been described by various embodiments above, the technical concept according to the present disclosure includes various substitutions, modifications, and changes that can be made within the scope of understanding by a person skilled in the art to which the present disclosure pertains. Furthermore, such substitutions, modifications, and changes should be interpreted as being included within the scope of the claims.

Claims

Claim 1 A method performed by an electronic device comprising: acquiring a detection signal from a sensor module of a house fan attached to the upper deck of a ship during the shipbuilding process; identifying the attachment location of the house fan based on a GPS signal included in the detection signal; analyzing the operating state of the house fan based on a current signal included in the detection signal; and providing a control interface for the house fan based on the attachment location and the operating state, wherein the control interface is an interface implemented as a digital map that visually displays the attachment location and the operating state. Claim 2 A method according to claim 1, wherein the upper deck of the vessel is attached with a first house fan and a second house fan distinguished from the first house fan, the first house fan includes a first sensor module, the second house fan includes a second sensor module, and the first sensor module and the second sensor module are each modules that transmit the detection signal through a wireless communication module based on a unique identifier, the step of identifying the attachment location includes distinguishing the first house fan and the second house fan based on the unique identifier and identifying the attachment location based on each GPS signal, and the step of providing the control interface includes providing a control interface capable of individual operation control for the first house fan and the second house fan. Claim 3 The method according to claim 1, wherein the step of analyzing the operating state includes the step of analyzing the operating state based on pattern analysis of the current signal based on an artificial intelligence model, wherein the artificial intelligence model is a model learned based on a combination of first type learning data having an abnormal state pattern and second type learning data having a normal state pattern, and the step of analyzing the operating state based on the analysis of the artificial intelligence model includes: the step of generating frequency domain data by performing a Fast Fourier Transform on the current signal; the step of extracting a feature vector including the magnitude and distribution of frequency components from the frequency domain data; and the step of determining the operating state by inputting the feature vector into the artificial intelligence model. Claim 4 A method according to claim 1, wherein the sensor module further includes a vibration sensor for detecting vibration of the house fan, the detection signal further includes a vibration signal detected from the vibration sensor, and the step of analyzing the operating state includes the step of analyzing the operating state based on a combination of the current signal and the vibration signal. Claim 5 A method according to claim 1, wherein the control interface displays an icon representing the house fan in a first color on the digital map when the operating state is normal, displays it in a second color distinct from the first color when the operating state is abnormal, displays it in response to a user selection for an icon corresponding to the house fan displayed on the digital map, displays a detailed information window including identification information, real-time current value, and cumulative operating time of the house fan, and is configured to receive power control input of the house fan through the detailed information window.

Images