Method for analyzing induced wave and apparatus thereof

Abstract

According to an embodiment of the present application, a method for analyzing cruising waves is provided. The method may include the steps of: acquiring wave height data; generating wave height displacement data from the wave height data and reference wave height data; acquiring point cloud data of a vessel; matching a reference pattern to the point cloud data; generating behavioral displacement data of the vessel based on the matching; and generating relationship information between cruising waves and the behavior of the vessel based on the wave height displacement data and the behavioral displacement data.

Description

Technology Field

[0001] This application relates to a method and apparatus for analyzing torsion frequency. Background Technology

[0002] Technology for analyzing the interaction between waves and ship motion plays a crucial role in the maritime industry. In particular, precisely analyzing wave characteristics and ship movements is essential to ensure vessel safety and the efficiency of cargo handling operations. To this end, conventional methods have primarily utilized ultrasonic or radar wave gauges to measure data such as significant wave height, period, and frequency, and to predict ship behavior based on this data.

[0003] However, since conventional wave measuring devices are fixedly installed at specific locations to collect data, there is a high probability of discrepancies occurring between the measured data and the actual wave conditions at the vessel's location. This prevents the measured data from adequately reflecting the real environment and undermines the reliability of the analysis results.

[0004] Furthermore, current ship behavior analysis is primarily conducted through simulations or scale model testing; however, because these methods utilize pre-modeled data rather than actual data, they fail to adequately reflect environmental variables (e.g., wind, currents, etc.). In particular, the lack of data collected at the same time and location makes it difficult to precisely derive the correlation between waves and ship behavior. The problem to be solved

[0005] Technology for analyzing the interaction between waves and ship motion plays a crucial role in the maritime industry. In particular, precisely analyzing wave characteristics and ship movements is essential to ensure vessel safety and the efficiency of cargo handling operations. To this end, conventional methods have primarily utilized ultrasonic or radar wave gauges to measure data such as significant wave height, period, and frequency, and to predict ship behavior based on this data.

[0006] However, since conventional wave measuring devices are fixedly installed at specific locations to collect data, there is a high probability of discrepancies occurring between the measured data and the actual wave conditions at the vessel's location. This prevents the measured data from adequately reflecting the real environment and undermines the reliability of the analysis results.

[0007] Furthermore, current ship behavior analysis is primarily conducted through simulations or scale model testing; however, because these methods utilize pre-modeled data rather than actual data, they fail to adequately reflect environmental variables (e.g., wind, currents, etc.). In particular, the lack of data collected at the same time and location makes it difficult to precisely derive the correlation between waves and ship behavior. means of solving the problem

[0008] According to an embodiment of the present application, a method for analyzing cruising waves is provided. The method may include the steps of: acquiring wave height data; generating wave height displacement data from the wave height data and reference wave height data; acquiring point cloud data of a vessel; matching a reference pattern to the point cloud data; generating behavioral displacement data of the vessel based on the matching; and generating relationship information between cruising waves and the behavior of the vessel based on the wave height displacement data and the behavioral displacement data.

[0009] In addition, the above behavior displacement data may include three linear displacement data and three rotational displacement data regarding the behavior of the vessel.

[0010] Additionally, the matching step may include a step of selecting a region of interest in the point cloud data; and a step of extracting coordinates of the reference pattern such that the difference between the point cloud data and the reference pattern is minimized within the region of interest.

[0011] Additionally, the method may further include a step of removing noise from the reference pattern using polynomial regression analysis, and the matching step may be performed based on the reference pattern from which the noise has been removed.

[0012] Additionally, the method may further include the steps of: acquiring reference point cloud data; selecting an area with high data density in the reference point cloud data as a region of interest; and selecting an area among the regions of interest that reflects the geometric features of the vessel as the reference pattern.

[0013] Additionally, the method may further include a step of removing noise from the wave height displacement data or the behavioral displacement data using a Kalman filter.

[0014] In addition, the step of generating the relationship information may include the step of integrating the wave height displacement data and the behavioral displacement data in a time series to generate time series displacement data.

[0015] Additionally, the step of generating the relationship information may further include: a step of dividing the time-series displacement data into a plurality of time intervals; a step of converting the divided time-series displacement data into the frequency domain; a step of calculating correlation coefficients between the wave height displacement data in the frequency domain and the behavioral displacement data in the frequency domain for each frequency; and a step of calculating the relationship information by combining the respective correlation coefficients according to the time intervals.

[0016] In addition, the step of generating the relationship information may further include the step of inputting the time-series displacement data into a predetermined machine learning model to output the relationship information.

[0017] A computer program is provided according to an embodiment of the present application. The program may be stored on a recording medium to execute a method according to an embodiment of the present application.

[0018] According to an embodiment of the present application, a cruising frequency analysis device is provided. The device may include a memory in which a program for cruising frequency analysis is stored; and a processor that acquires wave height data by executing the program, generates wave height displacement data from the wave height data and reference wave height data, acquires point cloud data of a vessel, matches a reference pattern to the point cloud data, generates behavioral displacement data of the vessel based on the matching, and generates relationship information between the cruising frequency and the behavior of the vessel based on the wave height displacement data and the behavioral displacement data.

[0019] Additionally, it may further include a wave height sensor that measures the wave height to generate the wave height data; and a LiDAR sensor that photographs the vessel to generate the point cloud data.

[0020] In addition, the wave height sensor may be installed facing the sea, and the lidar sensor may be installed facing the unloading dock or the vessel. Effects of the invention

[0021] According to the embodiments of the present application, data consistency can be maintained by simultaneously measuring the sailing frequency and the motion of the vessel at the same time and in the same space.

[0022] In addition, according to the embodiments of the present application, the amount of movement (linear displacement and rotational displacement) of a ship can be precisely measured by utilizing 3D point cloud data of the ship.

[0023] In addition, according to the embodiments of the present application, the relationship between the cruising frequency and the ship's behavior can be precisely modeled.

[0024] The effects obtainable from the embodiments of the present application are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present application belongs from the description below. Brief explanation of the drawing

[0025] A brief description of each drawing is provided to help to better understand the drawings cited in this application. FIG. 1 is a flowchart of a method for analyzing anti-frequency waves according to an embodiment of the present application. FIG. 2 is a block diagram of a frequency analysis device according to an embodiment of the present application. Specific details for implementing the invention

[0026] The technical concept of the present application is subject to various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the technical concept of the present application to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the scope of the technical concept of the present application.

[0027] In explaining the technical concept of the present application, detailed descriptions of related prior art are omitted if it is determined that such descriptions may unnecessarily obscure the essence of the present application.

[0028] The terms used in this specification are for describing embodiments and are not intended to limit or / or restrict this application. Singular expressions include plural expressions unless the context clearly indicates otherwise. Additionally, numbers used in the description of this application (e.g., First, Second, etc.) are merely identifiers to distinguish one component from another.

[0029] In this specification, when it is stated that a part is connected to another part, this includes not only cases where they are directly connected, but also cases where they are indirectly connected with other components in between. Furthermore, when it is stated that a part includes a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0030] Furthermore, in this application, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related configurations.

[0031] In addition, terms such as “~part,” “~device,” “~part,” “~module,” and “block” described in this application refer to a unit that processes at least one function or operation, and this can be implemented as hardware or software or a combination of hardware and software, such as a processor, microprocessor, microcontroller, CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerated Processor Unit), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), and FPGA (Field Programmable Gate Array).

[0032] Furthermore, it is intended to clarify that the classification of the components in this application is merely based on the primary function each component is responsible for. That is, two or more components described below may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Additionally, each component described below may additionally perform some or all of the functions performed by other components in addition to its own primary function, and it is obvious that some of the primary functions performed by each component may be exclusively performed by other components.

[0034] The method according to the embodiment of the present application may be performed on a personal computer, workstation, server computer device, etc., equipped with computing power, or on a separate device for this purpose.

[0035] Additionally, the method may be performed on one or more computing devices. For example, at least one step of the method according to an embodiment of the present application may be performed on a client device, and other steps may be performed on a server device. In this case, the client device and the server device may be connected via a network to transmit and receive computation results. Alternatively, the method may be performed by distributed computing technology.

[0037] Hereinafter, embodiments of the present application will be described in detail in turn.

[0039] FIG. 1 is a flowchart of a method for analyzing anti-frequency waves according to an embodiment of the present application.

[0040] In step S110, wave height data can be acquired. Wave height data is data that measures the characteristics of waves in the ocean, and in particular, may relate to the height of the waves. However, it is not limited thereto, and the wave height data may additionally include characteristics such as the period and frequency of the wave height.

[0041] In the embodiments, wave height data may be measured, for example, through a wave height sensor. A wave height sensor is intended to measure the characteristics of waves in a marine environment and can generate data such as significant wave height, period, and frequency. For example, an ultrasonic wave height sensor can calculate wave height by emitting an ultrasonic signal and receiving a signal reflected from the sea surface. Additionally, for example, a radar wave height sensor can measure changes in the sea surface using high-frequency electromagnetic waves. Furthermore, for example, a hydrostatic wave height sensor can detect changes in water pressure through a pressure sensor installed on the seabed and convert this into wave height. However, it is not limited thereto.

[0042] In step S120, wave height displacement data can be generated. Wave height displacement data represents the amount of change in sea level height and can be generated through comparison with reference wave height data. Additionally, the reference wave height data is a sea level height measured in advance, which may be, for example, the average sea level height over a predetermined period, the sea level height before the occurrence of the sailing wave, or the sea level height measured at the beginning of the sailing wave analysis.

[0043] In step S130, point cloud data of the vessel can be obtained. Point cloud data of the vessel is generated by photographing the vessel at least partially, and may refer to data that represents the external shape, position, etc. of the vessel in a three-dimensional coordinate system.

[0044] In the embodiments, point cloud data may be generated through a Light Detection and Ranging (LiDAR) sensor. The LiDAR sensor emits laser light and receives reflected signals to calculate the distance to an object, and based on this, can measure the shape and position of the object in three-dimensional space with high resolution. However, it is not limited thereto, and other sensor technologies may be used to generate point cloud data depending on the embodiments.

[0045] In step S140, a reference pattern can be matched to the point cloud data. Matching may mean transforming the coordinates of the point cloud data or the reference pattern to minimize the geometric difference between the point cloud data and the reference pattern. Through the transformed coordinates, the behavior of the vessel, namely its position and attitude, can be estimated.

[0046] In step S140, the reference pattern is a reference shape for determining the displacement of the ship's behavior and may mean point cloud data regarding at least a part of the ship.

[0047] In the embodiments, the reference pattern may relate to an area of ​​the vessel representing a geometric feature of the vessel. For example, the reference pattern may include the vessel's deck, hull corners, other structures, etc. However, it is not limited thereto.

[0048] In the embodiment, the reference pattern may be derived from previously generated point cloud data of a vessel, for example, point cloud data of a vessel before the occurrence of a sailing wave, point cloud data of a vessel generated at the beginning of the sailing wave analysis, etc.

[0049] In the embodiment, the measurement time of the reference pattern (or point cloud data from which the reference pattern originates) may correspond to the measurement time of the reference wave height data.

[0050] In an embodiment, step S140 may include: a step of selecting a Region of Interest (ROI) from the point cloud data of step S130; and a step of extracting coordinates of a reference pattern such that the difference between the point cloud data and the reference pattern within the region of interest is minimized.

[0051] In the embodiments, the region of interest may be selected, for example, as an area with a high density of point cloud data or an area that well reflects the geometric features of the ship.

[0052] In the embodiments, the step of extracting the coordinates of the reference pattern may be performed by changing the coordinates of the reference pattern so that the difference between the point cloud data and the reference pattern is minimized. At this time, quantitative indicators such as Root Mean Squared Error (RMSE) may be applied to calculate the difference. However, it is not limited thereto.

[0053] In step S150, motion displacement data of the vessel can be generated based on matching. The motion displacement data is obtained by classifying and quantifying the movement of the vessel into six degrees of freedom, and may include three linear displacement data and three rotational displacement data. Here, the linear displacement data represents the amount of movement in the x, y, and z axis directions, respectively, and the rotational displacement data may represent changes in roll, pitch, and yaw.

[0054] Specifically, step S150 can be performed based on the matching between the point cloud data and the reference pattern performed in step S140. That is, behavioral displacement data can be generated by comparing the coordinates of the reference pattern changed according to the matching in step S140 with the original coordinates of the reference pattern.

[0055] In step S160, relationship information between the cruising wave and the ship's behavior can be generated. Here, the relationship information represents the influence of the cruising wave on the ship's behavior and, for example, may refer to the correlation between wave height displacement data and the ship's behavior displacement data.

[0056] In an embodiment, step S160 may include the step of generating time-series displacement data by integrating wave height displacement data and behavior displacement data in a time-series manner. That is, through the above step, wave height displacement data and ship behavior displacement data measured at the same time can be integrated into a single data set.

[0057] In an embodiment, step S160 may further include: a step of dividing time-series displacement data into a plurality of time intervals; a step of converting the divided time-series displacement data into the frequency domain; a step of calculating correlation coefficients between wave height displacement data in the frequency domain and behavioral displacement data in the frequency domain for each frequency; and a step of calculating relationship information by combining the correlation coefficients.

[0058] That is, in step S160, time-series displacement data can be divided into multiple time intervals (e.g., divided into units of 10 minutes, 30 minutes, etc.) to generate multiple divided data, and each divided data can be transformed from the time domain to the frequency domain. For example, the Fourier Transform may be applied to such a transformation, but is not limited thereto.

[0059] For each segmented data continuously converted to the frequency domain, correlation coefficients (e.g., Pearson Correlation Coefficient) between behavioral displacement data and wave height displacement data can be calculated for each frequency. Relationship information can be calculated by aggregating such correlation coefficients. Specifically, relationship information can be calculated by accumulating (e.g., averaging) the correlation coefficients for each frequency for multiple segmented data in the frequency domain. The relationship information can represent the behavioral response range for each frequency band.

[0060] That is, in step S160, time-series displacement data can be divided into multiple time intervals (e.g., divided into units of 10 minutes, 30 minutes, etc.) to generate multiple divided data, and each divided data can be transformed from the time domain to the frequency domain. For example, the Fourier Transform may be applied to such a transformation, but is not limited thereto.

[0061] For each segmented data continuously converted to the frequency domain, correlation coefficients (e.g., Pearson Correlation Coefficient) between behavioral displacement data and wave height displacement data can be calculated for each frequency. Relationship information can be calculated by aggregating such correlation coefficients. Specifically, relationship information can be calculated by accumulating (e.g., averaging) the correlation coefficients for each frequency for multiple segmented data in the frequency domain. The relationship information can represent the behavioral response range for each frequency band.

[0062] In an embodiment, the method (100) may further include a step of removing noise from a reference pattern. Here, noise may refer to unnecessary or distorted information contained in the point cloud data corresponding to the reference pattern. Such noise may be caused, for example, by the resolution of the LiDAR sensor, reflected signals from the surrounding environment, or noise from the sensor itself. By removing noise from the reference pattern through the above step, at least a part of the shape of the ship (particularly, curved shape, etc.) based on the reference pattern can be represented more accurately.

[0063] In the embodiments, the step of removing noise from the reference pattern can be performed by polynomial regression analysis using polynomials to model the non-linear relationship between independent and dependent variables. Specifically, point cloud data corresponding to the reference pattern is fitted to a polynomial model to extract major trends, and in this process, higher-order terms are included to explain the data more accurately. Subsequently, the difference between the fitted model and the original data is calculated to isolate and remove noise components. This process can be optimized by performing iteratively. For example, high-order polynomials can be used to remove noise while preserving the geometric features of the reference pattern. However, this is not limited to this.

[0064] In an embodiment, the method (100) may further include a step of removing noise from wave height displacement data or motion displacement data. The noise may include system noise generated during the measurement process and environmental noise generated in the marine environment. For example, system noise may include measurement errors of the sensor, electrical interference, or errors in the data processing process. Additionally, environmental noise may include, for example, wind, currents, or disturbances caused by surrounding vessels. However, it is not limited thereto.

[0065] In the embodiments, the step of removing noise from wave height displacement data or motion displacement data may be performed using a Kalman filter. The Kalman filter is a recursive filtering algorithm that provides an optimal estimate by considering the system's previous state and current measurement value, and is effective for processing data in real time and removing noise. For example, white noise can be removed from wave height displacement data to more clearly identify changes in actual wave height, and noise caused by sensor measurement errors or environmental factors can be removed from ship motion displacement data to accurately track the actual movement of the ship. However, it is not limited to these examples.

[0066] In an embodiment, the method (100) may further include the steps of: acquiring reference point cloud data; selecting an area with high data density in the reference point cloud data as a region of interest; and selecting an area among the regions of interest that reflects the geometric features of the ship as a reference pattern.

[0067] FIG. 1 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0069] FIG. 2 is a block diagram of a frequency analysis device according to an embodiment of the present application.

[0070] The anti-vibration analysis device (200) is for performing the method (100) of FIG. 1, etc., and specifically may include a communication unit (210), an input unit (220), a memory (230), and a processor (240).

[0071] The communication unit (210) can receive or transmit data from inside or outside. The communication unit (210) may include a wired or wireless communication unit. If the communication unit (210) includes a wired communication unit, the communication unit (210) may include one or more components that enable communication through a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof. Additionally, if the communication unit (210) includes a wireless communication unit, the communication unit (210) may transmit or receive data or signals wirelessly using cellular communication, a wireless LAN (e.g., Wi-Fi), etc. In an embodiment, the communication unit (210) may transmit or receive data or signals to and from an external device or an external server under the control of a processor (240).

[0072] The input unit (220) can receive various user commands through external operation. To this end, the input unit (220) may include or be connected to one or more input devices. For example, the input unit (220) may receive user commands by being connected to an interface for various inputs, such as a keypad or a mouse. To this end, the input unit (220) may include an interface such as a USB port as well as a Thunderbolt. Additionally, the input unit (220) may receive external user commands by including or being combined with various input devices such as a touchscreen or a button.

[0073] The memory (230) can store programs and / or program instructions for the operation of the processor (240) and can temporarily or permanently store input / output data. Specifically, the memory (230) can store various data, programs (one or more instructions), applications, software, instructions, code, etc. for driving and controlling the processor (240). For example, the memory (230) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, magnetic memory, magnetic disk, and optical disk.

[0074] The processor (240) can control the overall operation of the device (200). The processor (240) can execute one or more programs or software stored in memory (230). The processor (240) may mean a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or a dedicated processor (240) on which the methods according to embodiments of the present application are performed.

[0075] In an embodiment, the processor (240) can acquire wave height data, generate wave height displacement data from the wave height data and reference wave height data, acquire point cloud data of the vessel, match a reference pattern to the point cloud data, generate behavioral displacement data of the vessel based on the matching, and generate relationship information between the cruising wave and the behavior of the vessel based on the wave height displacement data and the behavioral displacement data.

[0076] In an embodiment, the processor (240) can perform matching by selecting a region of interest in the point cloud data and extracting the coordinates of a reference pattern such that the difference between the point cloud data and the reference pattern is minimized within the region of interest.

[0077] In an embodiment, the processor (240) can remove noise from the reference pattern using polynomial regression analysis. Accordingly, the processor (240) can perform matching based on the noise-removed reference pattern.

[0078] In an embodiment, the processor (240) acquires reference point cloud data, selects an area with high data density in the reference point cloud data as a region of interest, and selects an area among the regions of interest that reflects the geometric features of the ship as a reference pattern.

[0079] In an embodiment, the processor (240) can remove noise from wave height displacement data or motion displacement data using a Kalman filter.

[0080] In an embodiment, the processor (240) can generate time-series displacement data by integrating wave height displacement data and motion displacement data in a time-series manner.

[0081] In an embodiment, the processor (240) divides time-series displacement data into multiple time intervals, converts the divided time-series displacement data into a frequency domain, calculates correlation coefficients between wave height displacement data in the frequency domain and behavioral displacement data in the frequency domain for each frequency, and calculates relationship information by combining the respective correlation coefficients according to the time intervals.

[0082] In an embodiment, the processor (240) can input time-series displacement data into a predetermined machine learning model and output relationship information.

[0083] Although not illustrated, according to an embodiment, the wave analysis device may further include a wave gauge sensor that measures wave height to generate wave height data; or a lidar sensor that photographs a vessel to generate point cloud data. In this case, the wave gauge sensor may be installed facing the sea, and the lidar sensor may be installed facing the unloading dock or the vessel.

[0084] FIG. 2 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0086] FIG. 3 is a drawing for explaining a tremolo frequency analysis device according to an embodiment of the present application.

[0087] Referring to FIG. 3, the nautical frequency analysis device may further include a support member (300) for installing detailed components of the nautical frequency analysis device (processor, wave height sensor, etc.).

[0088] Specifically, the support member (300) may include a vertical post (310) installed on the ground and extending upward; a first horizontal beam (320) extending from the post (310) toward the sea; and a second horizontal beam (330) extending in the opposite direction of the first horizontal beam (320).

[0089] A wave height sensor (400) and a lidar sensor (500) may be provided at the end of the first horizontal beam (320). At this time, the wave height sensor (400) may be installed facing the sea, and the lidar sensor (500) may be installed facing the unloading dock or the ship.

[0090] The first horizontal beam (320) may be adjustable in length. Specifically, the first horizontal beam (320) may include a first-1 horizontal beam (322) extending from a vertical post (310) and a first-2 horizontal beam (324) that can move in and out of the interior of the first-1 horizontal beam (322). The total length of the first horizontal beam (320) may be adjusted according to the movement of the first-1 horizontal beam (322). Additionally, a wave height sensor (400) and a LiDAR sensor (500) may be installed at the end of the first-2 horizontal beam (324).

[0091] Additionally, the support member (300) may further include a connecting member (340) connecting a vertical post (310) and the first horizontal beam (320) to secure the first horizontal beam (320) extending toward the sea. The vertical post (310), the first horizontal beam (320), and the connecting member (340) may form a truss structure.

[0092] Specifically, the connecting portion (340) may include a first connecting portion (342) connected to the first-1 horizontal beam (322) and a second connecting portion (344) connected to the first-2 horizontal beam (324). Considering the first-1 horizontal beam (322) which has no change in length, the first connecting portion (342) may also be formed of a rigid material that has no change in length. Alternatively, considering the first-2 horizontal beam (324) which has a change in position, the second connecting portion (344) may be formed to be adjustable in length. For example, the second connecting portion (344) may be made of an elastic material or configured to be adjustable in length through a change in the position of connection / disconnection. However, it is not limited thereto.

[0093] A housing (350) may be provided between the vertical post (310) and the second horizontal beam (330). The housing (350) may be equipped with a processor, a communication unit, etc.

[0094] The first horizontal beam (320) and the second horizontal beam (330) may have a hollow formed inside, and communication lines and power lines for the wave height sensor (400) and the lidar sensor (500) may be provided through the interior of the first horizontal beam (320) and the second horizontal beam (330).

[0095] FIG. 3 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0097] FIG. 4 is a diagram illustrating the anti-frequency analysis process according to an embodiment of the present application.

[0098] Referring to FIG. 4, wave height data over time is shown. Specifically, in FIG. 4, raw data is wave height data measured through a wave height sensor, and filtered data is wave height data with noise removed from the raw data.

[0099] Raw data can be distorted by environmental factors (e.g., wind, currents, interference from surrounding objects) and system noise (e.g., electrical noise from sensors) occurring during the measurement process. Such distortion can degrade data reliability and potentially have a negative impact on analysis results.

[0100] On the other hand, filtered data is obtained by applying a Kalman filter to the raw data to remove noise, and as shown, forms a much smoother and more stable curve compared to the raw data, which more accurately reflects the actual changes in wave height.

[0101] In particular, it demonstrates a process for effectively removing abrupt changes (spikes) occurring within specific time intervals. These sharp peaks are generally considered noise, and the accuracy of the analysis can be improved by removing this abnormal data through a filtering process.

[0102] FIG. 4 is exemplary, and various configurations may be applied according to embodiments of the present application. FIG. 4 illustrates noise removal of wave height data, but the same can be applied to point cloud data acquired through a lidar sensor.

[0104] FIG. 5 is a diagram illustrating the anti-frequency analysis process according to an embodiment of the present application.

[0105] Referring to FIG. 5, a process of extracting a reference pattern from the point cloud data of a ship and matching it to new point cloud data is illustrated.

[0106] Referring to FIG. 5(a), reference point cloud data is shown. The reference point cloud data may be point cloud data generated by capturing the vessel using a LiDAR sensor during the initial stage of the voyage analysis. In this case, the reference point cloud data may contain noise generated in the environment surrounding the vessel. That is, the density of the reference point cloud data may be partially uneven, and in particular, in certain areas, distorted information due to noise may be included.

[0107] Referring to Fig. 5(b), a region of interest selected from reference point cloud data is shown. The region of interest can be selected as an area with a high density of point cloud data in the reference point cloud data.

[0108] Referring to Fig. 5(c), a reference pattern selected in the region of interest is illustrated. The reference pattern can be selected as an area within the region of interest where the geometric features of the ship are clearly visible.

[0109] Referring to Figure 5(d), a noise-removed reference pattern is shown. The noise can be removed using polynomial regression analysis, and as shown, outliers can be removed and the continuity between data can be improved.

[0110] Referring to FIG. 5(e), the matching of the point cloud data of the ship (different from the reference point cloud data) with the reference pattern is illustrated. The matching can be performed by changing the coordinates of the reference pattern to correspond to the point cloud data. The ship's behavioral displacement data can be generated from the difference between the changed coordinates of the reference pattern and the original coordinates of the reference pattern.

[0111] FIG. 5 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0113] The method according to an embodiment of the present application may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present application or may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0114] Additionally, the method according to the disclosed embodiments 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.

[0115] A computer program product may include a software program and a computer-readable storage medium on which the software program is stored. For example, a computer program product may include a product in the form of a software program (e.g., a downloadable app) that is distributed electronically through a manufacturer of an electronic device or an electronic market (e.g., Google Play Store, App Store). For electronic distribution, at least a portion of the software program may be stored on a storage medium or temporarily created. In this case, the storage medium may be a server of the manufacturer, a server of the electronic market, or a storage medium of a relay server that temporarily stores the software program.

[0116] A computer program product may include a storage medium of a server or a storage medium of a client device in a system composed of a server and a client device. Alternatively, if there is a third device (e.g., a smartphone) that communicates with the server or the client device, the computer program product may include a storage medium of the third device. Alternatively, the computer program product may include the SW program itself that is transmitted from the server to the client device or the third device, or transmitted from the third device to the client device.

[0117] In this case, one of the server, the client device, and the third device may execute the computer program product to perform the method according to the disclosed embodiments. Alternatively, two or more of the server, the client device, and the third device may execute the computer program product to perform the method according to the disclosed embodiments in a distributed manner.

[0118] For example, a server (e.g., a cloud server or an artificial intelligence server, etc.) can execute a computer program product stored on the server to control a client device connected to the server in communication to perform a method according to the disclosed embodiments.

[0120] Although the embodiments have been described in detail above, the scope of the present application is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present application as defined in the following claims also fall within the scope of the present application.

Claims

Claim 1 A method for analyzing cruising waves, comprising: a step of acquiring wave height data; a step of generating wave height displacement data from the wave height data and reference wave height data; a step of acquiring point cloud data of a vessel; a step of matching a reference pattern to the point cloud data; a step of generating behavioral displacement data of the vessel based on the matching; and a step of generating relationship information between cruising waves and the behavior of the vessel based on the wave height displacement data and the behavioral displacement data. Claim 2 A method according to claim 1, wherein the behavioral displacement data comprises three mutually orthogonal linear displacement data and three mutually orthogonal rotational displacement data regarding the behavior of the vessel. Claim 3 A method according to claim 1, wherein the matching step comprises: a step of selecting a region of interest in the point cloud data; and a step of extracting the coordinates of the reference pattern such that the difference between the point cloud data and the reference pattern is minimized within the region of interest. Claim 4 A method according to claim 1, further comprising the step of removing noise from the reference pattern using polynomial regression analysis, and performing the matching step based on the reference pattern from which the noise has been removed. Claim 5 A method according to claim 1, further comprising: a step of acquiring reference point cloud data; a step of selecting an area of ​​high data density in the reference point cloud data as a region of interest; and a step of selecting an area among the regions of interest that reflects the geometric features of the vessel as a reference pattern. Claim 6 A method according to claim 1, further comprising the step of removing noise from the wave height displacement data or the behavioral displacement data using a Kalman filter. Claim 7 A method according to claim 1, wherein the step of generating the relationship information comprises the step of integrating the wave height displacement data and the behavioral displacement data in a time series to generate time series displacement data. Claim 8 In claim 7, the step of generating the relationship information further comprises: a step of dividing the time-series displacement data into a plurality of time intervals; a step of converting the divided time-series displacement data into a frequency domain; a step of calculating a correlation coefficient between the wave height displacement data in the frequency domain and the behavioral displacement data in the frequency domain for each frequency; and a step of calculating the relationship information by combining the respective correlation coefficients according to the time intervals. Claim 9 A method according to claim 7, wherein the step of generating the relationship information further comprises the step of inputting the time-series displacement data into a predetermined machine learning model and outputting the relationship information. Claim 10 A computer program stored on a recording medium to execute a method according to any one of paragraphs 1 through 9. Claim 11 A device comprising: a memory in which a program for analyzing a voyage frequency is stored; and a processor that acquires wave height data by executing the program, generates wave height displacement data from the wave height data and reference wave height data, acquires point cloud data of a vessel, matches a reference pattern to the point cloud data, generates behavioral displacement data of the vessel based on the matching, and generates relationship information between the voyage frequency and the behavior of the vessel based on the wave height displacement data and the behavioral displacement data. Claim 12 A device according to claim 11, further comprising: a wave height sensor that measures wave height and generates wave height data; and a lidar sensor that photographs the vessel and generates point cloud data. Claim 13 A device according to Clause 12, wherein the wave height sensor is installed facing the sea and the lidar sensor is installed facing the unloading dock or vessel.

Images