System for environmental, social and governance-based eco-friendly and work-safety management of dredging vessels

Abstract

An ESG management-based eco-friendly and operational safety management system for dredgers is provided, and includes an integrated control server comprising a sensor module that collects operational data in real time, including ground data, environmental data, and status data of dredging equipment within the dredger in the working area where the dredger operates; a collection unit that collects operational data from the sensor module; a prediction unit that inputs operational data into a pre-established prediction model to predict energy consumption and work load by layer; and a control unit that controls the operating speed, operating angle, and operating flow rate of the dredging equipment by optimizing them using an optimization algorithm according to the energy consumption and work load by layer.

Description

Technology Field

[0001] The present invention relates to an ESG management-based eco-friendly and operational safety management system for dredgers, providing a system capable of optimizing operation according to ground conditions, reducing carbon emissions, and increasing energy efficiency. Background Technology

[0002] A dredger ship refers to a vessel-shaped structure built for the purpose of scooping up sediment, sand, or minerals accumulated in rivers, canals, and harbors, and operating on the water. Maintaining a certain water depth is typically crucial for the passage of vessels in rivers, canals, and harbors; dredging operations allow for the maintenance or deepening of waterways and docks that are accumulating sediment, thereby enabling the entry and exit of large vessels. Additionally, dredgers are used for foundation work to construct underwater structures or for extracting seabed waste or minerals. Dredgers can be broadly classified into self-propelled barges, which have their own power, and non-self-propelled barges, which lack power and are towed by external forces such as tugboats. Types of dredgers include Cutter Suction Dredgers, Bucket Dredgers, Dipper Dredgers, Grab Dredgers, Trailing Suction Hopper Dredgers (TSHDs), and Rock Cutter Dredgers.

[0003] At this time, a method for operating a dredger or increasing suction and discharge efficiency using sensor data has been researched and developed. In this regard, prior art Korean Published Patent No. 2009-0099929 (published September 23, 2009) and Korean Registered Patent No. 10-2092256 (published April 23, 2020) disclose a configuration in which the density, flow rate, and pressure of a delivery pipe are measured in real time, stored in a data logger, transmitted to an integrated server through an integrated collector, and the operation of the dredger is monitored and controlled through alarms, remote control, and GPS linkage; and a configuration in which a buoyancy hull, hydraulic boom, cutter, water jet, vacuum suction unit, and centrifugal pump are integrated, and the efficiency of crushing, suctioning, and discharging the dredged object is increased using a spud, crawler track, and depth gauge.

[0004] However, the former discloses only a configuration for monitoring dredger operation and does not implement control through operation optimization based on sensor data; similarly, while the latter discloses a configuration with enhanced efficiency, it does not optimize operation according to the type of ground. The dredger industry consumes massive amounts of fuel and generates significant marine pollution and carbon emissions due to slurry discharge, making sustainable management essential from an environmental perspective. Furthermore, safety risks involving social factors—such as mooring line breakage, pump malfunctions, and human casualties during operations—are ever-present, requiring worker protection and a real-time safety management system. Additionally, transparent recording and reporting of work data, along with verification of equipment operational efficiency, serve as key grounds for strengthening corporate governance transparency and responsible management. Accordingly, research and development of a system capable of achieving energy savings, safety assurance, and environmental conservation by introducing ESG management principles into dredger operations is required. The problem to be solved

[0005] One embodiment of the present invention can provide an ESG management-based eco-friendly and operational safety management system for a dredger, which collects operational data including ground data, environmental data, and status data of dredging equipment within the dredger's operational area; predicts energy consumption and work load by layer based on the operational data; performs optimized operation by controlling the operating speed, operating angle, and operating flow rate of the dredging equipment using an optimization algorithm according to the predicted energy consumption and work load by layer; enables lowering carbon emissions while increasing fuel efficiency through energy optimization control; and reduces the risk of human casualties by monitoring the danger radius of mooring ropes and outputting a warning after detecting the approach of a worker. However, the technical problem that this embodiment aims to solve is not limited to the technical problem described above, and other technical problems may exist. means of solving the problem

[0006] As a technical means for achieving the aforementioned technical task, one embodiment of the present invention includes an integrated control server comprising: a sensor module that collects work data in real time, including ground data, environmental data, and status data of dredging equipment within the dredging vessel in a work area where the dredging vessel operates; a collection unit that collects work data from the sensor module; a prediction unit that inputs the work data into a pre-established prediction model to predict energy consumption and work load by layer; and a control unit that controls the operating speed, operating angle, and operating flow rate of the dredging equipment by optimizing them using an optimization algorithm according to the energy consumption and work load by layer. Effects of the invention

[0007] According to any one of the means for solving the problem of the present invention described above, work data including ground data, environmental data, and status data of dredging equipment within the work area of ​​the dredger is collected, energy consumption and work load by layer are predicted based on the work data, and optimized operation is performed by controlling the operating speed, operating angle, and operating flow rate of the dredging equipment using an optimization algorithm according to the predicted energy consumption and work load by layer, thereby increasing fuel efficiency and reducing carbon emissions through energy optimization control, and the risk of human casualties can be reduced by monitoring the danger radius of the mooring rope and outputting a warning after detecting the approach of a worker. Brief explanation of the drawing

[0008] FIG. 1 is a drawing illustrating an ESG management-based dredger eco-friendly and work safety management system according to one embodiment of the present invention. Figure 2 is a block diagram illustrating an integrated control server included in the system of Figure 1. FIGS. 3 and FIGS. 4 are drawings for illustrating an embodiment in which an ESG management-based management solution according to an embodiment of the present invention is implemented. FIG. 5 is a flowchart illustrating a method for providing an ESG management-based management solution according to an embodiment of the present invention. Specific details for implementing the invention

[0009] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0010] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components, and it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0011] Terms such as “about,” “substantially,” etc., used throughout the specification, are used to mean at or near the stated value when inherent manufacturing and material tolerances are presented in the stated meaning, and are used to prevent unscrupulous infringers from unfairly exploiting the disclosure in which precise or absolute values ​​are mentioned to aid in understanding the invention. Terms such as “step” or “step of” used throughout the specification of the invention do not mean “step for”.

[0012] In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, "part" is not limited to software or hardware, and "part" may be configured to reside in an addressable storage medium or configured to run on one or more processors. Accordingly, as an example, "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0013] Some of the operations or functions described herein as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0014] In this specification, some of the operations or functions described as mapping or matching with a terminal may be interpreted as meaning mapping or matching the terminal's unique number or personal identification information, which is the terminal's identifying data.

[0015] The present invention will be described in detail below with reference to the attached drawings.

[0016] FIG. 1 is a drawing illustrating an ESG management-based eco-friendly and work safety management system for dredgers according to an embodiment of the present invention. Referring to FIG. 1, the ESG management-based eco-friendly and work safety management system for dredgers (1) may include at least one administrator terminal (100), an integrated control server (300), and at least one sensor module (400). However, since the ESG management-based eco-friendly and work safety management system for dredgers (1) of FIG. 1 is merely an embodiment of the present invention, the present invention is not to be interpreted as being limited through FIG. 1.

[0017] At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one administrator terminal (100) can be connected to an integrated control server (300) through the network (200). Also, the integrated control server (300) can be connected to at least one administrator terminal (100) and at least one sensor module (400) through the network (200). Additionally, at least one sensor module (400) can be connected to the integrated control server (300) through the network (200).

[0018] Here, a network refers to a connection structure capable of exchanging information among individual nodes, such as multiple terminals and servers. Examples of such networks include Local Area Networks (LANs), Wide Area Networks (WANs), the World Wide Web (WWW), wired and wireless data networks, telephone networks, and wired and wireless television networks. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), 5G NR (New Radio), 6G (6th Generation of Cellular Networks), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0019] In the following, the term "at least one" is defined as a term including both singular and plural forms, and it will be obvious that even if the term "at least one" does not exist, each component may exist in a singular or plural form and may mean singular or plural. Furthermore, whether each component is provided in a singular or plural form may be changed according to the embodiment.

[0020] At least one administrator terminal (100) may be a terminal of an administrator that monitors work data using a web page, app page, program, or application related to an ESG management-based management solution.

[0021] Here, at least one administrator terminal (100) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a navigation system, a laptop equipped with a web browser, a desktop, a laptop, etc. At this time, at least one administrator terminal (100) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one manager terminal (100) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0022] The integrated control server (300) may be a server that provides a web page, app page, program, or application for an ESG management-based management solution. Additionally, the integrated control server (300) may be a server that receives work data from a sensor module (400) and controls the operation of a dredger in response to it. Here, the integrated control server (300) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, or laptop equipped with a navigation system or a web browser.

[0023] At least one sensor module (400) may be a device that uploads detection data of the dredging of a dredger using a web page, app page, program, or application related to an ESG management-based management solution.

[0024] Here, at least one sensor module (400) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a navigation system, a laptop equipped with a web browser, a desktop, a laptop, etc. At this time, at least one sensor module (400) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one sensor module (400) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0025] FIG. 2 is a block diagram for explaining an integrated control server (300) included in the system of FIG. 1, and FIG. 3 and FIG. 4 are drawings for explaining an embodiment in which an ESG management-based management solution according to an embodiment of the present invention is implemented.

[0026] Referring to FIG. 2, the integrated control server (300) may include a collection unit (310), a prediction unit (320), a control unit (330), a safety accident prediction unit (340), an eco-friendly unit (350), a carbon emission tracking unit (360), a mooring safety management unit (370), a safety monitoring unit (380), and an automatic mode switching unit (390).

[0027] When an integrated control server (300) or another server (not shown) operating in conjunction with an embodiment of the present invention transmits an ESG management-based management solution application, program, app page, web page, etc. to at least one administrator terminal (100) and at least one sensor module (400), the at least one administrator terminal (100) and at least one sensor module (400) may install or open the ESG management-based management solution application, program, app page, web page, etc. Additionally, a service program may be operated on at least one administrator terminal (100) and at least one sensor module (400) using a script executed in a web browser. Here, a web browser refers to a program that enables the use of web (WWW: World Wide Web) services and receives and displays hypertext described in HTML (Hyper Text Mark-up Language), and includes, for example, Chrome, Microsoft Edge, Safari, Firefox, Whale, UC Browser, etc. In addition, "application" refers to an application on a terminal, and includes, for example, an app running on a mobile terminal (smartphone).

[0028] Referring to FIG. 2, the collection unit (310) can collect work data from the sensor module (400). The sensor module (400) can collect work data in real time, including ground data, environmental data, and status data of the dredging equipment within the work area where the dredger is working. At this time, ground data refers to data representing the seabed topography and ground properties, such as soil characteristics, density, particle size, and ground strength of the work area, and environmental data refers to data representing marine and atmospheric environmental conditions that affect the dredging work, such as current velocity, tide, water temperature, salinity, and weather. In addition, status data refers to data representing the operating status, vibration, pressure, flow rate, temperature, power consumption, etc., of the dredging equipment, such as pumps, motors, and mooring ropes, in real time. The methods, sensors, and collection technologies for collecting ground data, environmental data, and condition data, respectively, may be summarized as shown in Table 1 below, but are not limited to those listed and are not excluded for reasons not listed.

[0029] Data classification Main contents (collected items) Collection Method / Sensor Configuration Data collection technology ① Ground data - Soil characteristics (grain size, cohesion, density) - Infiltration resistance, shear strength, permeability coefficient - Seabed topography and depth (water depth, fault, slope) - Soil Property Sensor, Cone Penetration Test (CPT) Sensor, Piezometer, Soil Sampler + AI Image Analysis - 3D Ground Map Created using Sonar and LiDAR - Edge Gateway + OPC-UA-Sonar / LiDAR SDK-Python (NumPy, Open3D, Pandas)- MQTT communication- AWS IoT Core or Azure IoT Hub ② Environmental Data - Ocean currents, current speed, current direction, tides - Water temperature, salinity, turbidity, dissolved oxygen - Weather information (wind speed, atmospheric pressure, humidity, temperature) Measurement of flow velocity and direction using ADCP (Acoustic Doppler Current Profiler) - Measurement of water temperature and salinity using CTD sensors (conductivity, temperature, depth) - Real-time integration of location and weather via meteorological sensors and GPS - Merging with satellite APIs (OpenWeather, NOAA) - IoT Sensor Network (LoRaWAN / LTE) - MQTT Broker (Mosquitto) - TimescaleDB / InfluxDB - Python + Grafana Visualization ③ Status Data - Pump pressure, flow rate, temperature - Engine speed (RPM), fuel consumption - Mooring rope tension, angle, vibration - Pump, winch, motor vibration, bearing temperature - Power consumption, control valve opening - Pressure Transducer, Flow Meter (Magnetic Flowmeter / Ultrasonic Flowmeter) - Temperature Sensor (RTD, Thermocouple), Accelerometer, Load Cell, IMU (Inertial Measurement Unit) - Power Monitoring Module (Power Meter), VFD (Variable Frequency Drive) Interconnection - PLC (Modbus RTU / TCP) - ROS2 Control Bus - Edge AI Board (NVIDIA Jetson) - OPC-UA / MQTT - Data Loading: InfluxDB, PostgreSQL, Kafka Stream

[0030] The sensor module (400) collects work data through at least one sensor layer, digitizes the collected signal through an edge gateway, converts it into an OPC-UA / MQTT protocol, and transmits it to a field server (not shown), and the transmission layer streams data from the field server to the cloud IoT Core via wireless communication (LTE / LoRa / 5G) or wired (Modbus TCP). Additionally, the collection unit (310) can store work data in a time series in InfluxDB / TimescaleDB through a storage and preprocessing layer (Data Layer), remove outliers, and perform synchronization. The collected work data is used for AI analysis, optimized operation, energy optimization, visualization, alarms, etc.

[0031] The prediction unit (320) can predict energy consumption and work load by layer by inputting work data into a pre-established prediction model. In the prediction model, energy consumption and work load by layer are calculated primarily based on a physical formula, and additional resistance by layer is learned and inferred through a machine learning model for residual correction, thereby accurately predicting energy consumption and work load by layer in real time. To this end, features are designed by configuring input data and learning labels are defined, and the prediction model is configured and modeled (learned-verified-tested) as a [physics + machine learning] hybrid model. Then, work data is input in real time into the prediction model thus modeled to infer energy consumption and work load by layer and control of the dredging equipment can be performed.

[0032] <Input Data Configuration>

[0033] Input data explanation Ground / Stratigraphy Characteristics (Ground Data) Particle size distribution, cohesion, density, cone penetration resistance, shear strength, permeability coefficient, water depth, slope, etc. Driving status (status data) Pump rotational speed, discharge pressure / suction pressure, operating flow rate, valve opening, pipe length / diameter / number of bends, mooring rope tension / angle. Environment (environmental data) Current velocity, current direction, wave height, water temperature, salinity, weather. Equipment status (status data) Vibration, temperature, bearing condition, power consumption

[0034] <Learning Label Definition>

[0035] type explanation Energy consumption (per unit volume) Ev=Pin / Q Ev: Energy consumption per unit volume (Wh·m-3) Pin: Input power or fuel equivalent power (W) Q: Operating flow rate (m33·s-1) Workload (Normalized Load Rate) Lr=Pin / Prated Lr: Load factor (dimensionless) Prated: Rated output (W)

[0036] Alternatively, the label can be configured based on the ratio of energy consumption to soil transport volume (kWh / m-3), the ratio of rated torque to pump torque, etc.

[0037] Hybrid Structure Prediction Model

[0038] Physics-based first-order estimation

[0039] Pump Power and Head Composition can be approximated and defined as Equations 1 and 2, respectively. In this context, Pump Power refers to the total energy (electricity) consumed by the dredging pump to transport the slurry (soil + water). This value reflects the system efficiency in the hydrostatic energy required for the fluid to rise to a certain height (Head) per unit time. In other words, Pump Power represents the actual mechanical energy required to raise the slurry to a specific height at a constant flow rate.

[0040]

[0041] Here, Phyd is pump power, that is, hydraulic power (unit W) that the dredging pump actually delivers to the fluid. ρ is the slurry density (kgkg·m-3), g is the acceleration due to gravity (m·s-2), Q is the operating flow rate (m³·s-1), H is the total head (m), and η is the system efficiency.

[0042] The head in head composition refers to the total energy height (head) that the dredging pump must overcome, and consists of static head, head loss, and velocity head. In dredging systems, [static head + head loss] is primarily considered. In other words, head composition is a component that constitutes the total energy requirement necessary for the dredging pump to move sediment, and based on this, the power requirements and efficiency of the dredging pump can be evaluated.

[0043]

[0044] Here, H is the Total Head, which is the total head height (m) that the dredging pump must overcome. Hstatic is the static head (m), Hloss is the head loss (m), fslurry is the slurry correction friction coefficient, Lp is the pipe length (m), D is the pipe diameter (m), v is the average flow velocity (m·s⁻¹), and Ki is the local loss coefficient.

[0045] The machine learning model is trained to use the difference between the calculated Phyd and the actual Pin as the residual, and to reflect the additional resistance created by geological layers, environment, and equipment conditions—that is, the layer-specific effects.

[0046] Machine Learning Secondary Residual Correction

[0047] model Gradient Boosting (XGBoost / LightGBM) + Time Series (LSTM / Temporal CNN) ensemble used. target Predicting residuals relative to the physical values ​​of Ev or Lr. Stratigraphic embeddings Learn "layer-specific continuous correction" by inputting layer IDs as one-hot or embeddings. Multitasking Utilizing the correlation structure by simultaneously predicting (Ev,L) in a single network.

[0048] At this time, Ev is the energy consumption per unit volume, which is the energy required to transport 1 m³ of fluid (J·m-3 or Wh·m-3), and Lr is the ratio of the rated load to the actual load of the dredging equipment as described above.

[0049] Learning Pipeline

[0050] step explanation 1. Synchronization and Refinement Sensor timestamp alignment, missing data interpolation, outlier removal. 2. Labeling Fuel flow rate → Power conversion, calculate Ev and Lr, and group by layer ID 3. First-order physical calculation Calculated Phyd, H, and Hloss 4. Feature Generation Added soil, environment, and operation features + physics calculation results + historical window statistics. 5. Model Training Leakage is prevented through K-fold cross-validation and strata ID group splitting (GroupKFold). 6. Correction · Calibration Calibration by temperature / flow rate range and dock correction by fleet applied. 7. Performance Indicators Evaluated MAPE(Ev), RMSE(Lr), equilibrium error by strata, and uncertainty.

[0051] <Inference and Control>

[0052] Inference and control loops (real-time) step explanation 1 Collects operational data in real-time input (stratum ID, operating flow rate, pressure, rotational speed, environment, etc.). 2 Phyd first-order estimation based on physics 3 Ev and Lr are calculated by correcting residuals using a machine learning model. 4 The controller (PLC / VFD) adjusts Q, n, and α under the minEv constraint (refer to Equation 3). 5 Results are stored and accumulated in the training data for periodic retraining.

[0053]

[0054] In other words, it is possible to adjust the flow rate Q, the dredging pump rotational speed n, and the valve opening α while minimizing energy consumption. Here, Qmin is the minimum transport flow rate and Lrmax is the maximum allowable load factor.

[0055] The control unit (330) can optimize and control the operating speed, operating angle, and operating flow rate of the dredging equipment according to the energy consumption and work load of each layer using an optimization algorithm. The operating speed, operating angle, and operating flow rate can be optimized using Q, n, and α derived from Equation 3, where n controls the operating speed, α controls the operating angle, and Q controls the operating flow rate. That is, n controls the operating speed by controlling the frequency of the VFD, and α controls the operating angle in real time by controlling the valve and cylinder opening.

[0056] n: Dredging pump rotation speed → Operating speed control Concept: The rotational speed n of a dredging pump is the impeller's rotational speed and is the most critical control variable, directly proportional to the flow rate Q and head H. In other words, increasing n increases the flow velocity, while decreasing n reduces energy consumption and wear. Control method item explanation control device Inverter (VFD, Variable Frequency Drive) or PWM-based motor drive Control principles The rotational speed is controlled by adjusting the frequency or amplitude of the power supplied to the dredging pump motor. Formula relationship (pump similarity law) Q∝n,H∝n2,P∝n3→ If the rotation speed is reduced by 10%, energy consumption decreases by approximately 27% Control Loop Configuration PLC (Modbus) ↔ VFD ↔ Motor ↔ RPM Sensor (Feedback) Real-time rotational speed adjustment via PID control or MPC AI integration If the Ev and Lr calculated by the prediction unit (320) are high → the control unit (330) transmits a frequency reduction command to the VFD to ↓n↓ organize n controls the operating speed of the pump impeller, cutter head, bucket chain, etc. by adjusting the motor rotational speed (frequency).

[0057] α: Valve opening → Operating angle control Concept: The variable α actually plays two roles: ① Flow Control Valve → Control of pump discharge flow ② Actuator for mechanical arm or cutter head tilt adjustment → Control of actual working angle ▶ That is, even if α is expressed as "valve opening" in the formula, physically it extends to operating angle control. Control method item Valve control Angle control (arm, cutter, suction pipe) Drive device Electric Actuated Valve or Hydraulic Servo Valve Hydraulic cylinder, linear actuator, servo motor control signal PLC → 420 mA or PWM → Valve Open / Closed Rate (%) Control PLC → Servo valve flow control → Cylinder stroke change Sensor feedback Potentiometer, position encoder IMU (Inertial Measurement Unit), angle sensor (Gyro / Encoder) Apply formula Control of valve flow rate according to opening angle αv Control of cutter / suction pipe entry depth and direction according to working angle αa AI control logic - Valve opening reduced (flow limit) when Ev is excessive - Cutter head angle αa automatically adjusted if ground resistance is high Maintaining optimal cutting angles for each soil type using feedback control (MPC / RL)

[0058] α is an abstract value representing a continuous control variable of machine operation, and it is assumed that in actual hardware, it can be concretized as the flow rate opening angle in the case of a valve, or as the working angle in the case of an arm or pipe. Also, since Q has already been derived as the flow rate, it can be used as the flow rate of the operating flow rate.

[0059] The safety accident prediction unit (340) can collect behavioral data of workers in the work area and input the behavioral data into a prediction model to predict the likelihood of safety accidents occurring to the workers. Predicting the likelihood of safety accidents using worker behavioral data means AI safety analysis that recognizes [changes in behavioral patterns] as danger signals, rather than simply observing the location of the workers. Since dredgers have many risk factors (mooring ropes, pumps, buckets, etc.), the movement, posture, and speed of the workers can be quantified to identify accident signatures and predict the risk of accidents, thereby giving warnings or stopping the dredger's operation.

[0060] Worker behavior data (input data) Data types Collection method / sensor example Location and movement data RTLS (UWB·GPS·BLE Tag) or CCTV-based object tracking Distance, speed, and frequency of a worker approaching the "snapback hazard zone" Posture and behavior data Vision-based Pose Estimation (e.g., YOLOv8 + PoseNet, OpenPose) Bending over, lifting heavy objects, repeating dangerous postures biosignal data Wearable (heart rate, body temperature, stress indicator HRV) Increased fatigue, overheating Voice / gesture data Microphone · IMU · Camera Screaming, asking for help, gestures of non-compliance with safety rules Work tool usage patterns IoT Tool Tag, Current Sensor Failure to wear safety equipment, use of unexpected tools

[0061] Feature extraction and labeling 1. Extraction of behavioral sequences Calculate time series coordinates (xt,yt,zt), joint angles, velocities, and motion vectors. 2. Pattern Labeling Labeled as normal work, caution work, and hazardous work (e.g., approaching snapback zones, moving at excessive speeds, abnormal posture). 3. Calculation of Fatigue and Attention Index Calculate fatigue score using HRV and heart rate variability. 4. Combine with environmental and location data Simultaneous input of mooring line tension, mechanical vibration, noise, etc.

[0062] Prediction model structure step model role Step 1 CNN + LSTM / Transformer Recognizing behavioral patterns from video frames or pose keypoint time series Step 2 Anomaly Detection (Isolation Forest / Autoencoder) Detection of abnormal movement compared to normal behavior Step 3 Risk Prediction Model (XGBoost / Logistic Regression) Calculate the probability of an accident P(accident) using input features Step 4 Reinforcement Learning (Optional) Strengthening real-time warning policies for high-risk behaviors

[0063] At this time, the probability of an accident occurring P(accident) can be defined as f(x1,x2,...,xn), where xi represents behavioral characteristics (posture, movement speed, zone approach distance, fatigue, vibration, etc.).

[0064] The eco-friendly department (350) can perform energy optimization control to optimize the fuel efficiency and carbon emissions of the dredger according to the energy consumption and work load of each layer. Fuel efficiency and carbon emission optimization is a process in which artificial intelligence (AI) adjusts the operating conditions of the dredger's pumps, propellers, generators, etc., in real time to maintain the same amount of work while using less fuel. In other words, energy optimization control is performed by considering all operating flow rates, pump speeds, tension, and soil conditions.

[0065] The objective of energy optimization control is to [minimize fuel consumption (F) and carbon emissions (C) while maintaining the same soil transport volume (Q)].

[0066]

[0067] At this time, n is the rotational speed of the dredging pump as described above, v is the flow velocity in the pipe, α is the valve opening, F is the fuel consumption rate function, C is the carbon emission amount function, Qmin is the minimum transport flow rate, Trope is the mooring rope tension (the mooring rope will be described later in the mooring rope safety management section (370)), Tsafe is the safety tension limit, and w1 and w2 are weighting factors (importance of fuel vs. emission ratio).

[0068] In other words, the structure is designed to simultaneously achieve [improved fuel efficiency + reduced carbon emissions + ensured work safety] by having artificial intelligence (AI) analyze work data, such as real-time data (operating flow rate, soil type, tension, engine load, etc.), find a combination that satisfies Equation 4, and automatically adjust the pump speed, valve opening, and winch tension. To find a combination that satisfies Equation 4, optimization algorithms such as MILP (Mixed Integer Linear Programming) or QP (Quadratic Programming) can be used, but are not limited to these.

[0069] The carbon emission tracking unit (360) can calculate the amount of carbon emissions reduced by energy optimization control in real time and link it with a carbon emission trading exchange. It can calculate the amount of fuel saved by energy optimization control in real time and convert that value into a carbon emission factor of the fuel to calculate the amount of carbon emissions (carbon reduction). That is, for the amount of fuel saved ΔF, it is calculated as ΔCO2 = ΔF × EF, where EF is the carbon emission factor for each fuel (e.g., diesel 2.68 kgCO₂ / L). The carbon reduction calculated in this way is accumulated in real time and automatically linked with a carbon emission trading exchange, and is used for generating or trading emission credits. At this time, the real-time fuel reduction can be calculated by accumulating the difference between the fuel consumption predicted in the standard operating state and the fuel consumption measured by the actual sensor over time.

[0070] The mooring rope safety management department (370) collects the tension, angle, vibration, and temperature of the mooring rope of the dredger using a mooring rope sensor, predicts mooring rope tension fluctuations based on ground data and environmental data, calculates the snapback risk, performs tension control and length adjustment of the mooring rope based on the tension fluctuation prediction results and the snapback risk, and can automatically issue a work stop order. A mooring rope refers to a thick rope used to tie a ship to a certain place, and is mainly made of materials such as nylon or PVC. This rope serves to keep the ship fixed to a dock in a port or to stay in a designated position, but if this mooring rope comes loose, breaks, or springs away, it can cause not only damage to the dredger but also casualties, leading to a major accident. Accordingly, it is necessary to check how the tension of the mooring rope is fluctuating and whether there is a possibility of a snapback, a phenomenon in which the taut rope springs back rapidly like a whip due to elasticity when the tensioned rope or wire (mooring rope) breaks.

[0071] To this end, mooring data is collected from mooring sensors, tension fluctuations are predicted, and the snapback risk is calculated. Then, control is performed, for example, by following the process shown in Table 12 below.

[0072] step Process name Key Activities Input / Output tool or model Step 1 Data Collection Real-time collection of tension, angle, vibration, and temperature data from mooring cable sensors. - Input: Sensor signals (load cell, IMU, acceleration, temperature sensor) - Output: Time series data (tension, angle, vibration, temperature) Load Cell, IMU (Inertial Measurement Unit), Accelerometer, Thermocouple / RTD, OPC-UA, MQTT, Edge Gateway, InfluxDB Step 2 Data Preprocessing and Fusion It performs noise removal, time synchronization, and unit conversion on the collected signals, and matches them with environmental data (wave height, flow velocity, wind speed) and ground data (soil resistance, water depth, etc.). - Input: Sensor time series data + Environmental / ground data - Output: Fusion feature set Python (Pandas, NumPy), Kalman Filter, Time-series Synchronization, Feature Engineering Pipeline Step 3 Tension fluctuation prediction Short-term prediction of tension (ΔTrope(t+1)) according to ground and environmental conditions was performed using an LSTM / GRU-based time series prediction model. - Input: Tension, angle, and vibration time series, environmental / ground data - Output: Predicted tension curve (ΔTrope_pred) TensorFlow, PyTorch (LSTM / GRU), Scikit-learn, MLflow, ONNX Runtime Step 4 Snapback Risk Calculation The snapback risk is calculated using predicted tension fluctuations, tension limit ratios, angle change rates, vibration acceleration, etc. - Input: ΔTrope_pred, θ rate of change, aRMS(oscillation) - Output: Risk score R_snap(0~1) Anomaly Detection (Autoencoder, Isolation Forest), Risk Index Model (Weighted Sum), PyTorch / Python Step 5 Generation of control commands If the snapback risk level exceeds a threshold, the winch control module issues a tension release command, automatic length adjustment (reel-in / reel-out), and a stop operation command if necessary. -Input: R_snap, ΔTrope_pred -Output: control_command(CMD_tension, CMD_length, CMD_stop) PLC (Modbus TCP / IP), ROS2 Control Node, MATLAB Simulink MPC, Pyomo MILP Solver Step 6 Feedback and learning Actual results (changes in tension, occurrence of accidents) are recorded and utilized as data for retraining the prediction model. - Input: Actual tension log, prediction result - Output: Updated parameters and feedback log InfluxDB, PostgreSQL, MLflow Tracking, Grafana Dashboard

[0073]

[0074] The snapback risk can be calculated as shown in Equation 5, where Rsnap is the snapback risk (0 to 1), Trope is the current tension (N), Tsafe is the allowable tension limit (N), △Trope is the change in tension (N), △θ is the rate of change in angle (rad / s), aRMS is the vibration acceleration (RMS value, m / s²), and w1 to w4 are weighting factors (values ​​learned from the risk model). It can also be set so that a stop operation command is automatically issued if Rsnap is 0.8 or higher.

[0075] In summary, ① the mooring rope status is collected using a mooring rope sensor, ② tension fluctuations are predicted by combining them with environmental and ground data, ③ the snapback risk is calculated, and ④ tension relief, length adjustment, and work stoppage can be automatically performed.

[0076] The safety monitoring unit (380) can monitor the snapback risk zone, which is an area where the snapback risk level exceeds a preset threshold, via video and check whether a worker is approaching the snapback risk zone. The snapback risk zone (Geofence) can be configured to generate an alarm if the union of [current mooring rope shape and the trajectory of bouncing back when broken] is calculated as a real-time polygon and overlaps with the worker's RTLS (Real-Time Location System) location. That is, it is a structure that creates a [bouncing path] using tension, angle, rate of change, and elastic energy, and determines whether the polygon created by buffering that path in real-time overlaps with the RTLS to trigger an alarm and control. To this end, a gentle carnetary curve is used when creating the mooring rope shape, and the bouncing trajectory can be generated by modeling or simulating [elastic energy stored in the rope → initial velocity at the moment of breakage → motion under air resistance and gravity].

[0077] In this way, when a trajectory is generated, a snapback danger zone drawing is created, and the trajectory skin obtained by sweeping the entire range of broken positions is projected onto the deck plane to determine the [no entry area] painting area and shape, and a danger sign can be placed on workers attempting to enter this area.

[0078] For detailed information on the trajectory of the mooring rope, refer to the paper (Keane, Ray, Ben Poulter, Andrew Diehl, and Choon Wong. “Snapback Characterisation for Arresting Structure Design: Physical Testing Insights.” Paper presented at the PIANC APAC Conference 2024, Sydney, Australia, August 27–30, 2024.).

[0079] The mode automatic switching unit (390) can model the optimal operating speed, operating angle, and operating flow rate of the dredging equipment according to ground data by learning, verifying, and testing them as an operating model, and can automatically switch the operating mode of the dredging equipment based on ground data. The operating mode may include, for example, Soft mode, Medium mode, Hard Ground mode, etc., but is not limited thereto. In order to automatically switch the operating mode in this way, LightGBM or RandomForest can be used as a classification model or regression model, and a GIS-based soil database can be used.

[0080] Hereinafter, the operation process according to the configuration of the integrated control server of FIG. 2 described above will be explained in detail with reference to FIG. 3 and FIG. 4. However, it is obvious that the embodiment is merely one of the various embodiments of the present invention and is not limited thereto.

[0081] Referring to FIG. 3a, (a) the integrated control server (300) collects work data from the sensor module (400) and inputs it into a prediction model as in (b) to predict energy consumption and work load by layer. Then, (c) based on this, the integrated control server (300) can optimize the operation of the dredger and (d) control the dredger to operate accordingly. In addition, the integrated control server (300) can predict and warn of safety accidents using worker behavior data to prevent safety accidents as in (a) of FIG. 3b, optimize operation to lower carbon emissions and increase fuel efficiency for eco-friendly operation as in (b), and perform mooring rope safety management as in (c), adjust the tension of the mooring rope, or create a danger zone to prevent workers from entering.

[0082] The applicant is currently operating a business as shown in FIGS. 4a to 4f and is preparing a system according to one embodiment of the present invention.

[0083] As for the details regarding the method of providing an ESG management-based management solution shown in Figures 2 to 4 that are not described, they are identical to or can be easily inferred from the details described above regarding the method of providing an ESG management-based management solution shown in Figure 1, so further explanation will be omitted.

[0084] FIG. 5 is a diagram illustrating the process of transmitting and receiving data between each component included in the ESG management-based dredger eco-friendly and work safety management system of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described through FIG. 5, but the present invention is not to be interpreted as being limited to such an embodiment, and it is obvious to those skilled in the art that the process of transmitting and receiving data illustrated in FIG. 5 may be changed according to various embodiments described above.

[0085] Referring to FIG. 5, the integrated control server collects work data from the sensor module (S5100) and inputs the work data into a pre-established prediction model to predict energy consumption and work load by layer (S5200).

[0086] In addition, the integrated control server controls the operating speed, operating angle, and operating flow rate of the dredging equipment by optimizing them according to the energy consumption and work load of each layer using an optimization algorithm (S5300).

[0087] The order of the steps described above (S5100~S5300) is merely an example and is not limited thereto. That is, the order of the steps described above (S5100~S5300) may vary, and some of these steps may be executed simultaneously or deleted.

[0088] As for the details regarding the method of providing an ESG management-based management solution of Fig. 5 that are not described, they are identical to or can be easily inferred from the details described above regarding the method of providing an ESG management-based management solution through Figs. 1 to 4, so further explanation will be omitted.

[0089] A method for providing an ESG management-based management solution according to one embodiment described through FIG. 5 may also be implemented in the form of a recording medium containing computer-executable instructions, such as an application or program module executed by a computer. A computer-readable medium may be any available medium accessible by a computer and includes both volatile and non-volatile media, as well as removable and non-removable media. Additionally, a computer-readable medium may include all computer storage media. Computer storage media include both volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0090] The method for providing an ESG management-based management solution according to one embodiment of the present invention described above may be executed by an application basically installed on a terminal (which may include a program included in a platform or operating system, etc., basically installed on the terminal), or by an application (i.e., a program) directly installed by a user on a master terminal through an application providing server, such as an application store server, an application, or a web server related to the service. In this sense, the method for providing an ESG management-based management solution according to one embodiment of the present invention described above may be implemented as an application (i.e., a program) that is basically installed on a terminal or directly installed by a user, and may be recorded on a computer-readable recording medium such as a terminal.

[0091] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0092] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

Claims

Claim 1 A sensor module that collects work data in real time, including ground data, environmental data, and status data of dredging equipment within the work area where the dredger is working; The integrated control server comprises: a collection unit that collects work data from the sensor module; a prediction unit that inputs the work data into a pre-established prediction model to predict energy consumption and work load by layer; and a control unit that optimizes and controls the operating speed, operating angle, and operating flow rate of the dredging equipment using an optimization algorithm according to the energy consumption and work load by layer; wherein the integrated control server includes: a safety accident prediction unit that collects behavioral data of a worker in the work area and inputs the behavioral data into the prediction model to predict the possibility of safety accidents occurring to the worker; an eco-friendly unit that performs energy optimization control to optimize the fuel efficiency and carbon emissions of the dredger according to the energy consumption and work load by layer; a carbon emission tracking unit that calculates the carbon emissions saved by the energy optimization control in real time and links it with a carbon emission trading exchange; and a unit that collects the tension, angle, vibration, and temperature of the mooring rope of the dredger using a mooring rope sensor and predicts mooring rope tension fluctuations according to the ground data and environmental data. Subsequently, a mooring rope safety management unit that calculates the snapback risk level, performs tension control and length adjustment of the mooring rope based on the tension fluctuation prediction results and the snapback risk level, and automatically issues a work stop order; a safety monitoring unit that monitors the snapback risk zone, which is an area where the snapback risk level exceeds a preset threshold, via video and checks whether a worker is approaching the snapback risk zone; and a mode automatic switching unit that models the optimal operating speed, operating angle, and operating flow rate of the dredging equipment according to the ground data by learning, verifying, and testing the operating model, and automatically switches the operating mode of the dredging equipment based on the ground data.An ESG management-based dredger eco-friendly and work safety management system characterized by including Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 delete Claim 7 delete

Images