Automatic measurement monitoring system for ship loading

Abstract

The present application relates to the field of navigation technology and ship engineering, and discloses a kind of ship loading automatic measurement monitoring system, comprising: monitoring network construction module, for configuring the multimodal sensor array of ship, and constructs the distributed intelligent monitoring network of ship;Loading state data fusion module, for after collecting the multidimensional loading state data of ship, data fusion is carried out, and fusion loading state data is generated;Loading state analysis module, for mapping fusion loading state data to parameterized three-dimensional model, to calculate the stability parameter of ship under current loading condition, shear bending moment distribution and damage stability margin, determine the loading state of ship;Risk early warning module, for analyzing the change of loading state of ship in subsequent loading process, to determine the risk early warning mechanism and loading parameter optimization scheme of ship;Intelligent monitoring execution module, for executing the automatic measurement monitoring of ship loading.The present application can improve the real-time and accuracy of ship loading monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of navigation technology and ship engineering, and particularly relates to a ship loading automatic measurement monitoring system. BACKGROUND

[0002] Ship loading automatic measurement monitoring refers to a series of technologies and methods that use automation technology and equipment to measure and monitor the ship loading process in real time and accurately, so as to ensure the safety, efficiency and compliance of ship loading. Ship loading automatic measurement monitoring can improve measurement accuracy and efficiency, enhance safety, reduce risks caused by human factors, and realize intelligent management of the ship loading process.

[0003] Traditional ship loading measurement methods mainly use rulers, sounding hammers and simple inclinometers for measurement. These methods are easily affected by environmental factors during measurement, and cannot monitor the loading state in real time and continuously, resulting in limited measurement data accuracy and poor real-time performance during ship loading, which leads to high risks and low safety in subsequent loading and transportation. SUMMARY

[0004] The present application provides a ship loading automatic measurement monitoring system, which aims to improve the real-time performance and accuracy of ship loading monitoring.

[0005] To achieve the above purpose, the present application provides a ship loading automatic measurement monitoring system, which comprises:

[0006] The monitoring network construction module is configured to configure a multi-modal sensor array of the ship, and construct a distributed intelligent monitoring network of the ship based on the multi-modal sensor array.

[0007] The loading state data fusion module is configured to collect multi-dimensional loading state data of the ship based on the distributed intelligent monitoring network, perform spatio-temporal alignment on the multi-dimensional loading state data to obtain aligned multi-dimensional data, extract a multi-dimensional feature vector of the aligned multi-dimensional data, perform data fusion on the aligned multi-dimensional data based on the multi-dimensional feature vector, and obtain fused loading state data.

[0008] The loading state analysis module is configured to fit a parameterized three-dimensional model of the ship, map the fused loading state data to the parameterized three-dimensional model, calculate the stability parameters, shear moment distribution and damage stability margin of the ship under the current loading condition, and determine the loading state of the ship according to the stability parameters, shear moment distribution and damage stability margin.

[0009] The risk warning module is configured to analyze a change in the loading state of the ship in a subsequent loading process based on the loading state, identify an abnormal factor of the change in the loading state, calculate a safety coefficient of the ship in the loading process according to the abnormal factor, determine a risk warning mechanism and a loading parameter optimization scheme of the ship based on the safety coefficient, and execute automatic measurement monitoring of the loading of the ship based on the risk warning mechanism and the loading parameter optimization scheme.

[0010] The intelligent monitoring execution module is configured to execute automatic measurement monitoring of the loading of the ship based on the risk warning mechanism and the loading parameter optimization scheme.

[0011] Optionally, the distributed intelligent monitoring network of the ship is constructed based on the multi-modal sensor array, including:

[0012] Determining a sensor hardware circuit and embedded software of a sensor in the multi-modal sensor array;

[0013] Identifying an application scenario of the sensor, and determining a protection device of the sensor based on the application scenario;

[0014] Integrating the sensor hardware circuit and the embedded software into the protection device to obtain a sensor node;

[0015] Constructing network communication and network protocols of the sensor node, and configuring a network device of the sensor node based on the network communication and the network protocols;

[0016] Determining network parameters and network wiring of the network device;

[0017] Determining a network topology structure of the sensor node according to the network parameters and the network wiring;

[0018] Constructing the distributed intelligent monitoring network of the ship according to the network topology structure.

[0019] Optionally, the spatio-temporal alignment of the multi-dimensional loading state data includes:

[0020] Data cleaning of the multi-dimensional loading state data to obtain cleaned multi-dimensional data;

[0021] Uniformly determining a timestamp of the cleaned multi-dimensional data;

[0022] Time synchronization of the cleaned multi-dimensional data based on the timestamp to obtain synchronized multi-dimensional data;

[0023] Constructing a spatial coordinate system of the synchronized multi-dimensional data, and extracting a location feature of the synchronized multi-dimensional data;

[0024] According to the position feature, a spatial position corresponding to a data point in the synchronous multi-dimensional data is determined;

[0025] According to the spatial position, the synchronous multi-dimensional data is mapped into the spatial coordinate system to obtain aligned multi-dimensional data.

[0026] Optionally, the aligned multi-dimensional data is subjected to data fusion based on the multi-dimensional feature vectors to obtain fused loading state data, including:

[0027] The feature correlation between the multi-dimensional feature vectors is analyzed;

[0028] According to the feature correlation, the multi-dimensional feature vectors are grouped to obtain multiple groups of feature vectors;

[0029] The feature weights of the multiple groups of feature vectors are determined;

[0030] Based on the feature weights, the multiple groups of feature vectors are spliced to obtain a high-dimensional feature vector;

[0031] The high-dimensional feature vector is subjected to dimension reduction processing to obtain a reduced-dimensional feature vector;

[0032] According to the reduced-dimensional feature vector, the aligned multi-dimensional data is subjected to data fusion to obtain fused loading state data.

[0033] Optionally, the parameterized three-dimensional model of the ship is fitted, including:

[0034] Design drawings of the ship are obtained, wherein the design drawings include a general arrangement drawing, a lines drawing, and a structure drawing;

[0035] Key parameters of the design drawings are extracted, and a global coordinate system of the ship is constructed;

[0036] A mapping relationship between the global coordinate system and the key parameters is determined;

[0037] Based on the mapping relationship, the key parameters are mapped into the global coordinate system to construct a ship geometric model of the ship;

[0038] Detailed features of the ship are extracted, and the ship geometric model is optimized according to the detailed features to obtain a parameterized three-dimensional model.

[0039] Optionally, the fused loading state data is mapped onto the parameterized three-dimensional model to calculate a stability parameter, a shear bending moment distribution, and a damage stability margin of the ship under a current loading working condition, including:

[0040] The parameterized three-dimensional model is divided into multiple sub-three-dimensional models;

[0041] determine a sub-model gravity center height and a sub-model weight of the plurality of sub three-dimensional models according to the fusion loading state data;

[0042] determine a transverse metacentre, a ship baseline and a ship roll angle of the parameterized three-dimensional model, and calculate a transverse metacentre to baseline height of the transverse metacentre and the ship baseline;

[0043] calculate a displacement of the parameterized three-dimensional model based on the fusion loading state data;

[0044] calculate a righting lever of the parameterized three-dimensional model according to the ship roll angle, the displacement, the transverse metacentre to baseline height, the sub-model gravity center height and the sub-model weight;

[0045] determine a static righting lever of the parameterized three-dimensional model based on the displacement and the ship roll angle;

[0046] determine a stability parameter of the ship under the current loading condition according to the static righting lever and the righting lever;

[0047] calculate a static load distribution and a dynamic load distribution of the parameterized three-dimensional model according to the fusion loading state data;

[0048] calculate a total bending moment of the parameterized three-dimensional model according to the static load distribution and the dynamic load distribution;

[0049] determine a shear bending moment distribution of the ship under the current loading condition according to the total bending moment;

[0050] simulate a damage scenario of the parameterized three-dimensional model;

[0051] extract a flooded compartment parameter in the fusion loading state data based on the damage scenario;

[0052] calculate a damage stability of the parameterized three-dimensional model according to the flooded compartment parameter;

[0053] analyze a damage stability margin of the ship under the current loading condition according to the damage stability.

[0054] Optionally, the calculating the dynamic load distribution of the parameterized three-dimensional model according to the fusion loading state data comprises:

[0055] determine a wave component received by the parameterized three-dimensional model based on the fusion loading state data;

[0056] identify a wave number, an amplitude, an angular frequency and an initial phase of the wave component;

[0057] Calculate the ship baseline corresponding to the parametric 3D model and the water depth direction coordinates corresponding to the water surface of the parametric 3D model;

[0058] The dynamic load distribution of the parameterized three-dimensional model is calculated based on the water depth coordinates, the wave number, the amplitude, the angular frequency, and the initial phase.

[0059] Optionally, calculating the safety factor of the vessel during loading based on the anomaly factor includes:

[0060] Obtain the safety standard parameters of the vessel during the loading process;

[0061] The abnormal factors are quantified to obtain abnormal factor values;

[0062] Based on the aforementioned anomaly factor values, the stability and structural strength changes of the vessel during the loading process are calculated.

[0063] The current loading status of the vessel is determined based on the stability changes and structural strength changes.

[0064] The safety factor of the vessel is calculated based on the current loading status and the safety standard parameters.

[0065] Optionally, determining the risk warning mechanism and loading parameter optimization scheme for the ship based on the safety factor includes:

[0066] Based on the safety factor, the risk warning level of the vessel is determined;

[0067] Determine the risk level threshold for the aforementioned risk warning level;

[0068] Based on the safety factor and the risk level threshold, determine the risk warning triggering conditions and the warning information transmission method for the vessel;

[0069] The risk warning mechanism of the vessel is determined based on the risk warning triggering conditions and the warning information transmission method.

[0070] Collect early warning information from the risk warning mechanism, and determine risk response measures for the vessel based on the early warning information;

[0071] Analyze the effectiveness of the risk mitigation measures, and based on the effectiveness, determine an optimization scheme for the vessel's loading parameters.

[0072] An automatic measurement and monitoring method for ship loading, characterized in that the method includes:

[0073] Configure a multimodal sensor array for the ship, and construct a distributed intelligent monitoring network for the ship based on the multimodal sensor array;

[0074] Based on the distributed intelligent monitoring network, multi-dimensional loading status data of the ship is collected, the multi-dimensional loading status data is spatiotemporally aligned to obtain aligned multi-dimensional data, multi-dimensional feature vectors of the aligned multi-dimensional data are extracted, and data fusion is performed on the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data.

[0075] Fit the parametric three-dimensional model of the ship, map the fused loading state data onto the parametric three-dimensional model, and calculate the stability parameters, shear moment distribution and damage stability margin of the ship under the current loading condition. Based on the stability parameters, shear moment distribution and damage stability margin, determine the loading state of the ship.

[0076] Based on the loading status, the changes in the loading status of the vessel during the subsequent loading process are analyzed, abnormal factors of the loading status changes are identified, and the safety factor of the vessel during the loading process is calculated based on the abnormal factors. Based on the safety factor, the risk warning mechanism and loading parameter optimization scheme of the vessel are determined.

[0077] Based on the aforementioned risk warning mechanism and the aforementioned loading parameter optimization scheme, the automatic measurement and monitoring of the ship's loading is performed.

[0078] This invention, through the construction of a distributed intelligent monitoring network for the ship based on the multimodal sensor array, enables real-time data acquisition and transmission, ensuring real-time monitoring of the ship's status and providing a massive, real-time data foundation for ship intelligence and automation. Optionally, this invention, by fusing the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data, can compensate for the deficiencies of a single data source, improving data integrity and reliability. This invention, by mapping the fused loading status data onto the parametric three-dimensional model to calculate the ship's stability parameters, shear moment distribution, and damage stability margin under the current loading condition, can accurately calculate the ship's stability parameters and damage stability margin under various loading conditions, helping to assess the ship's safety and ensuring its navigation safety under different sea states and loading conditions. This invention, by determining the ship's stability parameters, shear moment distribution, and damage stability margin based on the stability parameters, shear moment distribution, and damage stability margin, can further enhance the ship's safety. By precisely calculating and monitoring the distribution of shear force and bending moment under loading conditions, this invention ensures that the ship's structure will not exceed its design strength limit under any loading and sea state, preventing capsizing, structural damage, or even sinking during normal navigation or in the event of a breach. In this embodiment, based on the safety factor, a risk warning mechanism and loading parameter optimization scheme for the ship can be determined to promptly detect deteriorating trends in the ship's safety status. When the safety factor falls below a preset threshold, the system can trigger a warning signal, alerting crew and shore-based management personnel to potential risks, while simultaneously optimizing the loading scheme to ensure the ship meets safety standards under various loading conditions. Finally, by executing automatic loading measurement and monitoring based on the risk warning mechanism and loading parameter optimization scheme, this invention can precisely optimize loading, find better loading schemes, improve the ship's cargo capacity or navigation efficiency, and effectively prevent accidents caused by improper loading (such as capsizing or structural damage), protecting the lives of personnel and the safety of ship property. Therefore, this invention improves the real-time performance and accuracy of ship loading monitoring. Attached Figure Description

[0079] Figure 1 This is a functional block diagram of an automatic measurement and monitoring system for ship loading provided in an embodiment of the present invention;

[0080] Figure 2 This is a flowchart illustrating an automatic measurement and monitoring method for ship loading according to an embodiment of the present invention.

[0081] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0082] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0083] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0084] In practice, the server-side equipment deployed in a ship loading automatic measurement and monitoring system may consist of one or more devices. This system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node, providing automatic measurement and monitoring services for ship loading to various users. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage various users. Or, it can be implemented as a server composed of numerous identical or different types of hardware devices, with one or more devices configured to provide automatic measurement and monitoring services for ship loading to various users.

[0085] In terms of implementation, the ship loading automatic measurement and monitoring system and the user terminal are mutually compatible. That is, if the ship loading automatic measurement and monitoring system is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the ship loading automatic measurement and monitoring system is implemented as a website, then the user terminal is implemented as a webpage; or if the ship loading automatic measurement and monitoring system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0086] Reference Figure 1 The diagram shown is a functional block diagram of an automatic measurement and monitoring system for ship loading provided in an embodiment of the present invention.

[0087] The ship loading automatic measurement and monitoring system 100 described in this invention can be set up in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a server for ship loading automatic measurement and monitoring, a server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the ship loading automatic measurement and monitoring system 100 includes a monitoring network construction module 101, a loading status data fusion module 102, a loading status analysis module 103, a risk early warning module 104, and an intelligent monitoring execution module 105.

[0088] In this embodiment of the invention, in the tracking based on automatic measurement and monitoring of ship loading, each of the above modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the automatic measurement and monitoring system for ship loading provided by this embodiment of the invention, without modifying the program code, the applicable scope of the automatic measurement and monitoring architecture for ship loading can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the automatic measurement and monitoring system for ship loading. In practical applications, the above modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0089] The following describes the components and specific workflow of the ship loading automatic measurement and monitoring system, using specific embodiments as examples.

[0090] The monitoring network construction module 101 is used to configure the ship's multimodal sensor array and, based on the multimodal sensor array, construct the ship's distributed intelligent monitoring network.

[0091] This invention significantly enhances a ship's monitoring capabilities by configuring a multimodal sensor array, enabling more comprehensive, accurate, and real-time state perception. The multimodal sensor array refers to an array that organically combines and integrates various types and functions of sensors to achieve synchronous and comprehensive perception of multiple ship state parameters.

[0092] Optionally, the ship's multimodal sensor array can be configured using artificial intelligence (AI) and machine learning algorithms, such as determining the ship's specific structure and navigation environment, selecting the most suitable sensor type based on the specific structure and navigation environment using the AI ​​and machine learning algorithms, optimizing the sensor layout of the multimodal sensors corresponding to the sensor type, and determining the ship's multimodal sensor array based on the sensor layout.

[0093] This invention, through the construction of a distributed intelligent monitoring network for the ship based on the multimodal sensor array, enables real-time data acquisition and transmission, ensuring real-time monitoring of the ship's status and providing a massive, real-time data foundation for ship intelligence and automation. The distributed intelligent monitoring network refers to a network composed of multiple intelligent nodes distributed at various key locations on the ship. These nodes collect data through the multimodal sensor array and utilize network communication technology to achieve data exchange, processing, and sharing, thereby realizing a system for real-time, comprehensive, and collaborative monitoring of the ship's status.

[0094] As an embodiment of the present invention, the construction of the distributed intelligent monitoring network for the ship based on the multimodal sensor array includes:

[0095] Determine the sensor hardware circuitry and embedded software of the sensors in the multimodal sensor array;

[0096] Identify the application scenarios of the sensor, and based on the application scenarios, determine the protective devices for the sensor;

[0097] The sensor hardware circuit and the embedded software are integrated into the protection device to obtain a sensor node;

[0098] Establish the network communication and network protocol for the sensor node, and configure the network devices of the sensor node based on the network communication and network protocol;

[0099] Determine the network parameters and network cabling of the network devices;

[0100] The network topology of the sensor node is determined based on the network parameters and the network wiring.

[0101] Based on the network topology, a distributed intelligent monitoring network for the ship is constructed.

[0102] The sensor hardware circuit refers to the electronic circuit system used to realize the functions of sensor signal detection, processing, conversion, transmission, and control, such as signal conditioning circuits, power management circuits, and microcontroller circuits. The embedded software refers to the software program embedded in the hardware device (such as a microcontroller, DSP, FPGA, etc.) to control the hardware device and realize specific functions, such as driver programs, data acquisition programs, and communication programs. The application scenario refers to the application of the sensor to solve specific environmental problems in ship operation and maintenance, such as temperature, humidity, and corrosive environments. The protective equipment refers to the physical protection device used to protect the sensor node from harsh environmental conditions, ensuring its reliable, stable, and safe operation. The sensor node refers to an independent functional unit that integrates the sensor hardware circuit, embedded software, and necessary protective equipment. The network communication refers to the process of data exchange and command transmission between sensor nodes and between sensor nodes and the central server. The network protocol refers to the rules used to realize data exchange and command transmission between sensor nodes and between sensor nodes and the central server. The network equipment refers to various hardware devices used to build and maintain network infrastructure and realize data exchange and command transmission between sensor nodes and between sensor nodes and the central server, such as network switches, routers, and gateways. The network parameters refer to various parameters used to describe and configure network devices, communication protocols, and network performance, such as IP address, gateway address, and bandwidth. Network cabling refers to the process of connecting network devices (such as sensors, controllers, switches, and routers) through physical media (such as cables and optical fibers) to achieve data transmission and communication. Network topology refers to the connection methods and layout of various nodes (such as sensors, controllers, switches, and routers) in the network.

[0103] Optionally, the network communication and network protocol of the sensor node can be constructed using network function virtualization technology. For example, the network functions required by the sensor node can be analyzed, and the network functions can be virtualized using network function virtualization technology to obtain virtual network functions. Based on the virtual network functions, the virtual network of the sensor node can be configured, and the network communication and network protocol of the sensor node can be determined based on the virtual network.

[0104] Optionally, the network cabling of the network device can be determined using optical network technology, such as optical switching technology, wavelength division multiplexing technology, etc.

[0105] The loading status data fusion module 102 is used to collect multi-dimensional loading status data of the ship based on the distributed intelligent monitoring network, perform spatiotemporal alignment on the multi-dimensional loading status data to obtain aligned multi-dimensional data, extract multi-dimensional feature vectors from the aligned multi-dimensional data, and perform data fusion on the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data.

[0106] This invention, through the distributed intelligent monitoring network, collects multi-dimensional loading status data of the vessel in real time, providing data support for subsequent data processing and analysis. The multi-dimensional loading status data refers to a collection of various types of data describing and reflecting the vessel's loading status from multiple dimensions and aspects, such as weight data, spatial data, image and video data, and vessel status data.

[0107] This invention, through spatiotemporal alignment of the multi-dimensional loading status data, obtains aligned multi-dimensional data. This ensures that data from different sources and of different types are integrated within a unified temporal and spatial framework, eliminating spatiotemporal differences between data and resulting in better consistency and comparability. Specifically, the aligned multi-dimensional data refers to the data set obtained by integrating and synchronizing multi-dimensional loading status data from different sensors, systems, or time points according to a unified temporal and spatial reference framework.

[0108] As an embodiment of the present invention, the step of performing spatiotemporal alignment on the multi-dimensional loading state data to obtain aligned multi-dimensional data includes:

[0109] The multi-dimensional loading status data is cleaned to obtain cleaned multi-dimensional data;

[0110] The timestamps of the cleaned multi-dimensional data are uniformly determined;

[0111] Based on the timestamp, the cleaned multi-dimensional data is synchronized in time to obtain synchronized multi-dimensional data;

[0112] Construct a spatial coordinate system for the synchronized multi-dimensional data, and extract the positional features of the synchronized multi-dimensional data;

[0113] Based on the location features, determine the spatial location of the data point in the synchronized multi-dimensional data;

[0114] Based on the spatial location, the synchronized multi-dimensional data is mapped to the spatial coordinate system to obtain aligned multi-dimensional data.

[0115] The term "cleaned multi-dimensional data" refers to the process of removing noise, errors, and inconsistencies from the collected raw multi-dimensional loading status data. The "timestamp" refers to a digital marker used to mark the time of sensor data acquisition. The "synchronized multi-dimensional data" refers to multiple data sets from different sensor nodes, of different types, and with different acquisition frequencies, but related to the same point in time or time period, which, after timestamp alignment, can collectively describe a certain aspect of the ship's status. The "spatial coordinate system" refers to a reference system used to describe and locate the spatial relationships of various sensor nodes, equipment, and cargo within or around the ship. The "positional features" refer to the attributes and parameters used to describe and distinguish the positional information of various objects within or around the ship in the spatial coordinate system. The "spatial position" refers to the specific location point occupied by an object (such as a sensor node, equipment, or cargo) within or around the ship.

[0116] Optionally, the synchronized multi-dimensional data can be obtained by time synchronization through interpolation methods, such as linear interpolation, spline interpolation, etc.

[0117] Optionally, the aligned multi-dimensional data can be obtained by spatial alignment using spatial interpolation methods, such as Kriging interpolation, inverse distance weighted interpolation, etc.

[0118] This invention, through the extraction of multi-dimensional feature vectors from the aligned multi-dimensional data, can transform the original multi-source heterogeneous data into a more easily understood and manipulated format, laying the foundation for subsequent data fusion. The multi-dimensional feature vectors refer to a set of multiple feature indicators extracted from the aligned multi-dimensional loading status data, capable of characterizing key features and attributes of the ship's loading status.

[0119] Optionally, the multi-dimensional feature vectors of the aligned multi-dimensional data can be extracted using dimensionality reduction techniques, such as principal component analysis, t-distributed random neighborhood embedding, etc.

[0120] This invention, through data fusion of aligned multi-dimensional data based on the multi-dimensional feature vectors, yields fused loading status data. This fused loading status data can compensate for the shortcomings of a single data source, improving data integrity and reliability. Specifically, the fused loading status data refers to a comprehensive dataset with a larger amount of information formed by integrating and combining information from multiple dimensions and sources.

[0121] As an embodiment of the present invention, the step of performing data fusion on the aligned multi-dimensional data based on the multi-dimensional feature vector to obtain fused loading status data includes:

[0122] Analyze the feature correlations among the multi-dimensional feature vectors;

[0123] Based on the aforementioned feature correlation, the multi-dimensional feature vectors are grouped to obtain multiple sets of feature vectors;

[0124] Determine the feature weights of the multiple sets of feature vectors;

[0125] Based on the feature weights, the multiple sets of feature vectors are concatenated to obtain a high-dimensional feature vector;

[0126] The high-dimensional feature vector is reduced in dimensionality to obtain a reduced-dimensional feature vector;

[0127] Based on the reduced-dimensional feature vector, the aligned multi-dimensional data is fused to obtain fused loading status data.

[0128] The feature correlation refers to the degree of linear or non-linear association between different features. The multiple sets of feature vectors refer to the groups into which the original multi-dimensional feature vectors are divided based on the feature correlation analysis results. The feature weight is a numerical value assigned to each set of feature vectors to represent the relative importance of that set of feature vectors in the final data fusion process. The high-dimensional feature vector refers to the feature vectors of the original sets of feature vectors directly connected (stacked) according to their weights. The dimensionality-reduced feature vector refers to the new feature vector obtained after dimensionality reduction processing of the high-dimensional feature vectors.

[0129] Optionally, the feature correlation between the multi-dimensional feature vectors can be analyzed by causal inference, such as constructing a causal model of the multi-dimensional feature vectors, analyzing the causal relationship between the multi-dimensional feature vectors based on the causal model, and determining the feature correlation between the multi-dimensional feature vectors according to the causal relationship.

[0130] The loading status analysis module 103 is used to fit the parametric three-dimensional model of the ship, map the fused loading status data onto the parametric three-dimensional model, calculate the stability parameters, shear moment distribution and damage stability margin of the ship under the current loading condition, and determine the loading status of the ship based on the stability parameters, shear moment distribution and damage stability margin.

[0131] This invention, through fitting a parametric 3D model of the ship, can accurately represent the ship's geometry and structure, and intuitively display the ship's overall structure and details. The parametric 3D model refers to a 3D model constructed using parametric technology that can accurately represent the ship's geometry and structure.

[0132] As an embodiment of the present invention, fitting the parametric three-dimensional model of the ship includes:

[0133] Obtain the design drawings of the vessel, wherein the design drawings include: general arrangement drawing, lines drawing and structural drawing;

[0134] Extract key parameters from the design drawings and construct the global coordinate system of the ship;

[0135] Determine the mapping relationship between the global coordinate system and the key parameters;

[0136] Based on the mapping relationship, the key parameters are mapped to the global coordinate system to construct the ship's geometric model;

[0137] The ship's detailed features are extracted, and the ship's geometric model is optimized based on these features to obtain a parametric 3D model.

[0138] The design drawings refer to drawings used to define the detailed specifications and arrangement of the ship's shape, structure, systems, and equipment. The general arrangement drawing is a drawing that details the overall layout of the ship and the spatial relationships between its various parts. The lines drawing is a drawing that details the ship's external outline and main dimensions. The structural drawing is a drawing that details the ship's structural composition and component arrangement. The key parameters refer to design parameters that are crucial to the ship's performance, safety, and structural integrity. The global coordinate system is a reference system that defines the ship's geometry and spatial relationships. The mapping relationship refers to the method of associating key parameters on the design drawings with their positions and orientations in the global coordinate system. The ship's geometric model is a three-dimensional digital representation that accurately describes the ship's shape, structure, compartment layout, and the geometric features of various systems and equipment. The detailed features refer to the precise shape, size, position, and interrelationships of the specific parts or components that constitute the ship's geometric model.

[0139] Optionally, the key parameters of the design drawings can be extracted using image recognition and processing technologies, such as optical character recognition, edge detection, and contour extraction.

[0140] Optionally, the mapping relationship between the global coordinate system and the key parameters can be determined by parametric modeling and optimization, such as the least squares method, Bayesian method, etc.

[0141] This invention, through mapping the fused loading state data onto the parameterized three-dimensional model, calculates the ship's stability parameters, shear moment distribution, and damage stability margin under the current loading condition. This allows for accurate calculation of the ship's stability parameters and damage stability margin under various loading conditions, aiding in the assessment of ship safety and ensuring safe navigation under different sea states and loading conditions. The parameters describing the ship's ability to maintain upright buoyancy under various loading and operating conditions include initial metacentric height and center of gravity height. The distribution of shear force and bending moment generated within the hull structure under external loads (such as cargo, waves, and wind) is also included. Finally, the ship's stability capability after encountering damage leading to flooding of compartments is also assessed.

[0142] As an embodiment of the present invention, mapping the fused loading state data onto the parameterized three-dimensional model to calculate the ship's stability parameters, shear moment distribution, and damage stability margin under the current loading condition includes:

[0143] The parametric 3D model is divided into multiple sub-3D models;

[0144] Based on the fused loading status data, determine the sub-model center of gravity height and sub-model weight of the multiple sub-3D models;

[0145] Determine the transverse metacenter, ship baseline, and ship roll angle of the parametric 3D model, and calculate the height of the transverse metacenter from the baseline and the height of the ship baseline.

[0146] Based on the fused loading status data, the displacement of the parameterized three-dimensional model is calculated;

[0147] Based on the ship's heel angle, displacement, transverse metacenter height from the baseline, sub-model center of gravity height, and sub-model weight, the stabilizing moment of the parametric 3D model is calculated using the following formula:

[0148]

[0149] Where W represents the stabilizing moment, g represents the gravitational acceleration, P represents the displacement, sin represents the sine function, θ represents the ship's heel angle, G represents the height of the transverse metacenter from the baseline, n represents the number of sub-3D models, and Z... i h represents the weight of the i-th sub-3D model. i This represents the height of the centroid of the i-th sub-3D model;

[0150] Based on the displacement and the ship's heel angle, the static stability lever arm of the parameterized three-dimensional model is determined;

[0151] Based on the static stability lever arm and the stability moment, determine the stability parameters of the ship under the current loading condition;

[0152] Based on the fused loading status data, calculate the static load distribution and dynamic load distribution of the parameterized three-dimensional model;

[0153] Based on the static load distribution and the dynamic load distribution, the total bending moment of the parameterized three-dimensional model is calculated using the following formula:

[0154]

[0155] Where U(r) represents the total bending moment of the parametric 3D model at position r, r represents the position of the parametric 3D model, J(∈) represents the static load distribution, D9ε,t) represents the dynamic load distribution at time t, ∈ represents the integral variable, and d∈ represents the integration with respect to the integral variable ∈.

[0156] Based on the total bending moment, determine the shear moment distribution of the ship under the current loading condition;

[0157] Simulate the damage scenario of the parameterized 3D model;

[0158] Based on the damage scenario, the parameters of the water-intake compartment are extracted from the fused loading status data;

[0159] Based on the parameters of the flooded compartment, the breach stability of the parameterized three-dimensional model is calculated;

[0160] Based on the aforementioned damage stability, the damage stability margin of the vessel under the current loading conditions is analyzed.

[0161] The multiple sub-3D models refer to the original, overall parametric 3D model of the ship, logically divided into several smaller, independent 3D model parts with clearly defined boundaries. The sub-model center of gravity height refers to the vertical position of the center of gravity of each sub-model. The sub-model weight refers to the weight of each sub-model. The transverse metacenter refers to the intersection of the buoyancy line and the ship's centerline when the parametric 3D model of the ship is tilted laterally. The ship's baseline refers to the waterline position of the ship under normal loading and operating conditions. The ship's heel angle refers to the angle of tilt of the parametric 3D model of the ship relative to its normal horizontal position. The height of the transverse metacenter from the baseline refers to the vertical distance from the ship's baseline to the transverse metacenter. The displacement refers to the weight of water displaced by the ship in the water. The restoring moment refers to the restoring moment generated within the parametric 3D model of the ship when it tilts due to external forces (such as wind, waves, cargo movement, etc.). The static stability arm refers to the horizontal distance between the line of action of buoyancy (a line vertically upward through the center of buoyancy) and the line of action of the center of gravity (a line vertically downward through the center of gravity) of the parametric 3D model of the ship at a certain tilt angle. The static load distribution refers to the distribution of various forces acting on the parametric 3D model of the ship in a static or equilibrium state. The dynamic load distribution refers to the distribution of forces generated by various dynamic factors during navigation or operation of the parametric 3D model of the ship. The total bending moment refers to the vector sum of all bending moments acting on the hull structure. The damage scenario refers to the description and analysis of various situations after the ship suffers damage (such as collision, grounding, explosion, etc.). The flooded compartment parameters refer to key parameters describing the flooding of internal compartments after damage, such as compartment location, compartment space type, and compartment size. Damaged stability refers to the ship's ability to maintain sufficient stability and buoyancy to avoid sinking or capsizing even when damage occurs, resulting in flooding of one or more compartments.

[0162] Optionally, the displacement of the parametric 3D model can be determined by identifying the draft of the parametric 3D model, determining the underwater volume of the model based on the draft, and calculating the displacement of the parametric 3D model based on the underwater volume.

[0163] Optionally, the static stability arm of the parametric three-dimensional model can be determined by determining the transverse metacentric radius of the parametric three-dimensional model based on the displacement, determining the transverse metacentric height of the parametric three-dimensional model based on the transverse metacentric radius, and determining the static stability arm of the parametric three-dimensional model based on the transverse metacentric height and the ship's heel angle.

[0164] Optionally, calculating the dynamic load distribution of the parameterized 3D model based on the fused loading state data includes:

[0165] Based on the fused loading state data, the wave components experienced by the parameterized three-dimensional model are determined;

[0166] Identify the wave number, amplitude, angular frequency, and initial phase of the wave components;

[0167] Calculate the ship baseline corresponding to the parametric 3D model and the water depth direction coordinates corresponding to the water surface of the parametric 3D model;

[0168] Based on the water depth coordinates, wave number, amplitude, angular frequency, and initial phase, the dynamic load distribution of the parameterized three-dimensional model is calculated using the following formula:

[0169]

[0170] Where D(r,t) represents the dynamic load distribution of the parametric 3D model at position r and time t, f j Let N represent the amplitude of the j-th wave component, e represent the exponential function with base e, and N j Let d represent the wave number of the j-th wave component, d represent the water depth coordinate, cos represent the cosine function, r represent the position of the parametric 3D model, and s represent the position of the wave component. j b represents the angular frequency of the j-th wave component. j Let t represent the initial phase of the j-th wave component, and t represent the time.

[0171] The wave component refers to the individual simple waves that make up a complex ocean wave. The wave number refers to the number of cycles of a wave component per unit distance. The amplitude refers to the maximum distance a wave deviates from its equilibrium position. The angular frequency refers to the angular velocity of the wave, i.e., the change in the wave's phase per unit time. The phase of the wave at its initial moment determines the wave's temporal offset. The water depth coordinate refers to the distance from the ship's baseline to the water surface in the vertical direction.

[0172] Optionally, the wave components can be determined using machine learning algorithms, such as neural networks, support vector machines, etc.

[0173] This invention, through the determination of the ship's loading state based on the stability parameters, shear moment distribution, and damage stability margin, can ensure that the ship's structure will not exceed its design strength limit under any loading and sea state by accurately calculating and monitoring the distribution of shear force and bending moment. This prevents capsizing, structural damage, or even sinking during normal navigation or in the event of a damage accident. The loading state refers to the sum of the weight and distribution of various components carried by the ship at a specific moment, including cargo, passengers, fuel, fresh water, and ballast water.

[0174] Optionally, the loading status of the ship can be determined using dynamic statistical algorithms, such as Kalman filtering or particle filtering.

[0175] The risk warning module 104 is used to analyze the changes in the loading status of the vessel during the subsequent loading process based on the loading status, identify abnormal factors of the changes in the loading status, calculate the safety factor of the vessel during the loading process based on the abnormal factors, and determine the risk warning mechanism and loading parameter optimization scheme of the vessel based on the safety factor.

[0176] This invention, by analyzing changes in the loading state of the vessel during subsequent loading processes based on the loading state, can identify risk factors that may lead to insufficient stability, structural overload, or failure to meet stability requirements due to hull damage. Specifically, changes in loading state refer to alterations in the overall mass and mass distribution of the vessel during loading, resulting in changes to a series of vessel performance parameters and safety indicators.

[0177] Optionally, the changes in the loading state of the vessel during the subsequent loading process can be analyzed by simulating the subsequent loading process of the vessel, calculating the vessel's stability parameters based on the subsequent loading process, and analyzing the changes in the vessel's loading state during the subsequent loading process based on the stability parameters.

[0178] This invention, through identifying abnormal factors in the changes of the loading status, can provide early warnings of potential safety risks, thereby enabling corresponding measures to be taken to avoid serious accidents such as capsizing and structural damage to the vessel. These abnormal factors refer to those that occur during the loading process, causing a decline in the vessel's safety performance or exceeding the safe operating range, and that do not meet expectations or regulatory requirements.

[0179] Optionally, the abnormal factors of the loading status change can be identified using digital twin technology. For example, a digital twin model of the ship can be constructed using digital twin technology, the ship's performance under different loading statuses can be simulated using the digital twin model, and the abnormal factors of the loading status change can be identified based on the ship's performance.

[0180] This invention, through calculation of the ship's safety factor during loading based on the aforementioned anomaly factors, can intuitively reflect the degree to which the ship deviates from the safety boundary under the current loading state, and accurately pinpoint the main factors leading to safety risks. The safety factor refers to the factor used to quantify the ship's safety level under a specific loading condition.

[0181] As an embodiment of the present invention, calculating the safety factor of the ship during the loading process based on the anomaly factor includes:

[0182] Obtain the safety standard parameters of the vessel during the loading process;

[0183] The abnormal factors are quantified to obtain abnormal factor values;

[0184] Based on the aforementioned anomaly factor values, the stability and structural strength changes of the vessel during the loading process are calculated.

[0185] The current loading status of the vessel is determined based on the stability changes and structural strength changes.

[0186] The safety factor of the vessel is calculated based on the current loading status and the safety standard parameters.

[0187] The safety standard parameters refer to pre-set, quantified indicators or thresholds used to assess whether a ship meets safety requirements under various loading conditions. The anomaly factor values ​​refer to a set of correction coefficients used to analyze various abnormal or non-ideal situations. Stability change refers to the phenomenon where the ship's stability parameters change during loading due to the loading, unloading, or movement of cargo, ballast water, fuel oil, fresh water, etc. Structural strength change refers to the phenomenon where the stress and deformation of the hull structure change during loading due to the loading, unloading, or movement of cargo, ballast water, fuel oil, fresh water, etc. The current loading state refers to the ship's loading status at a specific moment, including the distribution and quantity of all loads on board.

[0188] Optionally, the stability changes and structural strength changes of the ship during loading can be calculated using a hybrid computational method that integrates machine learning and finite element analysis.

[0189] This invention, through its risk warning mechanism and loading parameter optimization scheme based on the safety factor, can promptly detect deteriorating trends in the ship's safety status. When the safety factor falls below a preset threshold, the system can trigger a warning signal, alerting crew and shore-based management personnel to potential risks. Simultaneously, it optimizes the loading scheme to ensure the ship meets safety standards under various loading conditions. The risk warning mechanism refers to a complete system based on real-time monitoring data, safety standards, and preset thresholds for identifying, assessing, warning of, and handling potential risks during ship operation. The loading parameter optimization scheme refers to a set of specific measures and strategies for adjusting and optimizing various loading parameters to improve the ship's safety, economy, and environmental friendliness.

[0190] As an embodiment of the present invention, determining the risk warning mechanism and loading parameter optimization scheme of the ship based on the safety factor includes:

[0191] Based on the safety factor, the risk warning level of the vessel is determined;

[0192] Determine the risk level threshold for the aforementioned risk warning level;

[0193] Based on the safety factor and the risk level threshold, determine the risk warning triggering conditions and the warning information transmission method for the vessel;

[0194] The risk warning mechanism of the vessel is determined based on the risk warning triggering conditions and the warning information transmission method.

[0195] Collect early warning information from the risk warning mechanism, and determine risk response measures for the vessel based on the early warning information;

[0196] Analyze the effectiveness of the risk mitigation measures, and based on the effectiveness, determine an optimization scheme for the vessel's loading parameters.

[0197] The risk warning level refers to the classification of a ship's current safety status and potential risks based on its safety coefficient, such as low risk, medium risk, and high risk. The risk level threshold refers to the specific numerical limit of the safety coefficient used to classify different risk warning levels; for example, a low-risk threshold is set to a safety coefficient greater than 1.2, and a medium-risk threshold is a safety coefficient between 1 and 1.2. The risk warning triggering condition refers to the specific conditions under which a corresponding level of risk warning should be triggered when one or more parameters reach or exceed a preset threshold. The warning information transmission method refers to the way and means of transmitting warning information to relevant personnel or systems when the risk warning triggering condition is met, such as light and sound warnings, voice broadcasts, etc. The warning information refers to the information generated when the ship's safety coefficient is lower than the preset risk warning triggering condition, containing key data and indications, such as abnormal factors and abnormal locations, used to notify relevant personnel of the potential risks the ship faces. The risk response measures refer to a series of pre-defined, targeted actions and measures taken to reduce or eliminate potential risks and ensure ship safety after a risk warning is triggered. The response effect refers to the actual impact and outcome on the ship's safety status and potential risks after the implementation of risk response measures.

[0198] Optionally, the risk response measures for the vessel can be implemented by constructing a risk response measures database for the vessel and matching the risk response measures in the database with the early warning information.

[0199] Optionally, the effectiveness of the risk response measures can be analyzed using digital twin technology. For example, the risk response measures can be simulated using digital twin technology to obtain simulation results, and the effectiveness of the risk response measures can be analyzed based on the simulation results.

[0200] The intelligent monitoring execution module 105 is used to perform automatic measurement and monitoring of the ship's loading based on the risk warning mechanism and the loading parameter optimization scheme.

[0201] This invention, through its implementation of the risk warning mechanism and loading parameter optimization scheme, enables precise loading optimization by performing automatic measurement and monitoring of the ship's loading. This leads to finding a better loading scheme, improving the ship's cargo carrying capacity or navigation efficiency, and effectively preventing accidents caused by improper loading (such as capsizing or structural damage), thus ensuring the safety of personnel and ship property.

[0202] This invention, through the construction of a distributed intelligent monitoring network for the ship based on the multimodal sensor array, enables real-time data acquisition and transmission, ensuring real-time monitoring of the ship's status and providing a massive, real-time data foundation for ship intelligence and automation. Optionally, this invention, by fusing the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data, can compensate for the deficiencies of a single data source, improving data integrity and reliability. This invention, by mapping the fused loading status data onto the parametric three-dimensional model to calculate the ship's stability parameters, shear moment distribution, and damage stability margin under the current loading condition, can accurately calculate the ship's stability parameters and damage stability margin under various loading conditions, helping to assess the ship's safety and ensuring its navigation safety under different sea states and loading conditions. This invention, by determining the ship's stability parameters, shear moment distribution, and damage stability margin based on the stability parameters, shear moment distribution, and damage stability margin, can further enhance the ship's safety. By precisely calculating and monitoring the distribution of shear force and bending moment under loading conditions, this invention ensures that the ship's structure will not exceed its design strength limit under any loading and sea state, preventing capsizing, structural damage, or even sinking during normal navigation or in the event of a breach. In this embodiment, based on the safety factor, a risk warning mechanism and loading parameter optimization scheme for the ship can be determined to promptly detect deteriorating trends in the ship's safety status. When the safety factor falls below a preset threshold, the system can trigger a warning signal, alerting crew and shore-based management personnel to potential risks, while simultaneously optimizing the loading scheme to ensure the ship meets safety standards under various loading conditions. Finally, by executing automatic loading measurement and monitoring based on the risk warning mechanism and loading parameter optimization scheme, this invention can precisely optimize loading, find better loading schemes, improve the ship's cargo capacity or navigation efficiency, and effectively prevent accidents caused by improper loading (such as capsizing or structural damage), protecting the lives of personnel and the safety of ship property. Therefore, this invention can improve the real-time performance and accuracy of ship loading monitoring.

[0203] like Figure 2The diagram shown is a flowchart illustrating an automatic measurement and monitoring method for ship loading according to an embodiment of the present invention. In this embodiment, the automatic measurement and monitoring method for ship loading includes:

[0204] Configure a multimodal sensor array for the ship, and construct a distributed intelligent monitoring network for the ship based on the multimodal sensor array;

[0205] Based on the distributed intelligent monitoring network, multi-dimensional loading status data of the ship is collected, the multi-dimensional loading status data is spatiotemporally aligned to obtain aligned multi-dimensional data, multi-dimensional feature vectors of the aligned multi-dimensional data are extracted, and data fusion is performed on the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data.

[0206] Fit the parametric three-dimensional model of the ship, map the fused loading state data onto the parametric three-dimensional model, and calculate the stability parameters, shear moment distribution and damage stability margin of the ship under the current loading condition. Based on the stability parameters, shear moment distribution and damage stability margin, determine the loading state of the ship.

[0207] Based on the loading status, the changes in the loading status of the vessel during the subsequent loading process are analyzed, abnormal factors of the loading status changes are identified, and the safety factor of the vessel during the loading process is calculated based on the abnormal factors. Based on the safety factor, the risk warning mechanism and loading parameter optimization scheme of the vessel are determined.

[0208] Based on the aforementioned risk warning mechanism and the aforementioned loading parameter optimization scheme, the automatic measurement and monitoring of the ship's loading is performed.

[0209] In the several embodiments provided by this invention, it should be understood that the provided systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0210] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0211] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An automatic measurement and monitoring system for ship loading, characterized in that, The system includes: A monitoring network construction module is used to configure the ship's multimodal sensor array and, based on the multimodal sensor array, construct the ship's distributed intelligent monitoring network. The loading status data fusion module is used to collect multi-dimensional loading status data of the ship based on the distributed intelligent monitoring network, perform spatiotemporal alignment on the multi-dimensional loading status data to obtain aligned multi-dimensional data, extract multi-dimensional feature vectors from the aligned multi-dimensional data, and perform data fusion on the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data. The loading status analysis module is used to fit the parametric three-dimensional model of the ship, map the fused loading status data onto the parametric three-dimensional model, calculate the stability parameters, shear moment distribution and damage stability margin of the ship under the current loading conditions, and determine the loading status of the ship based on the stability parameters, shear moment distribution and damage stability margin. The risk warning module is used to analyze the changes in the loading status of the vessel during the subsequent loading process based on the loading status, identify abnormal factors of the changes in the loading status, calculate the safety factor of the vessel during the loading process based on the abnormal factors, and determine the risk warning mechanism and loading parameter optimization scheme of the vessel based on the safety factor. The intelligent monitoring and execution module is used to perform automatic measurement and monitoring of the ship's loading based on the risk warning mechanism and the loading parameter optimization scheme.

2. The automatic measurement and monitoring system for ship loading as described in claim 1, characterized in that, The construction of the distributed intelligent monitoring network for the ship based on the multimodal sensor array includes: Determine the sensor hardware circuitry and embedded software of the sensors in the multimodal sensor array; Identify the application scenarios of the sensor, and based on the application scenarios, determine the protective devices for the sensor; The sensor hardware circuit and the embedded software are integrated into the protection device to obtain a sensor node; Establish the network communication and network protocol for the sensor node, and configure the network devices of the sensor node based on the network communication and network protocol; Determine the network parameters and network cabling of the network devices; The network topology of the sensor node is determined based on the network parameters and the network wiring. Based on the network topology, a distributed intelligent monitoring network for the ship is constructed.

3. The automatic measurement and monitoring system for ship loading as described in claim 1, characterized in that, The process of performing spatiotemporal alignment on the multi-dimensional loading state data to obtain aligned multi-dimensional data includes: The multi-dimensional loading status data is cleaned to obtain cleaned multi-dimensional data; The timestamps of the cleaned multi-dimensional data are uniformly determined; Based on the timestamp, the cleaned multi-dimensional data is synchronized in time to obtain synchronized multi-dimensional data; A spatial coordinate system for the synchronized multi-dimensional data is constructed, and the positional features of the synchronized multi-dimensional data are extracted. The spatial coordinate system refers to a reference system used to describe and locate the spatial positional relationships of various sensor nodes, equipment, and cargo inside or around the ship. Based on the positional features, the spatial position corresponding to the data points in the synchronized multi-dimensional data is determined. Based on the spatial location, the synchronized multi-dimensional data is mapped to the spatial coordinate system to obtain aligned multi-dimensional data.

4. The automatic measurement and monitoring system for ship loading as described in claim 1, characterized in that, The process of fusing the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data includes: Analyze the feature correlations among the multi-dimensional feature vectors; Based on the aforementioned feature correlation, the multi-dimensional feature vectors are grouped to obtain multiple sets of feature vectors; Determine the feature weights of the multiple sets of feature vectors; Based on the feature weights, the multiple sets of feature vectors are concatenated to obtain a high-dimensional feature vector; The high-dimensional feature vector is reduced in dimensionality to obtain a reduced-dimensional feature vector; Based on the reduced-dimensional feature vector, the aligned multi-dimensional data is fused to obtain fused loading status data.

5. The automatic measurement and monitoring system for ship loading as described in claim 1, characterized in that, The fitting of the parametric three-dimensional model of the ship includes: Obtain the design drawings of the vessel, wherein the design drawings include: general arrangement drawing, lines drawing and structural drawing; Key parameters of the design drawings are extracted to construct the global coordinate system of the ship; the global coordinate system refers to the reference system that defines the ship's geometry and spatial relationships. Determine the mapping relationship between the global coordinate system and the key parameters; Based on the mapping relationship, the key parameters are mapped to the global coordinate system to construct the ship's geometric model; The ship's detailed features are extracted, and the ship's geometric model is optimized based on these features to obtain a parametric 3D model.

6. The automatic measurement and monitoring system for ship loading as described in claim 1, characterized in that, The process of mapping the fused loading state data onto the parameterized three-dimensional model to calculate the ship's stability parameters, shear moment distribution, and damage stability margin under the current loading condition includes: The parametric 3D model is divided into multiple sub-3D models; Based on the fused loading status data, determine the sub-model center of gravity height and sub-model weight of the multiple sub-3D models; Determine the transverse metacenter, ship baseline, and ship roll angle of the parametric 3D model, and calculate the height of the transverse metacenter from the baseline and the height of the ship baseline. Based on the fused loading status data, the displacement of the parameterized three-dimensional model is calculated; The stabilizing moment of the parametric 3D model is calculated based on the ship's heel angle, displacement, transverse metacenter height from baseline, sub-model center of gravity height, and sub-model weight. Based on the displacement and the ship's heel angle, the static stability lever arm of the parameterized three-dimensional model is determined; Based on the static stability lever arm and the stability moment, determine the stability parameters of the ship under the current loading condition; Based on the fused loading status data, calculate the static load distribution and dynamic load distribution of the parameterized three-dimensional model; Calculate the total bending moment of the parameterized three-dimensional model based on the static load distribution and the dynamic load distribution; Based on the total bending moment, determine the shear moment distribution of the ship under the current loading condition; Simulate the damage scenario of the parameterized 3D model; Based on the damage scenario, the parameters of the water-intake compartment are extracted from the fused loading status data; Based on the parameters of the flooded compartment, the breach stability of the parameterized three-dimensional model is calculated; Based on the aforementioned damage stability, the damage stability margin of the vessel under the current loading conditions is analyzed.

7. The automatic measurement and monitoring system for ship loading as described in claim 6, characterized in that, The step of calculating the dynamic load distribution of the parameterized 3D model based on the fused loading state data includes: Based on the fused loading state data, the wave components experienced by the parameterized three-dimensional model are determined; Identify the wave number, amplitude, angular frequency, and initial phase of the wave components; Calculate the ship baseline corresponding to the parametric 3D model and the water depth direction coordinates corresponding to the water surface of the parametric 3D model; The dynamic load distribution of the parameterized three-dimensional model is calculated based on the water depth coordinates, the wave number, the amplitude, the angular frequency, and the initial phase.

8. The automatic measurement and monitoring system for ship loading as described in claim 7, characterized in that, The calculation of the ship's safety factor during loading based on the anomaly factor includes: Obtain the safety standard parameters of the vessel during the loading process; The abnormal factors are quantified to obtain abnormal factor values; Based on the aforementioned anomaly factor values, the stability and structural strength changes of the vessel during the loading process are calculated. The current loading status of the vessel is determined based on the stability changes and structural strength changes. The safety factor of the vessel is calculated based on the current loading status and the safety standard parameters.

9. The automatic measurement and monitoring system for ship loading as described in claim 1, characterized in that, The process of determining the ship's risk warning mechanism and loading parameter optimization scheme based on the safety factor includes: Based on the safety factor, the risk warning level of the vessel is determined; Determine the risk level threshold for the aforementioned risk warning level; Based on the safety factor and the risk level threshold, determine the risk warning triggering conditions and the warning information transmission method for the vessel; The risk warning mechanism of the vessel is determined based on the risk warning triggering conditions and the warning information transmission method. Collect early warning information from the risk warning mechanism, and determine risk response measures for the vessel based on the early warning information; Analyze the effectiveness of the risk mitigation measures, and based on the effectiveness, determine an optimization scheme for the vessel's loading parameters.

10. An automatic measurement and monitoring method for ship loading, characterized in that, The method includes: Configure a multimodal sensor array for the ship, and construct a distributed intelligent monitoring network for the ship based on the multimodal sensor array; Based on the distributed intelligent monitoring network, multi-dimensional loading status data of the ship is collected, the multi-dimensional loading status data is spatiotemporally aligned to obtain aligned multi-dimensional data, multi-dimensional feature vectors of the aligned multi-dimensional data are extracted, and data fusion is performed on the aligned multi-dimensional data based on the multi-dimensional feature vectors to obtain fused loading status data. Fit the parametric three-dimensional model of the ship, map the fused loading state data onto the parametric three-dimensional model, and calculate the stability parameters, shear moment distribution and damage stability margin of the ship under the current loading condition. Based on the stability parameters, shear moment distribution and damage stability margin, determine the loading state of the ship. Based on the loading status, the changes in the loading status of the vessel during the subsequent loading process are analyzed, abnormal factors of the loading status changes are identified, and the safety factor of the vessel during the loading process is calculated based on the abnormal factors. Based on the safety factor, the risk warning mechanism and loading parameter optimization scheme of the vessel are determined. Based on the aforementioned risk warning mechanism and the aforementioned loading parameter optimization scheme, the automatic measurement and monitoring of the ship's loading is performed.

Images