Ship cabin volume measurement method and system based on digital twinning

Abstract

The invention discloses a ship cabin volume measurement method and system based on digital twinning, relates to the field of ship cabin volume measurement and monitoring, and is suitable for liquid cargo ship cabin volume measurement and monitoring. Point cloud data of a cabin main body, an additional structure and a deduction structure are obtained through scanning, a digital twin ship cabin capacity system is established, and a ship cabin capacity table and a heeling correction table are obtained through calculation of a cabin capacity calculation model and input into the digital twin ship cabin capacity system. The cabin capacity information can be corrected in combination with the ship cabin capacity table and the heeling correction table, the cabin capacity information is displayed in real time, automatic calibration of the cabin capacity information is achieved, and the ship cabin capacity measurement efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of ship tank volume measurement and monitoring, and in particular to a ship tank volume measurement method and system based on digital twin, which is suitable for tank volume measurement and monitoring of liquid cargo ships. Background Art

[0002] The LNG market is experiencing explosive growth, with growing demand for LNG equipment, such as LNG carriers and LNG bunker vessels, both domestically and internationally. Tank capacity is a crucial indicator for LNG vessels. Upon ship delivery and cargo delivery, tank capacity is often the most important economic indicator for shipowners. This metric is particularly crucial for vessels in service, and accurate and effective measurement of tank capacity is crucial for shipowners' core interests. Precise measurement of this metric can also determine key indicators such as a vessel's range and capacity, providing reliable and effective performance data for future deployment. Furthermore, real-time monitoring and early warning of tank capacity during navigation significantly enhances safety and reliability. Summary of the Invention

[0003] The present invention mainly addresses the problem that the existing technology for measuring the volume of a ship's hold is low in efficiency and inaccurate, relies on manual experience and has high labor intensity, making it difficult to measure the volume of a ship's hold.

[0004] The technical solution adopted in the present invention is: The present invention provides a method for measuring the volume of a ship's hold based on digital twins, comprising the following steps: Using a laser scanner to scan and obtain three-dimensional point cloud data of the ship's cabin body, additional structures, and subtracted structures, obtaining real-time stress data collected by sensors in the cabin, correcting the point cloud data based on the real-time stress data, and optimizing the point cloud data; Performing surface fitting based on the point cloud data to establish a digital twin ship capacity system, and calculating a ship capacity table and a heel and roll correction table using a capacity calculation model and inputting them into the digital twin ship capacity system; The digital twin ship capacity system collects physical tank temperature, liquid level information, and tilt angle change information, corrects the tank capacity information in combination with the ship tank capacity table and the roll and inclination correction table, and displays the tank capacity information in real time.

[0005] Furthermore, the acquiring of real-time stress data collected by sensors in the cabin and the correction of point cloud data according to the real-time stress data include: Setting an infrared thermal imager to acquire temperature data, setting stress sensors to be deployed in a grid topology to form a strain sensing network, and acquiring stress data through the strain sensing network; The stress sensor position is matched with the corresponding position of the point cloud data to align the stress data with the point cloud data, the displacement caused by the stress is calculated, and the point cloud data is compensated for thermal expansion according to the temperature data to correct the point cloud data.

[0006] Furthermore, matching the position of the stress sensor with the corresponding position of the point cloud data to align the stress data with the point cloud data, calculating the displacement caused by the stress, and performing thermal expansion compensation on the point cloud data according to the temperature data to correct the point cloud data includes: pass , Correcting the point cloud data; in, is the mechanical deformation at the stress sensor location, is the stress value at the stress sensor location, E is the Poisson’s ratio of the material, is the thermal expansion deformation at the stress sensor location, is the coefficient of thermal expansion, is the change in temperature relative to the reference value, and A vector displacement of the stress sensor position is synthesized, the discrete displacement vector is interpolated onto the point cloud, and the displacement is decomposed into unit direction vectors to correct the point cloud data.

[0007] Furthermore, the point cloud data optimization processing includes: The acquired 3D point cloud data of the ship's cabin main body, attached structures and subtracted structures are processed by removing point cloud noise, downsampling and filling defect data to obtain point cloud data of the cabin main body, attached structures and subtracted structures; The point cloud data is subjected to point cloud filtering, point cloud data splicing and point cloud registration processing, wherein the point cloud filtering adopts a bilateral filtering method, and the bilateral filtering method includes: Suppose a point in the point cloud is , for A point in the neighborhood, , the point after bilateral filtering The position is calculated as follows: ; ; ; in, is the spatial weight function, is the value weight function, is the spatial standard deviation parameter, which controls the size of the geometric neighborhood. is the attribute standard deviation parameter, which is used to control the feature similarity tolerance. It is the characteristic function of a point, including the normal vector, curvature or coordinates of the point.

[0008] Furthermore, the step of obtaining real-time stress data collected by sensors in the cabin and correcting the point cloud data according to the real-time stress data further includes: Set up the liquid level meter matrix to obtain liquid level data, and set up the pressure sensor to obtain pressure data; Deformation compensation is performed on the point cloud data according to the liquid level surface data, and pressure compensation is performed on the point cloud data according to the pressure data.

[0009] Furthermore, performing surface fitting based on the point cloud data to establish a digital twin ship cabin capacity system includes: Obtain the optimized 3D point cloud data of the ship cabin body, additional structure and subtracted structure; Performing point cloud splicing on the three-dimensional point cloud data of the ship cabin body and the additional structure to form spliced ​​point cloud data; The point cloud data are fitted using a B-spline surface fitting algorithm according to the spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure, so as to form a B-spline surface.

[0010] Furthermore, the step of fitting the point cloud data using a B-spline surface fitting algorithm based on the spliced ​​point cloud data and the three-dimensional point cloud data after the structure subtraction, wherein the fitting to form a B-spline surface comprises: The spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure are used as input point clouds, and the input point clouds are parameterized to determine node vectors, solve control points, generate surfaces, and perform error analysis to determine whether the accuracy requirements are met; If so, a B-spline surface is output; otherwise, the input point cloud is parameterized again.

[0011] Furthermore, when the point cloud data is fitted using a B-spline surface fitting algorithm based on the spliced ​​point cloud data and the three-dimensional point cloud data with the subtracted structure, a cubic B-spline curve is selected for fitting. The parameter expression of the cubic B-spline curve is as follows: ; in, 、 、 、 are any four discrete points in the plane, P(t) is the coordinate of the fitting curve, and the component form of the above formula is: ; in: , .

[0012] Furthermore, when the B-spline surface is formed by fitting, the B-spline surface is formed by constructing multiple B-spline curves in the u and v directions multiple times, where u and v are two independent parameters defined on the parameter domain, and a control grid is formed by (m+1)×(n+1) control points, and the B-spline surface is formed by fitting. The equation of the B-spline surface is: ; in is the set of control points (i=0,1…m;j=0,1…n), m is the number of control points of the surface in the u direction minus 1, n is the number of control points of the surface in the v direction minus 1, and is the B-spline surface basis function.

[0013] Furthermore, the ship tank capacity table and heel and roll correction table calculated by the tank capacity calculation model include: The tank capacity calculation model is set to calculate the tank volume using a surface reconstruction method, and the B-spline surfaces formed by the tank capacity calculation model are respectively fitted according to the spliced ​​point cloud data and the three-dimensional point cloud data with the structure subtracted are used to obtain a main capacity table and a structure subtracted capacity table with 1 cm as the minimum unit through a fitting algorithm; At room temperature of 20°C, a rolling sphere boundary with a radius of α is used to extract non-convex surfaces and generate a uniformly distributed grid. The ship tank volume result is obtained by superposition calculation and the ship tank capacity table is output, and the roll and inclination correction table is output simultaneously.

[0014] Furthermore, the digital twin ship capacity system collects physical tank temperature, liquid level information, and tilt angle change information, and corrects the tank capacity information in combination with the ship tank capacity table and the heel and roll correction table, including: Determine whether the physical cabin temperature of the ship's cabin is the room temperature of 20°C. If the cabin temperature is not 20°C, correct the cabin volume based on the temperature calibration formula. The temperature calibration formula is: ; in: is the capacity after temperature correction, in cubic meters; The capacity shown in the tank capacity table is in cubic meters; is the average temperature of the bulkhead in degrees Celsius; is the linear expansion coefficient of the cabin material, in degrees Celsius. =0.000012 / ℃.

[0015] Furthermore, the method further comprises: The system collects information about liquid level changes in ship hold tanks and constructs a CNN-LSTM (convolutional neural network-long short-term memory network) hybrid model to capture the spatiotemporal characteristics of liquid level changes. This information is then input into the LSTM model to build a time series prediction model. The final hidden layer of the LSTM model outputs leakage risk results to indicate leakage risks. The cabin stress data history is collected and a 3D-CNN model is established. The spatiotemporal information is fused through three-dimensional convolution, the association between spatial topology and spatiotemporal information sequence is retained, and the fatigue accumulation index is output to predict fatigue damage.

[0016] The present application also provides a digital twin-based ship tank volume measurement system for implementing the digital twin-based ship tank volume measurement method described above, the system comprising a multi-source data acquisition module, a core fitting algorithm module, and a digital twin application module; The multi-source data acquisition module includes a laser radar scanning unit, a radar level gauge matrix, a strain sensor network, an infrared thermal imaging unit, and a hull tilt angle measurement unit deployed on the ship's cabin, which is used to record real-time monitoring data of the physical ship cabin and share it with the core fitting algorithm module and the digital twin application module; The core fitting algorithm module is used to fuse point cloud dynamic data, perform surface fitting calculations and cabin volume calculations, and correct cabin capacity information in combination with the real-time monitoring data collected by the multi-source data acquisition module; The digital twin application module includes a visual cabin capacity dashboard, a leakage warning platform and a fatigue damage prediction platform. The visual cabin capacity dashboard is used to display the cabin capacity information in real time, the leakage warning platform is used to display leakage risk results, and the fatigue damage prediction platform is used to display the fatigue accumulation index.

[0017] The present application provides a ship tank volume measurement method and system based on digital twins. By scanning, point cloud data of the ship tank body, additional structures and subtracted structures are obtained to establish a digital twin ship tank volume system. The ship tank capacity table and the roll and inclination correction table are calculated by the tank volume calculation model and input into the digital twin ship tank volume system. The tank volume information can be corrected in combination with the ship tank capacity table and the roll and inclination correction table, and the tank volume information can be displayed in real time to realize automatic calibration of the tank volume information and improve the efficiency and accuracy of ship tank volume measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a step diagram of a method for measuring the volume of a ship's hold based on digital twins according to the present invention; Figure 2 This is a hardware structure diagram of a digital twin-based ship tank volume measurement system of the present invention; Figure 3 It is a flow chart of B-spline surface fitting in the present invention; Figure 4 It is a structural diagram of the CNN-LSTM model in the present invention; Figure 5 It is a flow chart of the method for calculating ship capacity in the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] like Figure 1 As shown, the present invention provides a method for measuring the volume of a ship cabin based on digital twins, comprising the following steps: Step S1, using a laser scanner to scan and obtain three-dimensional point cloud data of the ship cabin body, additional structures, and subtracted structures, obtain real-time stress data collected by sensors in the cabin, correct the point cloud data according to the real-time stress data, and optimize the point cloud data; Step S2, performing surface fitting based on the point cloud data to establish a digital twin ship capacity system, and calculating a ship capacity table and a heel and roll correction table using a capacity calculation model and inputting them into the digital twin ship capacity system; In step S3, the digital twin ship capacity system collects the physical tank temperature, liquid level information, and tilt angle change information, corrects the tank capacity information in combination with the ship tank capacity table and the roll and inclination correction table, and displays the tank capacity information in real time.

[0022] This application obtains point cloud data of the cabin body, additional structure and subtracted structure by scanning, establishes a digital twin ship cabin capacity system, calculates the ship cabin capacity table and roll and inclination correction table by the cabin capacity calculation model and inputs them into the digital twin ship cabin capacity system, can correct the cabin capacity information in combination with the ship cabin capacity table and the roll and inclination correction table, and display the cabin capacity information in real time, realize automatic calibration of the cabin capacity information, and improve the efficiency and accuracy of ship cabin volume measurement.

[0023] Furthermore, the acquiring of real-time stress data collected by sensors in the cabin and the correction of point cloud data according to the real-time stress data include: Setting an infrared thermal imager to acquire temperature data, setting stress sensors to be deployed in a grid topology to form a strain sensing network, and acquiring stress data through the strain sensing network; The stress sensor position is matched with the corresponding position of the point cloud data to align the stress data with the point cloud data, the displacement caused by the stress is calculated, and the point cloud data is compensated for thermal expansion according to the temperature data to correct the point cloud data.

[0024] Furthermore, matching the position of the stress sensor with the corresponding position of the point cloud data to align the stress data with the point cloud data, calculating the displacement caused by the stress, and performing thermal expansion compensation on the point cloud data according to the temperature data to correct the point cloud data includes: pass , Correcting the point cloud data; in, is the mechanical deformation at the stress sensor location, is the stress value at the stress sensor location, E is the Poisson’s ratio of the material, is the thermal expansion deformation at the stress sensor location, is the coefficient of thermal expansion, is the change in temperature relative to the reference value, and A vector displacement of the stress sensor position is synthesized, the discrete displacement vector is interpolated onto the point cloud, and the displacement is decomposed into unit direction vectors to correct the point cloud data.

[0025] Furthermore, the point cloud data optimization processing includes: The acquired 3D point cloud data of the ship's cabin main body, attached structures and subtracted structures are processed by removing point cloud noise, downsampling and filling defect data to obtain point cloud data of the cabin main body, attached structures and subtracted structures; The point cloud data is subjected to point cloud filtering, point cloud data splicing and point cloud registration processing, wherein the point cloud filtering adopts a bilateral filtering method, and the bilateral filtering method includes: Suppose a point in the point cloud is , for A point in the neighborhood, , the point after bilateral filtering The position is calculated as follows: ; ; ; in, is the spatial weight function, is the value weight function, is the spatial standard deviation parameter, which controls the size of the geometric neighborhood. is the attribute standard deviation parameter, which is used to control the feature similarity tolerance. is the characteristic function of a point, including the normal vector, curvature or coordinates of the point. Represents the point coordinates, that is .

[0026] Furthermore, the step of obtaining real-time stress data collected by sensors in the cabin and correcting the point cloud data according to the real-time stress data further includes: Set up the liquid level meter matrix to obtain liquid level data, and set up the pressure sensor to obtain pressure data; Deformation compensation is performed on the point cloud data according to the liquid level surface data, and pressure compensation is performed on the point cloud data according to the pressure data.

[0027] Among them, the deformation compensation of the point cloud data based on the liquid level surface data and the pressure compensation of the point cloud data based on the pressure data are both performed by aligning the theoretical vector displacement caused by the real-time stress corresponding to the pressure with the point cloud, that is, the deformation compensation and pressure compensation are performed simultaneously. Specifically, the deformation compensation of the point cloud data is performed based on the liquid level data and the pressure data, the liquid level height data in the cabin is collected in real time, and time synchronization verification is carried out with the pressure data. Finite element modeling is performed in the digital twin system based on the collected point cloud data in the cabin, the hydrostatic pressure distribution driven by the real-time liquid level height is calculated, and the real-time pressure of each part of the cabin is calibrated using the pressure matrix collection data. The theoretical vector displacement caused by the real-time stress is calculated, the discrete displacement vector is interpolated onto the point cloud, and the displacement is decomposed into unit direction vectors to correct the point cloud data.

[0028] like Figure 3 As shown, performing surface fitting based on the point cloud data to establish a digital twin ship cabin capacity system includes: Obtain the optimized 3D point cloud data of the ship cabin body, additional structure and subtracted structure; Performing point cloud splicing on the three-dimensional point cloud data of the ship cabin body and the additional structure to form spliced ​​point cloud data; The point cloud data are fitted using a B-spline surface fitting algorithm according to the spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure, so as to form a B-spline surface.

[0029] Furthermore, the step of fitting the point cloud data using a B-spline surface fitting algorithm based on the spliced ​​point cloud data and the three-dimensional point cloud data after the structure subtraction, wherein the fitting to form a B-spline surface comprises: The spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure are used as input point clouds, and the input point clouds are parameterized to determine node vectors, solve control points, generate surfaces, and perform error analysis to determine whether the accuracy requirements are met; If so, a B-spline surface is output; otherwise, the input point cloud is parameterized again.

[0030] Furthermore, when the point cloud data is fitted using a B-spline surface fitting algorithm based on the spliced ​​point cloud data and the three-dimensional point cloud data with the subtracted structure, a cubic B-spline curve is selected for fitting. The parameter expression of the cubic B-spline curve is as follows: ; in, 、 、 、 are any four discrete points in the plane, P(t) is the coordinate of the fitting curve, and the component form of the above formula is:

[0031] in: , .

[0032] Furthermore, when the B-spline surface is formed by fitting, the B-spline surface is formed by constructing multiple B-spline curves in the u and v directions multiple times, where u and v are two independent parameters defined on the parameter domain, and a control grid is formed by (m+1)×(n+1) control points, and the B-spline surface is formed by fitting. The equation of the B-spline surface is: ; in is the set of control points (i=0,1…m;j=0,1…n), m is the number of control points of the surface in the u direction minus 1, n is the number of control points of the surface in the v direction minus 1, and is the B-spline surface basis function.

[0033] like Figure 5 As shown, the ship tank capacity table and heel and roll correction table calculated by the tank capacity calculation model include: The tank capacity calculation model is set to calculate the tank volume using a surface reconstruction method, and the B-spline surfaces formed by the tank capacity calculation model are respectively fitted according to the spliced ​​point cloud data and the three-dimensional point cloud data with the structure subtracted are used to obtain a main capacity table and a structure subtracted capacity table with 1 cm as the minimum unit through a fitting algorithm; At room temperature of 20°C, a rolling sphere boundary with a radius of α is used to extract non-convex surfaces and generate a uniformly distributed grid. The ship tank volume result is obtained by superposition calculation and the ship tank capacity table is output, and the roll and inclination correction table is output simultaneously.

[0034] It is understood that all tank volume calculations were performed at room temperature (20°C). First, a rolling sphere with a radius of α was used to extract non-convex surfaces and generate a uniformly distributed mesh. The mesh.get_volume() function in Open3D in Python was used to calculate and output the tank volume, along with a roll and heel correction table. Subsequent tank volume corrections were performed based on the tank volume calculations at room temperature (20°C).

[0035] Furthermore, the digital twin ship capacity system collects physical tank temperature, liquid level information, and tilt angle change information, and corrects the tank capacity information in combination with the ship tank capacity table and the heel and roll correction table, including: Determine whether the physical cabin temperature of the ship's cabin is the room temperature of 20°C. If the cabin temperature is not 20°C, correct the cabin volume based on the temperature calibration formula. The temperature calibration formula is: ; in: is the capacity after temperature correction, in cubic meters; The capacity shown in the tank capacity table is in cubic meters; is the average temperature of the bulkhead in degrees Celsius; is the linear expansion coefficient of the cabin material, in degrees Celsius. =0.000012 / ℃.

[0036] Among them, the correction of the ship's cabin capacity according to the heel angle and the roll angle includes: using a radar level gauge to measure the liquid level height when the cabin is tilted at a certain angle, and the height correction value △h at the tilt is: △h = H0-H'; Wherein, H0 is the height (m) measured by the radar level gauge when the ship is in an upright state; H' is the height (m) measured by the radar level gauge when the ship is in an inclined state (including heel and roll).

[0037] The ship's tank upright volume table is a table showing the correspondence between the actual height of the liquid level and the tank volume below the liquid level when the ship is in an upright position; the ship's tank heel correction table is a table showing the correspondence between the actual height of each liquid level and the height correction value under the heel angle; the ship's roll correction table is a table showing the correspondence between the actual height of each liquid level and the height correction value under the bow and stern draft difference.

[0038] Based on the point cloud fitting results and the tank capacity calculation model, the ship's tank's upright volume table, heel correction table, and roll correction table are calculated and integrated with the digital twin ship tank capacity system. During actual navigation, the radar level gauge and various sensors collect data on the actual height of the liquid level in the tank, the heel angle, and the bow and stern draft difference. The digital twin ship tank capacity system obtains the corresponding height correction based on the correction table, and then uses the corrected height to search the upright volume table to obtain the liquid volume in the tank at that time.

[0039] like Figure 1 As shown, the method further includes: S4. Build an AI model based on the changes in the liquid level in the ship's cabin, historical stress data, and infrared thermal imaging results to provide leakage risk and fatigue damage prediction.

[0040] For details, please refer to Figure 4 , Figure 4 It is a CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory Network) hybrid model, where CNN is a convolutional neural network and LSTM is a long short-term memory network.

[0041] In other words, the method further comprises: The system collects information about liquid level changes in ship hold tanks and constructs a CNN-LSTM (convolutional neural network-long short-term memory network) hybrid model to capture the spatiotemporal characteristics of liquid level changes. This information is then input into the LSTM model to build a time series prediction model. The final hidden layer of the LSTM model outputs leakage risk results to indicate leakage risks. The cabin stress data history is collected and a 3D-CNN model is established. The spatiotemporal information is fused through three-dimensional convolution, the association between spatial topology and spatiotemporal information sequence is retained, and the fatigue accumulation index is output to predict fatigue damage.

[0042] The system collects information about the liquid level changes in the ship's hold and constructs a CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory Network) hybrid model to capture the spatiotemporal characteristics of the liquid level changes. This information is then input into the LSTM model to build a time series prediction model. The final hidden layer of the LSTM model outputs leakage risk results, indicating leakage risks, including: Multiple radar level gauges are deployed in each tank of the ship to synchronously collect and record ship attitude data (including heel, pitch, and tank liquid level) in time coordinates. Kalman filtering is used to reduce noise and remove outliers from the collected ship attitude data, establish characteristic data (the liquid level change rate dh) and the liquid level difference fh between adjacent compartments, and construct a time series ship attitude database. The database is used to train a CNN-LSTM network, which consists of two convolutional layers with 64 convolutional kernels and a long short-term memory (LSTM) network. The loss function consists of standard binary cross entropy and focal loss. After training convergence, a leakage risk prediction model is obtained and deployed in the digital twin system. The system collects ship attitude data in real time and inputs it into the prediction model. The final fully connected layer of the model outputs the risk coefficient at that time, thereby indicating the risk of abnormal leakage in the cabin. A stress sensor matrix is ​​arranged on the cabin, and the sensor density is increased in key structural areas. Sensor data w, corresponding point coordinates (x, y, z) and time information t are collected to construct a five-dimensional data set (t, x, y, z, w). The data is denoised to remove abnormal data points. The 3D-CNN network is trained using a database. The network mainly consists of a 3D convolution layer, a 3D maximum pooling layer, an LSTM layer and a fully connected layer. 3D convolution and 1D temporal convolution are performed on the data to extract spatial and temporal features, and the LSTM is input into the enhanced model's sensitivity to time. A linear function is used to accumulate fatigue damage. The loss function uses standard binary cross entropy to train a fatigue damage prediction model and deploy it in the digital twin system. During the ship's navigation, the system collects stress sensor data and inputs it into the fatigue damage prediction model to obtain predicted future fatigue damage, indicating the system's service life.

[0043] By inputting the ship's tank capacity table into the digital twin system and automatically calibrating it based on real-time temperature and pressure, the system uses the actual temperature, pressure, and liquid level information within the tank, combined with the tank capacity table information, to visualize the ship's tank volume in real time, record changes in liquid level and tank capacity, and indicate leakage risks. This system builds an AI model based on changes in liquid levels within the tank, historical stress data, and infrared thermal imaging results, providing leakage risk and fatigue damage prediction.

[0044] like Figure 2 As shown, the present application also provides a ship tank volume measurement system based on digital twins, which is used to implement the ship tank volume measurement method based on digital twins mentioned above. The system includes a multi-source data acquisition module, a core fitting algorithm module, and a digital twin application module; The multi-source data acquisition module includes a laser radar scanning unit, a radar level gauge matrix, a strain sensor network, an infrared thermal imaging unit, and a hull tilt angle measurement unit deployed on the ship's cabin, which is used to record real-time monitoring data of the physical ship cabin and share it with the core fitting algorithm module and the digital twin application module; The core fitting algorithm module is used to fuse point cloud dynamic data, perform surface fitting calculations and cabin volume calculations, and correct cabin capacity information in combination with the real-time monitoring data collected by the multi-source data acquisition module; The digital twin application module includes a visual cabin capacity dashboard, a leakage warning platform and a fatigue damage prediction platform. The visual cabin capacity dashboard is used to display the cabin capacity information in real time, the leakage warning platform is used to display leakage risk results, and the fatigue damage prediction platform is used to display the fatigue accumulation index.

[0045] For the specific definition of the digital twin-based ship tank volume measurement system, please refer to the definition of the digital twin-based ship tank volume measurement method above, which will not be repeated here. The various modules in the above-mentioned digital twin-based ship tank volume measurement system can be implemented in whole or in part through software, hardware, and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0046] The present application provides a ship tank volume measurement method and system based on digital twins. By scanning, point cloud data of the ship tank body, additional structures and subtracted structures are obtained to establish a digital twin ship tank volume system. The ship tank capacity table and the roll and inclination correction table are calculated by the tank volume calculation model and input into the digital twin ship tank volume system. The tank volume information can be corrected in combination with the ship tank capacity table and the roll and inclination correction table, and the tank volume information can be displayed in real time to realize automatic calibration of the tank volume information and improve the efficiency and accuracy of ship tank volume measurement.

[0047] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for measuring the volume of a ship's hold based on digital twins, characterized in that: The following steps are involved: Using a laser scanner to scan and obtain three-dimensional point cloud data of the ship's cabin body, additional structures, and subtracted structures, obtaining real-time stress data collected by sensors in the cabin, correcting the point cloud data based on the real-time stress data, and optimizing the point cloud data; Performing surface fitting based on the point cloud data to establish a digital twin ship capacity system, and calculating a ship capacity table and a heel and roll correction table using a capacity calculation model and inputting them into the digital twin ship capacity system; The digital twin ship capacity system collects physical tank temperature, liquid level information, and tilt angle change information, corrects the tank capacity information in combination with the ship tank capacity table and the roll and inclination correction table, and displays the tank capacity information in real time.

2. The method for measuring the volume of a ship tank based on digital twin according to claim 1 is characterized in that: The acquiring of real-time stress data collected by sensors in the cabin and the correction of point cloud data according to the real-time stress data include: Setting an infrared thermal imager to acquire temperature data, setting stress sensors to be deployed in a grid topology to form a strain sensing network, and acquiring stress data through the strain sensing network; The stress sensor position is matched with the corresponding position of the point cloud data to align the stress data with the point cloud data, the displacement caused by the stress is calculated, and the point cloud data is compensated for thermal expansion according to the temperature data to correct the point cloud data.

3. The method for measuring the volume of a ship tank based on digital twin according to claim 2 is characterized in that: The step of matching the stress sensor position with the corresponding position of the point cloud data to align the stress data with the point cloud data, calculating the displacement caused by the stress, and performing thermal expansion compensation on the point cloud data according to the temperature data to correct the point cloud data includes: pass , Correcting the point cloud data; in, is the mechanical deformation at the stress sensor location, is the stress value at the stress sensor location, E is the Poisson’s ratio of the material, is the thermal expansion deformation at the stress sensor location, is the coefficient of thermal expansion, is the change in temperature relative to the reference value, and A vector displacement of the stress sensor position is synthesized, the discrete displacement vector is interpolated onto the point cloud, and the displacement is decomposed into unit direction vectors to correct the point cloud data.

4. The method for measuring the volume of a ship tank based on digital twin according to claim 2 is characterized in that: The optimization processing of the point cloud data includes: The acquired 3D point cloud data of the ship's cabin main body, attached structures and subtracted structures are processed by removing point cloud noise, downsampling and filling defect data to obtain point cloud data of the cabin main body, attached structures and subtracted structures; The point cloud data is subjected to point cloud filtering, point cloud data splicing and point cloud registration processing, wherein the point cloud filtering adopts a bilateral filtering method, and the bilateral filtering method includes: Suppose a point in the point cloud is , for A point in the neighborhood, , the point after bilateral filtering The position is calculated as follows: ； ； ； in, is the spatial weight function, is the value weight function, is the spatial standard deviation parameter, which controls the size of the geometric neighborhood. is the attribute standard deviation parameter, which is used to control the feature similarity tolerance. It is the characteristic function of a point, including the normal vector, curvature or coordinates of the point.

5. The method for measuring the volume of a ship tank based on digital twin according to claim 2 is characterized in that: The acquiring of real-time stress data collected by sensors in the cabin and correcting the point cloud data according to the real-time stress data further includes: Set up the liquid level meter matrix to obtain liquid level data, and set up the pressure sensor to obtain pressure data; Deformation compensation is performed on the point cloud data according to the liquid level surface data, and pressure compensation is performed on the point cloud data according to the pressure data.

6. The method for measuring the volume of a ship tank based on digital twin according to claim 1, characterized in that: The performing surface fitting according to the point cloud data to establish a digital twin ship cabin capacity system includes: Obtain the optimized 3D point cloud data of the ship cabin body, additional structure and subtracted structure; Performing point cloud splicing on the three-dimensional point cloud data of the ship cabin body and the additional structure to form spliced ​​point cloud data; The point cloud data are fitted using a B-spline surface fitting algorithm according to the spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure, so as to form a B-spline surface.

7. The method for measuring the volume of a ship tank based on digital twin according to claim 6 is characterized in that: The step of fitting the point cloud data using a B-spline surface fitting algorithm based on the spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure, and forming a B-spline surface by fitting includes: The spliced ​​point cloud data and the three-dimensional point cloud data of the subtracted structure are used as input point clouds, and the input point clouds are parameterized to determine node vectors, solve control points, generate surfaces, and perform error analysis to determine whether the accuracy requirements are met; If so, a B-spline surface is output; otherwise, the input point cloud is parameterized again.

8. The method for measuring the volume of a ship tank based on digital twin according to claim 6 is characterized in that: When fitting the point cloud data using the B-spline surface fitting algorithm based on the spliced ​​point cloud data and the three-dimensional point cloud data with the subtracted structure, a cubic B-spline curve is selected for fitting. The parameter expression of the cubic B-spline curve is as follows: ； in, 、 、 、 are any four discrete points in the plane, P(t) is the coordinate of the fitting curve, and the component form of the above formula is: ； in: , .

9. The method for measuring the volume of a ship tank based on digital twin according to claim 8, characterized in that: When fitting to form a B-spline surface, the B-spline surface is formed by constructing multiple B-spline curves in the u and v directions multiple times. u and v are two independent parameters defined on the parameter domain. A control grid is formed by (m+1)×(n+1) control points, and the B-spline surface is formed by fitting. The equation of the B-spline surface is: ； in is the set of control points (i=0,1…m;j=0,1…n), m is the number of control points of the surface in the u direction minus 1, n is the number of control points of the surface in the v direction minus 1, and is the B-spline surface basis function.

10. The method for measuring the volume of a ship tank based on digital twin according to claim 6, characterized in that: The ship tank capacity table and heel and roll correction table calculated by the tank capacity calculation model include: The tank capacity calculation model is set to calculate the tank volume using a surface reconstruction method, and the B-spline surfaces formed by the tank capacity calculation model are respectively fitted according to the spliced ​​point cloud data and the three-dimensional point cloud data with the structure subtracted are used to obtain a main capacity table and a structure subtracted capacity table with 1 cm as the minimum unit through a fitting algorithm; At room temperature of 20°C, a rolling sphere boundary with a radius of α is used to extract non-convex surfaces and generate a uniformly distributed grid. The ship tank volume result is obtained by superposition calculation and the ship tank capacity table is output, and the roll and inclination correction table is output simultaneously.

11. The method for measuring the volume of a ship tank based on digital twin according to claim 10, characterized in that: The digital twin ship capacity system collects physical tank temperature, liquid level information, and tilt angle change information, and corrects the tank capacity information in combination with the ship tank capacity table and the heel and roll correction table, including: Determine whether the physical cabin temperature of the ship's cabin is the room temperature of 20°C. If the cabin temperature is not 20°C, correct the cabin volume based on the temperature calibration formula. The temperature calibration formula is: ； in: is the capacity after temperature correction, in cubic meters; The capacity shown in the tank capacity table is in cubic meters; is the average temperature of the bulkhead in degrees Celsius; is the linear expansion coefficient of the cabin material, in degrees Celsius. =0.000012 / ℃.

12. The method for measuring the volume of a ship tank based on digital twin according to claim 10, characterized in that: The method further comprises: The liquid level changes in the ship's cabin are collected and a CNN-LSTM hybrid model is constructed to capture the spatiotemporal characteristics of the liquid level changes. This information is then input into the LSTM model to build a time series prediction model. The final hidden layer of the LSTM model outputs the leakage risk result to indicate the leakage risk. The cabin stress data history is collected and a 3D-CNN model is established. The spatiotemporal information is fused through three-dimensional convolution, the association between spatial topology and spatiotemporal information sequence is retained, and the fatigue accumulation index is output to predict fatigue damage.

13. A ship tank volume measurement system based on digital twin, characterized in that: Used to implement the ship tank volume measurement method based on digital twin according to any one of claims 1 to 12, the system includes a multi-source data acquisition module, a core fitting algorithm module, and a digital twin application module; The multi-source data acquisition module includes a laser radar scanning unit, a radar level gauge matrix, a strain sensor network, an infrared thermal imaging unit, and a hull tilt angle measurement unit deployed on the ship's cabin, which is used to record real-time monitoring data of the physical ship cabin and share it with the core fitting algorithm module and the digital twin application module; The core fitting algorithm module is used to fuse point cloud dynamic data, perform surface fitting calculations and cabin volume calculations, and correct cabin capacity information in combination with the real-time monitoring data collected by the multi-source data acquisition module; The digital twin application module includes a visual cabin capacity dashboard, a leakage warning platform and a fatigue damage prediction platform. The visual cabin capacity dashboard is used to display the cabin capacity information in real time, the leakage warning platform is used to display leakage risk results, and the fatigue damage prediction platform is used to display the fatigue accumulation index.

Images