Quantitative management and BIM (Building Information Modeling) data integration system for construction process of sanding ship

Abstract

The invention relates to the technical field of ship engineering and BIM, and particularly discloses a sand-paving ship construction process quantitative management and BIM data integration system. The system comprises a construction data acquisition module, a three-dimensional thickness modeling and visualization module, a multi-dimensional quantitative evaluation module, a multi-source information fusion analysis module and a process parameter optimization decision module, through integration of high-precision sounding, thickness sensing, equipment operation and geological data, a three-dimensional thickness distribution model is constructed, and a multi-dimensional quantitative index is calculated. And establishing a correlation model of equipment parameters, geological conditions and thickness uniformity, and dynamically generating a process optimization instruction based on an analysis result. According to the invention, three-dimensional visual monitoring, multi-dimensional quantitative evaluation and closed-loop optimization control of the construction quality of the sand-paving ship are realized.

Description

Technical Field

[0001] This invention belongs to the field of marine engineering and BIM technology, specifically relating to a quantitative management and BIM data integration system for the construction process of a sand-laying vessel. Background Technology

[0002] In the fields of large-scale marine engineering and port and waterway construction, sand pavers are key operational equipment, and the level of precise control and information management of their construction process directly determines the overall quality and efficiency of the project. Quantitative management of the sand paver construction process aims to achieve refined control of construction process parameters through data collection and analysis.

[0003] Layered backfilling with sand-laying vessels is a core technical aspect of deep soft soil reclamation projects. Its key technological requirement is to precisely control the thickness of each layer within a specific range and ensure its uniformity to guarantee the long-term stability and load-bearing capacity of the soft soil. Current technologies primarily rely on traditional data processing and presentation methods to assess construction quality.

[0004] Existing technologies have limitations in data presentation dimensions, typically only providing two-dimensional water depth difference planar maps or cross-sectional thickness curves. They cannot intuitively and three-dimensionally display the overall thickness distribution in three-dimensional space, making it difficult to quickly identify and locate construction areas that are excessively thick or thin.

[0005] Meanwhile, the quantitative indicators of existing evaluation methods are too simplistic, often using only whether the thickness is greater than the threshold as the criterion for qualification, without systematically quantifying core indicators that reflect uniformity, such as the proportion of the effective thickness range and the dispersion of thickness data. This results in one-sided and shallow evaluation conclusions.

[0006] Furthermore, the thickness data generated during construction is isolated from key information such as the equipment operating parameters of the sand-laying vessel and the specific geological conditions of the work area, lacking effective correlation and integration. This makes it impossible to trace and analyze the root causes of thickness unevenness. These shortcomings collectively restrict the effectiveness of accurate construction quality assessment and process optimization, constituting a pressing technical challenge that needs to be addressed. Summary of the Invention

[0007] The technical problem this invention aims to solve is to overcome the shortcomings of existing sand-laying vessel construction management technologies, such as limited data presentation dimensions, single quantitative evaluation indicators, and the difficulty in correlated analysis of isolated multi-source information. This invention provides a quantitative management system for sand-laying vessel construction processes that integrates BIM (Building Information Modeling) data. This system aims to achieve a three-dimensional visual display of the construction thickness, construct a multi-dimensional quantitative evaluation indicator system, and deeply integrate equipment operating parameters and geological condition information, thereby achieving the fundamental goal of accurate assessment of sand-laying vessel construction quality and process optimization.

[0008] This invention provides a quantitative management and BIM data integration system for sand-laying vessel construction process. The system includes a construction data acquisition module, a three-dimensional thickness modeling and visualization module, a multi-dimensional quantitative evaluation module, a multi-source information fusion analysis module, and a process parameter optimization decision-making module.

[0009] The construction data acquisition module is used to collect various types of data in real time during the sand-laying vessel's operation. The collected data includes water depth data of the operation area obtained by the shipborne high-precision depth sounder, real-time paving thickness data obtained by the thickness sensor installed on the paving mechanism, sand-laying vessel's sailing speed and material gate opening equipment operating parameters obtained by the ship's automation system, and geological conditions data of soil layer characteristics and soft foundation distribution in the operation area retrieved from the engineering geological survey database.

[0010] The 3D thickness modeling and visualization module is connected to the construction data acquisition module to construct a 3D digital terrain model of the work area based on the acquired water depth and thickness data. This module uses a spatial interpolation algorithm to transform discrete measurement point thickness data into a continuous spatial thickness field, and then renders the thickness distribution in a 3D manner using a chromatographic mapping method on this 3D model. The chromatographic color depth is positively correlated with the thickness value, thus intuitively identifying the spatial location of local ultra-thick and ultra-thin areas.

[0011] The multi-dimensional quantitative evaluation module is connected to the 3D thickness modeling and visualization module to perform systematic quantitative analysis on the rendered 3D thickness model. This analysis process calculates several core evaluation indicators, including the percentage of thickness data points falling within the preset effective thickness range out of the total number of measurement points (i.e., the effective thickness percentage), the thickness dispersion characterized by the standard deviation of all thickness measurement data points, and the skewness and kurtosis indices indicating the degree to which the thickness distribution curve deviates from the ideal normal distribution.

[0012] The multi-source information fusion analysis module is connected to both the construction data acquisition module and the multi-dimensional quantitative evaluation module to establish a correlation model between equipment operating parameters, geological condition data, and quantitative evaluation indicators. This module uses temporal alignment and spatial registration techniques to perform correlation analysis between the thickness dispersion index at a specific time and in a specific area and the sailing speed of the sand-laying vessel, the opening of the material gate, and the compression modulus of the soft soil in that area at that time, in order to identify the key influencing factors leading to thickness non-uniformity.

[0013] The process parameter optimization decision module is connected to the multi-source information fusion analysis module and the multi-dimensional quantitative evaluation module. It is used to generate adjustment instructions for construction process parameters based on the correlation analysis results and the quantitative evaluation results. When the thickness dispersion output by the multi-dimensional quantitative evaluation module is greater than a preset threshold, and the multi-source information fusion analysis module identifies that high dispersion is related to low sailing speed, the process parameter optimization decision module generates an optimization instruction to increase the sailing speed of the sand-laying vessel and sends it to the sand-laying vessel control system.

[0014] Furthermore, the spatial interpolation algorithm executed in the 3D thickness modeling and visualization module is specifically the Kriging interpolation algorithm. The execution process of this algorithm is as follows: First, the semi-variogram function among all thickness measurement points in 3D space is calculated to quantify spatial autocorrelation; then, a system of equations for a linear unbiased estimator is constructed based on the semi-variogram function model; finally, the system of equations is solved to obtain the best linear unbiased thickness estimate for unsampled points, thereby generating a continuous and smooth 3D thickness distribution model.

[0015] Furthermore, the multi-dimensional quantitative evaluation module uses the coefficient of variation (COP) of the thickness data as the indicator when calculating the thickness dispersion. The COP is calculated as follows: first, the standard deviation of the thickness values ​​at all valid measurement points is calculated; then, the arithmetic mean of the thickness values ​​at all valid measurement points is calculated; finally, the standard deviation is divided by the arithmetic mean and multiplied by 100% to obtain the dimensionless COP percentage. This percentage is used to compare the relative dispersion of the thickness data at different mean levels.

[0016] Furthermore, the correlation model established in the multi-source information fusion analysis module is a multiple linear regression model. This model uses the thickness dispersion as the dependent variable and the speed of the sand-laying vessel, the opening of the material gate, and the compression modulus of the soft soil as independent variables. The model fits the regression coefficients of each independent variable using the least squares method, and the absolute value of the regression coefficient directly characterizes the strength of the influence of that independent variable on the thickness uniformity.

[0017] Furthermore, the process parameter optimization decision module also integrates feedback control logic. This logic continuously monitors the thickness data collected in the next round of construction after the optimization command is executed, and recalculates the thickness dispersion index. If the recalculated dispersion index does not show the expected decrease compared to before optimization, the module will automatically adjust the parameter weights in its internal decision rules and attempt to generate a different set of process parameter combinations for the next round of optimization testing until the thickness uniformity index meets the preset qualification standard.

[0018] Furthermore, the entire system is built on a unified BIM data platform. All raw data collected by the construction data acquisition module, the 3D model generated by the 3D thickness modeling and visualization module, all indicators calculated by the multi-dimensional quantitative evaluation module, the correlation model established by the multi-source information fusion analysis module, and all instructions and their execution results issued by the process parameter optimization decision-making module are associated and stored with the corresponding construction component objects in the BIM platform according to the preset data structure, forming a traceable digital twin covering the entire construction process.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention upgrades the traditional two-dimensional plane or cross-sectional thickness display to three-dimensional rendering based on spatial interpolation algorithms through a three-dimensional thickness modeling and visualization module. It can present the spatial distribution of thickness in the entire working area in an all-round and comprehensive manner, enabling construction personnel to identify abnormal areas that are too thick or too thin in a very intuitive and quick way, thereby improving the efficiency and accuracy of locating quality defects.

[0020] 2. This invention, through a multi-dimensional quantitative evaluation module, transcends the limitations of existing technologies that rely on a single threshold criterion. It systematically introduces indicators such as effective thickness ratio, thickness dispersion, and distribution morphology characteristics, constructing a multi-dimensional, multi-level quantitative evaluation system. This system comprehensively reflects construction quality from multiple perspectives, including thickness qualification rate, uniformity, and distribution patterns, resulting in more comprehensive and insightful evaluation conclusions and providing richer data support for process optimization.

[0021] 3. This invention, through a multi-source information fusion analysis module, breaks down the information silos between equipment parameters, geological conditions, and construction quality data, establishing a quantitative correlation model among them. This enables the system to trace the root cause of thickness non-uniformity, clarifying whether improper equipment operation or complex geological conditions are the main influencing factors. This achieves a leap from simple quality result evaluation to process causal analysis, providing a clear target for precise optimization of process parameters.

[0022] 4. This invention, through a process parameter optimization decision-making module and its integrated feedback control logic, forms a closed-loop control system from data acquisition, analysis, diagnosis to decision execution. This system can not only provide optimization instructions based on current analysis results, but also self-adjust and learn based on feedback from the effects of instruction execution, thereby continuously improving the accuracy and adaptability of decision-making, ultimately promoting the dynamic optimization of sand-laying vessel construction process parameters and the steady improvement of construction quality. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the overall technical solution architecture of the sand-dredging vessel construction process quantitative management and BIM data integration system proposed in this invention; Figure 2 This is a schematic diagram of the core principle framework of the three-dimensional thickness modeling and visualization module in this invention; Figure 3 This is a logical flow diagram of the multi-dimensional quantitative evaluation module in this invention; Figure 4 This is a schematic diagram of the association model framework of the multi-source information fusion analysis module in this invention; Figure 5 This is a feedback control logic framework diagram of the process parameter optimization decision module in this invention; Figure 6 This is a construction diagram of layered sand laying by a sand-laying vessel in this invention; Detailed Implementation Please refer to the attached document. Figures 1 to 6 This embodiment details the technical implementation of a quantitative management and BIM data integration system for sand-laying vessel construction. The system is built on a unified BIM data platform, which serves as the central hub for the storage, management, and interaction of all data. The system comprises five core modules: a construction data acquisition module, a 3D thickness modeling and visualization module, a multi-dimensional quantitative evaluation module, a multi-source information fusion analysis module, and a process parameter optimization decision-making module. These modules exchange data and transmit instructions through pre-defined data interfaces and communication protocols, forming a complete closed loop from data perception to decision execution.

[0024] The construction data acquisition module is responsible for acquiring various raw data during the sand paving operation in real time. This module integrates multiple sensors and data sources. A shipborne high-precision depth sounder collects water depth data of the operating area at a frequency of 2 times / s, achieving centimeter-level accuracy. A thickness sensor array installed on the paving mechanism monitors the thickness of the paved layer in real time. This thickness sensor, based on laser ranging, has a measurement range of 0.1m to 5m and a resolution of 1cm. The real-time sailing speed and material gate opening parameters of the sand paving vessel are directly read via the ship's automation system data bus. The sailing speed range is 0 to 10 knots, and the material gate opening range is 0% to 100%.

[0025] In addition, this module also retrieves corresponding soil layer characteristic parameters and soft soil foundation distribution data from a pre-established engineering geological survey database through a standard database query interface, according to the coordinate range of the work area. Key parameters include the soil compression modulus, which typically ranges from 2MPa to 100MPa. All collected real-time data are accompanied by timestamps and spatial coordinate information, and after preliminary encapsulation according to the data structure defined by the BIM platform, they are transmitted to the 3D thickness modeling and visualization module.

[0026] The 3D thickness modeling and visualization module receives water depth and thickness data from the construction data acquisition module. Its core task is to construct a 3D digital terrain model of the work area and achieve three-dimensional visualization of the thickness distribution. Please refer to the appendix. Figure 2 The data processing flow of this module begins with the data preprocessing submodule.

[0027] The data preprocessing submodule verifies the validity of the input raw water depth and thickness data, and removes obvious abnormal values ​​caused by sensor malfunctions or communication interference, such as data points with negative thickness values ​​or greater than 5m.

[0028] Then, coordinate unification was performed to transform the coordinates of all measuring points to the same engineering coordinate system.

[0029] After preprocessing, the spatial interpolation calculation submodule is activated. This system uses the Kriging interpolation algorithm as the core spatial interpolation method. The execution of this algorithm consists of three main steps.

[0030] The first step is spatial structure analysis, which calculates the semivariogram among all effective thickness measurement points. The semivariogram is used to quantify spatial autocorrelation, and its calculation depends on the difference between the distance and thickness values ​​between the measurement points.

[0031] The second step is model fitting. Based on the calculated empirical semivariogram, a theoretical model is selected for fitting. Commonly used models include the spherical model or the exponential model.

[0032] The third step is Kriging estimation. Based on the well-fitted semi-variogram model, a system of equations for a linear unbiased estimator is constructed. By solving this system of equations, the best linear unbiased thickness estimate for any unsampled point within the working area is obtained.

[0033] This process ultimately generates a continuous and smooth three-dimensional thickness distribution model.

[0034] Once the model is built, the 3D rendering and visualization submodule begins to work.

[0035] This submodule loads the 3D thickness distribution model into the graphics engine and applies chromatographic mapping technology for stereo rendering.

[0036] A strict mapping relationship is established between the color depth and thickness values ​​of the color spectrum. A gradient color spectrum from blue to red is usually used, with blue representing a thinner area and red representing a thicker area.

[0037] This rendering method allows construction workers to intuitively identify the spatial location and distribution range of local ultra-thick and ultra-thin areas in a 3D scene.

[0038] The generated 3D model and its rendering results are synchronously stored in the BIM platform and associated with the corresponding construction area component objects.

[0039] The multi-dimensional quantitative evaluation module receives thickness data processed by the 3D thickness modeling and visualization module, as well as a directly constructed 3D thickness model. This module's function is to provide a systematic, multi-dimensional, quantitative evaluation of construction thickness quality. Please refer to the appendix. Figure 3 The evaluation process is executed by the indicator calculation submodule.

[0040] The indicator calculation submodule performs parallel calculations of the three core evaluation indicators.

[0041] The first indicator is the percentage of effective thickness.

[0042] The calculation of this indicator first requires pre-setting a valid thickness range, such as 0.3m to 0.8m. The system then counts the number of thickness measurement points whose thickness values ​​fall within this preset range. Finally, the percentage of these valid points out of the total number of measurement points is calculated. This percentage directly reflects the overall pass rate of the construction thickness.

[0043] The second indicator is the degree of thickness dispersion.

[0044] This system uses the coefficient of variation (CV) as an indicator to measure the dispersion of thickness. The calculation process for the CV is as follows: First, calculate the standard deviation of the thickness values ​​at all valid measuring points. The standard deviation represents the fluctuation range of the thickness value relative to its mean. Second, calculate the arithmetic mean of the thickness values ​​at all valid measuring points. Finally, divide the standard deviation by the arithmetic mean and multiply by 100% to obtain a dimensionless percentage value, which is the CV. Using the CV, rather than simply the standard deviation, can eliminate the influence caused by differences in average thickness, making the uniformity of construction thickness comparable across different batches or regions.

[0045] The third indicator is the morphological characteristics of thickness distribution.

[0046] This metric is achieved by calculating the skewness and kurtosis of the thickness data. Skewness measures the degree to which the thickness distribution curve deviates from a symmetrical distribution. Positive skewness indicates a rightward shift in the thickness distribution, meaning there are more overly thick points; negative skewness indicates a leftward shift, meaning there are more underly thin points. Kurtosis measures the steepness of the thickness distribution curve. Compared to an ideal normal distribution, high kurtosis indicates more concentrated data, while low kurtosis indicates more dispersed data.

[0047] All these calculated index values, along with the original data identifiers on which their calculations are based, are transmitted to the multi-source information fusion analysis module and simultaneously archived to the BIM platform.

[0048] The multi-source information fusion analysis module is a crucial bridge connecting construction process parameters and construction quality results. This module simultaneously receives equipment operating parameters and geological condition data from the construction data acquisition module, as well as quantitative evaluation indicators from the multi-dimensional quantitative evaluation module. Please refer to the appendix. Figure 4 Its core task is to build the association model sub-module.

[0049] The correlation model submodule employs a multiple linear regression model to establish a quantitative relationship between thickness dispersion and multiple influencing factors. In this model, thickness dispersion, i.e., the coefficient of variation, is used as the dependent variable, while the speed of the sand-laying vessel, the opening of the material gate, and the compression modulus of the soft soil are used as independent variables.

[0050] Before model building, data preprocessing is required, including temporal alignment and spatial registration. Temporal alignment ensures that the equipment parameters, geological data, and thickness indices used for analysis correspond to the same construction period in time. Spatial registration ensures that these data correspond to the same work area in space.

[0051] After preprocessing, the least squares method is used to fit the multiple linear regression model, and the regression coefficients of each independent variable are solved. The absolute value of the regression coefficient directly characterizes the strength of the influence of that independent variable on thickness uniformity. For example, if the regression coefficient of sailing speed is negative and has a large absolute value, it indicates that an increase in sailing speed is associated with a decrease in thickness dispersion. The established correlation model and its parameters are stored for subsequent analysis and decision-making.

[0052] When correlation analysis is required, the correlation analysis execution submodule is invoked. This submodule inputs current or multiple sets of historical independent variable data into the fitted model, calculates the predicted thickness dispersion, and compares it with the actual value to identify the key influencing factors that lead to the current thickness uniformity.

[0053] The process parameter optimization decision-making module is the control terminal of the entire system. This module receives correlation analysis results from the multi-source information fusion analysis module and the latest quantitative evaluation results from the multi-dimensional quantitative evaluation module. Please refer to the appendix. Figure 5 Its decision-making logic is jointly implemented by the decision rule library submodule and the feedback control submodule.

[0054] The decision rule library submodule contains a series of pre-defined decision rules. These rules typically take the form of conditional judgments. For example, a typical rule is: if the thickness dispersion output by the multi-dimensional quantitative evaluation module is greater than the preset threshold of 15%, and the multi-source information fusion analysis module identifies that the current high dispersion is related to the low speed of the sand-laying vessel, then the process parameter optimization decision module generates an optimization instruction to increase the speed of the sand-laying vessel by 0.5 knots.

[0055] Once the command is generated, it is sent to the central control system of the sand-dredging vessel via a standard industrial communication protocol.

[0056] The feedback control submodule is responsible for evaluating the effectiveness of the optimization commands. This submodule continuously monitors the thickness data newly acquired by the construction data acquisition module after the optimization commands are executed.

[0057] Based on this new data, the multi-dimensional quantitative evaluation module recalculates the thickness dispersion index.

[0058] The feedback control submodule compares the recalculated dispersion index with the index before optimization. If the index does not decrease as expected, or even increases, the feedback control submodule triggers the decision rule base submodule to make adaptive adjustments.

[0059] Such adjustments may include modifying the thresholds in the rules or changing the weighting of different influencing factors.

[0060] The system then attempts to generate a different set of process parameter combinations based on the adjusted rules, such as simultaneously adjusting the sailing speed and the gate opening, for the next round of optimization testing.

[0061] This feedback loop continues until the thickness uniformity index meets the preset qualification standard, such as the thickness dispersion being less than 10%.

[0062] The entire system relies on the support of a BIM data platform. All raw data collected by the construction data acquisition module, including every water depth point, thickness value, equipment parameters, and geological information, is stored according to the object types and attributes defined by the platform.

[0063] The 3D model generated by the 3D thickness modeling and visualization module is managed as a 3D view object within the platform. Each index value calculated by the multi-dimensional quantitative evaluation module is recorded as attribute data of the corresponding construction area component. The association model established by the multi-source information fusion analysis module is stored as an analysis model resource of the platform. Every instruction issued by the process parameter optimization decision-making module and its subsequent effect feedback data are associated with the relevant construction process objects, forming a complete and traceable data chain.

[0064] This deep integration makes the system not just a standalone analysis tool, but a traceable digital twin covering the entire sand-laying vessel construction process, providing a solid data foundation for project quality control, process review and optimization.

[0065] This embodiment focuses on the application of a quantitative management and BIM data integration system for sand-dredging vessel construction processes in another typical construction condition, particularly in work areas with extremely complex geological conditions and uneven distribution of soft soil. The basic architecture and module connections of this system are the same as described above, but its internal data processing strategies and decision-making logic have been adaptively enhanced for complex working conditions.

[0066] In the construction data acquisition module, for complex geological conditions, the data retrieved from the engineering geological survey database is more refined. In addition to basic soil layer characteristics and soft soil foundation distribution data, dynamic geological parameters such as groundwater level depth and soil permeability coefficient are also added.

[0067] These parameters are provided in the form of grid data, with a higher spatial resolution, for example, up to 5m × 5m.

[0068] The thickness sensors are also deployed more densely, with a double-row staggered sensor array on the paving mechanism to ensure sufficient density of thickness data in areas where uneven settlement may occur.

[0069] The data acquisition frequency was also increased to 5 times / second to capture faster thickness changes.

[0070] The 3D thickness modeling and visualization module optimizes its spatial interpolation algorithm to handle complex geological conditions. When using the Kriging interpolation algorithm, the calculation of the semi-variogram no longer assumes spatial isotropy, but instead introduces an anisotropic model. This model allows for different spatial correlation ranges in different directions, thus more accurately characterizing the anisotropic features of thickness distribution caused by directional changes in geological conditions.

[0071] In terms of 3D rendering, in addition to basic thickness color mapping, transparency and isosurface display functions have been added. Construction personnel can adjust the transparency of the 3D model and observe the overlap between the thickness distribution and the underlying geological model, intuitively analyzing the spatial correspondence between thickness anomalies and specific geological units such as weak interlayers.

[0072] In complex working conditions, the multi-dimensional quantitative evaluation module introduces the concept of spatial zoning statistics into the calculation of evaluation indicators. Instead of calculating the entire work area as a whole, the system automatically divides the area into several evaluation sub-regions based on differences in geological conditions or the division of construction sections. Within each sub-region, the effective thickness percentage, thickness variation coefficient, skewness, and kurtosis indices are calculated independently.

[0073] This zoning assessment can accurately pinpoint the specific sub-regions where quality problems occur, preventing overall indicators from masking serious local issues. For example, even if the overall coefficient of variation is within acceptable limits, the coefficient of variation of a sub-region in a soft soil foundation area may be severely excessive, and the system can immediately identify that region.

[0074] When constructing the correlation model, the multi-source information fusion analysis module adds a geological interaction term as an independent variable to its multiple linear regression model for complex working conditions. For example, in addition to sailing speed, gate opening, and soil compression modulus, the model may also include a product term of sailing speed and soil compression modulus as a new independent variable. This enables the model to capture the nonlinear influence of the combined effects of equipment operating parameters and geological conditions on thickness uniformity.

[0075] By analyzing the regression coefficients of these interaction terms after model fitting, it can be revealed under what geological conditions the adjustment of equipment parameters will be more sensitive or less effective.

[0076] The process parameter optimization decision-making module has a more forward-looking and adaptable decision-making logic in complex geological areas. Its decision rule base is no longer a simple single parameter adjustment rule, but includes parameter combination recommendation strategies based on multi-objective optimization.

[0077] When the system identifies that the thickness uniformity of a certain sub-region is poor, the decision rule library sub-module will consider multiple objectives at the same time, including improving the thickness uniformity of the sub-region, avoiding disturbance to adjacent qualified sub-regions, and ensuring that the overall construction efficiency does not decrease significantly.

[0078] Based on these objectives, a set of recommended process parameters is generated by querying a historical success case library or running a simple optimization algorithm. This set typically includes fine-tuning suggestions for sailing speed, gate opening, and even the construction path. The learning capability of the feedback control submodule is also more prominent in this operating condition. It not only records the changes in thickness uniformity after the optimization command is executed, but also records the geological background parameters at that time in detail.

[0079] By accumulating a large number of such cases, the system can gradually build a knowledge base of optimal process parameters under different geological profiles, thereby realizing the evolution from adaptive adjustment to predictive optimization. All detailed data, zoning evaluation results, complex correlation models containing interaction terms, and multi-objective decision records generated under complex working conditions are thoroughly integrated into the BIM platform, providing extremely valuable reference data and decision support for future engineering projects under similar geological conditions.

[0080] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0081] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A quantitative management and BIM data integration system for sand-laying vessel construction process, characterized in that, include: The construction data acquisition module is used to collect various types of data in real time during the sand-laying vessel operation. The 3D thickness modeling and visualization module is connected to the construction data acquisition module and is used to build a 3D digital terrain model of the work area based on the acquired water depth and thickness data. The multi-dimensional quantitative evaluation module is connected to the 3D thickness modeling and visualization module. It is used to perform systematic quantitative analysis on the rendered 3D thickness model. This analysis process calculates multiple core evaluation indicators, including the percentage of thickness data points that fall within the preset effective thickness range to the total number of measurement points, i.e., the effective thickness ratio; the thickness dispersion represented by the standard deviation of all thickness measurement point data; and the skewness and kurtosis indicators of the degree to which the thickness distribution curve deviates from the ideal normal distribution. The multi-source information fusion analysis module is connected to both the construction data acquisition module and the multi-dimensional quantitative evaluation module. It is used to establish a correlation model between equipment operating parameters, geological condition data and quantitative evaluation indicators. This module uses time alignment and spatial registration technology to perform correlation analysis between the thickness dispersion index at a specific time and in a specific area and the sailing speed of the sand-laying vessel, the opening of the material gate, and the compression modulus of the soft soil in that area at that time. The process parameter optimization decision module is connected to the multi-source information fusion analysis module and the multi-dimensional quantitative evaluation module. It is used to generate adjustment instructions for construction process parameters based on the correlation analysis results and the quantitative evaluation results. When the thickness dispersion output by the multi-dimensional quantitative evaluation module is greater than the preset threshold, and the multi-source information fusion analysis module identifies that high dispersion is related to low sailing speed, this module generates an optimization instruction to increase the sailing speed of the sand-laying vessel and sends it to the sand-laying vessel control system.

2. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The construction data acquisition module collects data including water depth data of the work area obtained by a shipborne high-precision depth sounder, real-time paving thickness data obtained by a thickness sensor installed on the paving mechanism, the sailing speed of the sand-laying vessel and the operating parameters of the material gate opening equipment obtained by the ship automation system, and geological conditions data of soil characteristics and soft foundation distribution in the work area retrieved from the engineering geological survey database.

3. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The three-dimensional thickness modeling and visualization module transforms discrete measurement point thickness data into a continuous spatial thickness field through a spatial interpolation algorithm, and renders the thickness distribution in three dimensions using a chromatographic mapping method on this three-dimensional model. The chromatographic color depth is positively correlated with the thickness value.

4. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 3, characterized in that, The spatial interpolation algorithm is specifically the Kriging interpolation algorithm, and its execution process is as follows: First, the semivariogram function among all thickness measurement points in three-dimensional space is calculated to quantify spatial autocorrelation. Then, a system of equations for a linear unbiased estimator is constructed based on the semivariogram function model. Finally, the system of equations is solved to obtain the best linear unbiased thickness estimate for unsampled points, thereby generating a continuous and smooth three-dimensional thickness distribution model. The Kriging interpolation algorithm employs an anisotropic model when calculating the semi-variogram, which allows for different spatial correlation ranges in different directions.

5. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The thickness dispersion is measured by the coefficient of variation of the thickness data. The calculation process of the coefficient of variation is as follows: first, calculate the standard deviation of the thickness values ​​of all valid measuring points; then, calculate the arithmetic mean of the thickness values ​​of all valid measuring points; finally, divide the standard deviation by the arithmetic mean and multiply by 100% to obtain the dimensionless coefficient of variation percentage.

6. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The correlation model is a multiple linear regression model. The model uses the thickness dispersion as the dependent variable and the speed of the sand-laying vessel, the opening of the material gate, and the compression modulus of the soft soil as independent variables. The model fits the regression coefficients of each independent variable using the least squares method. The multiple linear regression model adds a geological interaction term as an independent variable, which includes the product of navigation speed and soil compression modulus.

7. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The process parameter optimization decision module also integrates feedback control logic. This logic continuously monitors the thickness data collected in the new round of construction after the optimization command is executed, and recalculates the thickness dispersion index. If the recalculated dispersion index does not show the expected decrease compared to before optimization, the module automatically adjusts the parameter weights in its internal decision rules and attempts to generate a different set of process parameter combinations for the next round of optimization testing.

8. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The system is built on a unified BIM data platform. All the raw data collected by the construction data acquisition module, the 3D model generated by the 3D thickness modeling and visualization module, all the indicators calculated by the multi-dimensional quantitative evaluation module, the association model established by the multi-source information fusion analysis module, and all the instructions and execution results issued by the process parameter optimization decision module are associated and stored with the corresponding construction component objects in the BIM platform according to the preset data structure.

9. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The multi-dimensional quantitative evaluation module introduces the concept of spatial partition statistics when calculating evaluation indicators. It automatically divides the work area into several evaluation sub-areas based on differences in geological conditions or the division of construction sections. Within each sub-area, it independently calculates the effective thickness ratio, thickness variation coefficient, skewness and kurtosis index.

10. The quantitative management and BIM data integration system for sand-laying vessel construction process according to claim 1, characterized in that, The process parameter optimization decision module includes a decision rule base, which contains a parameter combination recommendation strategy based on multi-objective optimization. This strategy simultaneously considers multiple objectives, such as improving thickness uniformity, avoiding disturbance to adjacent qualified sub-regions, and ensuring overall construction efficiency.

Images