Visual analysis method for comparing multi-system progress data of shipbuilding project

Abstract

The invention relates to the technical field of data analysis and management, in particular to a visual analysis method for comparing multi-system progress data of a shipbuilding project, which comprises the following steps of: extracting progress related characteristic data from a management system, a human resource system, a production system, a financial system and a supply chain system of the shipbuilding project; generating a standardized multi-dimensional progress feature matrix; performing convolution operation on the weight coefficient and the multi-dimensional progress characteristic matrix to generate a comprehensive progress deviation cloud picture with time sequence relevance; mapping the comprehensive progress deviation cloud picture to a three-dimensional coordinate system; and updating the curved surface form in real time and outputting a key path early warning signal. According to the method, the self-adaptive sliding window and the dynamic weight convolution mechanism are combined, so that the real-time comparison precision and the time sequence traceability of the cross-system progress deviation are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis management, and in particular to a visual analysis method for comparing multi-system progress data of a shipbuilding project. Background Art

[0002] As the scale of shipbuilding projects becomes increasingly large, the management systems, human resources systems, production execution systems, financial management systems and supply chain systems involved are interconnected and complex in coordination, and the difficulty of overall control of project progress has increased significantly. Existing project management methods are mainly based on single-system or linear-dimensional plan tracking, which often ignores the time synchronization deviation between multiple systems, inconsistent data dimensions and their combined impact on the actual progress, making it difficult to timely identify the root cause of progress imbalance and its evolution trend.

[0003] In addition, traditional progress analysis methods mostly rely on static reports or two-dimensional graphics, lacking the ability to model and visualize the coupling relationship between progress deviations of different systems, and are difficult to meet the precise requirements of dynamic changes, critical path control, and process conflict warning in shipbuilding. Especially in the face of special working conditions such as dock resource sharing, complex lifting operations, and material delays, existing methods have obvious deficiencies in multi-domain progress data fusion, deviation identification granularity, and interactive analysis capabilities. Summary of the invention

[0004] The present invention provides a visual analysis method for multi-system progress data comparison of shipbuilding projects, which integrates multi-system progress characteristics and has dynamic weight analysis and three-dimensional visualization capabilities to improve the progress transparency, control accuracy and abnormal response efficiency of shipbuilding projects.

[0005] A visual analysis method for comparing multi-system progress data of a shipbuilding project comprises the following steps:

[0006] S1, multi-system data standardization processing: extract progress-related feature data from the management system, human resources system, production system, financial system, and supply chain system of the shipbuilding project, align the timestamps of the feature data, and unify the dimensions to generate a standardized multi-dimensional progress feature matrix;

[0007] S2, dynamic weight allocation and progress comparison: Based on the progress influencing factors of each system in the multi-dimensional progress feature matrix, an adaptive sliding window algorithm is used to calculate the weight coefficient of each system in real time, and the weight coefficient is convolved with the multi-dimensional progress feature matrix to generate a comprehensive progress deviation cloud map with time series correlation;

[0008] S3. 3D Visualization Model Construction: Map the comprehensive progress deviation cloud chart to a three-dimensional coordinate system, where the X-axis represents the project timeline, the Y-axis represents the correlation degree of each system, and the Z-axis represents the deviation impact intensity. Generate a visual comparison surface through a spatial interpolation algorithm;

[0009] S4. Interactive Intelligent Analysis: Embed adjustable threshold parameters in the visual comparison surface, adjust the time slice range and weight allocation ratio through touch interaction, and update the surface morphology in real time and output key path warning signals.

[0010] Optionally, the S1 specifically includes:

[0011] S11. Extract the task node completion rate, approval process response duration, and project milestone deviation value from the management system; extract the work type labor saturation, skill matching degree, and personnel turnover rate from the human resources system; extract the sectional construction completion degree, overall equipment efficiency, and quality inspection pass rate from the production system; extract the budget execution rate, payment node achievement rate, and cost overrun coefficient from the financial system; extract the material kit completion rate and logistics on-time rate from the supply chain system;

[0012] S12. Use the task node number as the association key for timestamp alignment, and perform two-way matching between the sectional construction timestamp of the production system and the task node timestamp of the management system: When the deviation between the hoisting completion time recorded in the production system and the node deadline set in the management system exceeds the predetermined time, based on the production system timestamp, synchronously update the actual completion time of the corresponding node in the management system;

[0013] S13. Perform dimension unification processing and execute outlier processing, and finally generate a standardized multi-dimensional progress feature matrix. The row vector of the matrix represents the time series segment, and the column vector is arranged by domain as follows: management domain (3 dimensions), human domain (3 dimensions), production domain (3 dimensions), financial domain (3 dimensions), supply chain domain (3 dimensions).

[0014] Optionally, the dimension unification processing includes converting man-hour data into standard man-days (8 hours / man-day), normalizing the budget execution rate to a value in the [0, 1] interval, binaryizing equipment status data into a Boolean type (0 - shutdown / 1 - running), and mapping the supply chain material delay days to a risk level value in the range of [0, 10] through a piecewise function; the outlier processing includes performing outlier cleaning on the processed data, setting the threshold range of the task node completion rate to [0, 1.2], and interpolating data points outside the range with the mean value of adjacent time periods.

[0015] Optionally, the S2 specifically includes:

[0016] S21, Progress impact factor extraction: Core impact factors are separated by domain from the multi-dimensional progress feature matrix, including management domain factors, human resource domain factors, production domain factors, financial domain factors, and supply chain domain factors;

[0017] S22, Adaptive sliding window algorithm execution: Initialize the window length based on the total project cycle, with the step size being the reciprocal of the human resource turnover rate; when it is detected that the overall equipment efficiency in the production domain drops too much for multiple window periods, automatically shorten the window length; if the supply chain risk level value breaks through the risk threshold, then superimpose the supply chain risk penalty factor when the window slides. The supply chain risk level value is mapped to a supply chain risk level value in the range of [0, 10] through a piecewise function based on the supply chain material delay days;

[0018] S23, Convolution operation design: Construct a three-dimensional convolution kernel, whose time dimension length matches the adaptive sliding window, and the spatial dimension corresponds to the five-domain feature channels; Perform depthwise separable convolution on the dynamic weight coefficient matrix and the multi-dimensional progress feature matrix, and initialize the convolution kernel weights using the inter-domain correlation strength matrix;

[0019] S24, Generation of comprehensive progress deviation cloud map: Perform temporal normalization processing on the convolution output, and separate the deviation and random fluctuation components through feature decoupling technology; Map the deviation intensity to the RGB color space, where the red channel represents the production domain-dominated deviation, the blue channel represents the supply chain domain-dominated deviation, and the brightness of the green channel is positively correlated with the financial domain deviation intensity to form a comprehensive progress deviation cloud map.

[0020] Optionally, the supply chain risk penalty factor is calculated as: ; where, is the supply chain risk penalty factor, is the material delay days, is the risk conduction coefficient; is the supply chain risk level value, and the risk conduction coefficient is determined according to the Pearson correlation coefficient between material delay and progress deviation in historical data.

[0021] Optionally, the management domain factor is the product of the task node completion rate and the milestone deviation value; the human resource domain factor takes the weighted harmonic mean of the work type man-hour saturation and the skill matching degree; the production domain factor is calculated by the geometric mean of the segmented construction completion degree, the overall equipment efficiency, and the quality inspection pass rate; the financial domain factor is the ratio of the budget execution rate to the cost overrun coefficient; the supply chain domain factor is based on the product of the material kit completeness rate and the logistics on-time rate.

[0022] Optionally, the mapping rule for mapping the comprehensive progress deviation cloud map to a three-dimensional coordinate system includes:

[0023] The X-axis timeline adopts a segmented non-linear scale, compressing the project plan timeline at a ratio of 1:1, and the actual progress timeline dynamically expands and contracts according to the deviation intensity. The expansion and contraction factor is calculated as: ; where is the expansion and contraction factor of the timeline, is the Z-axis normalized deviation intensity from the comprehensive progress deviation cloud map;

[0024] The Y-axis correlation calculation adopts a cross-domain coupling algorithm: construct a five-domain correlation matrix, set the basic correlation weight between the management domain and the production domain, and set the dynamic correlation weight between the supply chain domain and the financial domain as the square root of the budget execution rate; extract the eigenvector through cluster analysis, and project the first principal component onto the Y-axis to form the correlation scale of each system;

[0025] The Z-axis intensity mapping adopts logarithmic processing, and sets the benchmark intensity value based on the historical project progress deviation;

[0026] The spatial interpolation algorithm includes embedding dynamic constraint conditions in the standard Kriging interpolation process;

[0027] The generation of the visualization comparison surface includes converting the interpolated three-dimensional point cloud data into a NURBS surface, taking the square root of the number of effective task nodes within the current time window as the number of surface control points, and setting special constraint conditions during the surface parameterization process.

[0028] Optionally, the dynamic constraint conditions include:

[0029] ① When the overall equipment efficiency (OEE) of the production domain is lower than the efficiency threshold, add a radial basis function penalty term to the interpolation equation, and the penalty coefficient λ is calculated as: ;

[0030] ② For the area where the budget execution rate of the financial domain is lower than 70%, adopt an anisotropic interpolation strategy, and expand the search neighborhood along the time axis direction to a 2-fold standard deviation range.

[0031] Optionally, the interactive intelligent analysis in S4 includes embedding adjustable threshold panels at the four vertices of the visualization comparison surface, respectively setting the production beat tolerance threshold, man-hour saturation threshold, supply chain risk diffusion coefficient, and financial budget elasticity coefficient. When the threshold is adjusted, the surface color temperature is driven to change dynamically according to the HSV color ring.

[0032] Optionally, the interactive intelligent analysis also includes adjusting the time slice range and weight allocation ratio based on touch gestures, and using incremental recomputation to update the surface morphology in real time. At the same time, generate a three-level critical path warning and output an exception report according to the multi-domain deviation intensity and its correlation relationship.

[0033] The beneficial effects of the present invention:

[0034] In the present invention, by extracting key progress characteristic indicators from five major systems including management, human resources, production, finance, and supply chain, and constructing a multi-dimensional progress characteristic matrix with a unified dimension, time alignment, and anomaly elimination mechanism, technical problems such as inconsistent data calibers, large dimension spans, and poor time correlation in the shipbuilding process are solved; combined with an adaptive sliding window and a dynamic weight convolution mechanism, the real-time comparison accuracy and chronological traceability of cross-system progress deviations are significantly improved.

[0035] In the present invention, a three-dimensional comparison coordinate system is constructed by using a comprehensive progress deviation cloud map and environmental variables such as tidal cycles. Through spectral clustering, domain coupling characteristic projections are extracted to form a Y-axis subsystem correlation scale, and industry-specific regulation mechanisms such as dock and slipway deformation compensation and welding stress disturbance mapping are introduced. Finally, a topologically maintained adjustable NURBS surface is generated, enabling users to intuitively identify spatial concentration areas and key causes of progress imbalance in dynamic interactions.

[0036] In the present invention, by embedding four types of adjustment threshold parameter panels, supporting multi-dimensional touch gesture operations, and an incremental update mechanism based on GPU, real-time update and feedback response of the progress surface are achieved; a three-level critical path warning rule is constructed, combined with in-domain deviation fluctuations and coupling conflict conditions, to automatically generate abnormal time period reports and visual ripple warnings, improving the risk perception and scheduling decision-making efficiency of shipbuilding tasks in critical process stages. Brief Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of the three-dimensional coordinate mapping of the deviation cloud map according to an embodiment of the present invention. Detailed Embodiments

[0040] The following will describe the present invention in detail with reference to the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0041] It should be noted that in the specification, the mention of "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicates that the described embodiments may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. Additionally, when combining embodiments to describe a specific feature, structure or characteristic, implementing such feature, structure or characteristic in combination with other embodiments (whether explicitly described or not) should be within the knowledge scope of those skilled in the relevant art.

[0042] Generally, terms can be understood at least in part from their use in context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily aiming to convey a set of exclusive factors, but instead, at least in part depending on the context, allowing for the existence of other factors that may not be explicitly described.

[0043] As Figure 1 - Figure 2 shown, a visualization analysis method for multi-system schedule data comparison in a shipbuilding project includes the following steps:

[0044] S1, multi-system data standardization processing: Extract schedule-related feature data from the management system, human resources system, production system, financial system, and supply chain system of the shipbuilding project, perform timestamp alignment and dimension unification processing on the feature data, and generate a standardized multi-dimensional schedule feature matrix;

[0045] S2, dynamic weight assignment and schedule comparison: Based on the schedule impact factors of each system in the multi-dimensional schedule feature matrix, use an adaptive sliding window algorithm to calculate the weight coefficients of each system in real time, perform a convolution operation on the weight coefficients and the multi-dimensional schedule feature matrix, and generate a comprehensive schedule deviation cloud map with time series correlation;

[0046] S3, three-dimensional visualization model construction: Map the comprehensive schedule deviation cloud map to a three-dimensional coordinate system, where the X-axis represents the project timeline, the Y-axis represents the correlation degree of each system, and the Z-axis represents the deviation impact intensity, and generate a visualization comparison surface through a spatial interpolation algorithm;

[0047] S4, interactive intelligent analysis: Embed adjustable threshold parameters in the visualization comparison surface, adjust the time slice range and weight assignment ratio through touch interaction, update the surface morphology in real time and output a key path warning signal.

[0048] S1 specifically includes:

[0049] S11. Extract the task node completion rate, approval process response time, and project milestone deviation value from the management system; extract the labor hour saturation rate, skill matching degree, and personnel turnover rate from the human resources system; extract the sectional construction completion degree, overall equipment efficiency (OEE), and quality inspection pass rate from the production system; extract the budget execution rate, payment node achievement rate, and cost overrun coefficient from the financial system; extract the material kit completeness rate and logistics on-time rate from the supply chain system.

[0050] In the management system: the task node completion rate , the approval process response time , and the project milestone deviation value ;

[0051] In the human resources system: the labor hour saturation rate , the skill matching degree , and the personnel turnover rate ;

[0052] In the production system: the sectional construction completion degree , the overall equipment efficiency OEE, and the quality inspection pass rate ;

[0053] In the financial system: the budget execution rate , the payment node achievement rate , and the cost overrun coefficient ;

[0054] In the supply chain system: the material kit completeness rate , and the logistics on-time rate .

[0055] S12. Align the timestamps using the task node number as the correlation key, and perform two-way matching between the sectional construction timestamp in the production system and the task node timestamp in the management system: when the deviation between the hoisting completion time recorded in the production system and the node deadline set in the management system exceeds the predetermined time, based on the production system timestamp, synchronously update the actual completion time of the corresponding node in the management system.

[0056] S13. Perform dimensionality unification processing and execute outlier handling, and finally generate a standardized multi-dimensional progress feature matrix. The row vectors of the matrix represent time series segments, and the column vectors are arranged by domain as follows: management domain (3 dimensions), human domain (3 dimensions), production domain (3 dimensions), financial domain (3 dimensions), and supply chain domain (3 dimensions).

[0057] Dimensionality unification processing includes converting man-hour data into standard man-days (8 hours / man-day), normalizing the budget execution rate to a value in the range of [0, 1], binaryizing the equipment status data into a Boolean type (0 - shutdown / 1 - running), and mapping the number of days of supply chain material delay to a risk level value in the range of [0, 10] through a piecewise function; outlier processing includes performing outlier cleaning on the processed data, setting the threshold range of the task node completion rate to [0, 1.2], and interpolating the data points outside the range with the average value of adjacent time periods.

[0058] Dimensionality unification processing: Unifying man-hours into standard man-days: ; where represents the original number of man-hours, represents the standard man-day (8 hours / man-day);

[0059] Normalization of the budget execution rate: ;

[0060] Binaryization of the equipment operation status: ;

[0061] The multi-dimensional progress feature matrix is expressed as:

[0062] ;

[0063] where each row : represents the th time segment, and each column is arranged in the domain order as:

[0064] Management domain: ;

[0065] Human resources domain: ;

[0066] Production domain: , OEE ;

[0067] Finance domain: ;

[0068] Supply chain domain: ;

[0069] Finally, the Z-score method is used to standardize each column of data and retain 4 significant figures.

[0070] S2 specifically includes:

[0071] S21, extraction of progress impact factors: From the standardized multi-dimensional progress feature matrix extract the following core impact factors by dividing into five major domains:

[0072] Management domain factor : ;

[0073] Human domain factor : ;

[0074] Production domain factor : ;

[0075] Financial domain factor : ;

[0076] Supply chain domain factor : ;

[0077] S22, Adaptive sliding window algorithm:

[0078] Window initialization: ;

[0079] Among them, is the initial window length, is the total project cycle, is the sliding step size, is the personnel turnover rate;

[0080] Window adjustment mechanism: If the equipment efficiency satisfies: ;

[0081] Then adjust: ; Among them, is the current weight coefficient of the financial domain;

[0082] Supply chain risk penalty factor: When , increase the weight penalty factor: ; Among them, is the risk penalty factor, is the number of days of material delay, is the risk conduction coefficient (i.e., the Pearson correlation coefficient between material delay and schedule deviation), is the supply chain risk level value, mapped to a risk level value of [0, 10] based on the number of days of supply chain material delay through a piecewise function:

[0083] ;

[0084] is the number of days of material delay.

[0085] Special working condition detection: If the application volume of crane use in a certain time slice satisfies: , then enable: Window freezing mechanism (pause window sliding), offline weight calculation mode (perform discrete optimization based on historical segments).

[0086] S23, Convolution operation design:

[0087] Convolution kernel setting: The shape of the convolution kernel is set to: , where is the time window length, 1 represents spatial sliding (fixed), and 5 represents the five-domain feature channel;

[0088] Convolution kernel initialization: The initial inter-domain correlation strength matrix takes values as: ; Management domain and production domain: 0.7, finance domain and supply chain domain: 0.5;

[0089] Gating mechanism: If , then close the convolution channel of the finance domain: ;

[0090] Tidal cycle compensation parameter: According to the tidal cycle of the dock location Adjust the time distribution function of the production domain weight : ; where represents the original production domain weight coefficient at time point , which is used to measure the influence degree of the production domain on the comprehensive progress deviation at the current stage. represents the tidal cycle compensation factor at time point , which is used to adjust the time weight distribution of production activities, reflecting the influence of tidal changes (such as high tide / low tide) on the feasible time window of production tasks (such as hull hoisting, equipment installation, etc.), and is expressed as: , is the tidal cycle, is the tidal fluctuation influence amplitude (empirical value 0.1 - 0.3), is the phase adjustment constant, which is used to synchronize the tidal table and the starting time of production scheduling.

[0091] S24, Generation of comprehensive progress deviation cloud map:

[0092] Time series normalization and smoothing processing: Use the double exponential smoothing method: , where represents the smoothed sequence, represents the original convolution output, represents the smoothing factor, with a value range of 0.2 - 0.3;

[0093] Feature decoupling: Decompose the convolution output signal into: , where represents the systematic deviation, represents the random fluctuation component;

[0094] Cloud map color mapping: Map the intensity of the decoupled deviation components to the RGB three channels respectively:

[0095] .

[0096] S3 specifically includes:

[0097] S31, 3D coordinate mapping rule:

[0098] X-axis: Timeline mapping: Use piecewise non-linear coordinate scales. Among them, the project planned timeline uses a compression ratio of 1:1, and the actual progress timeline dynamically expands and contracts according to the deviation intensity. The expansion and contraction factor formula is as follows:

[0099] ; where is the timeline expansion and contraction factor, is the normalized deviation intensity from the Z-axis of the comprehensive progress deviation cloud map;

[0100] Y-axis: System correlation mapping: Construct a five-domain basic correlation matrix , and the example elements include:

[0101] , use the spectral clustering method to perform eigen-decomposition on the matrix, extract the first principal component vector , and map it to the Y-axis to form a subsystem correlation scale;

[0102] Z-axis: Deviation intensity mapping: Perform a logarithmic transformation on the cloud map deviation intensity to enhance the perception of differences:

[0103] ; where is the absolute deviation value of the current time slice, is the 90th percentile of the historical project progress deviation intensity (set as the logarithmic benchmark).

[0104] S32, Optimization of spatial interpolation algorithm: Dynamic Kriging interpolation. When the overall equipment effectiveness (OEE) of the production domain equipment , introduce a radial basis function (RBF) penalty term into the interpolation function: , for the area of the budget execution rate in the financial domain, enable the anisotropic interpolation strategy and expand the search neighborhood in the time axis direction to: ; is the standard deviation of the progress indicators in the time series.

[0105] S33, Visualization surface generation: Use 3D interpolation point clouds to generate a NURBS surface (Non-Uniform Rational B-Spline), and set the number of control points to: , Indicates the number of valid task nodes within the current time window;

[0106] Special constraints for the curved surface: For peak hoisting periods (09:00–11:00 and 14:00–16:00), set the maximum curvature threshold to prevent excessive deformation during visualization; when multiple dockyards are operating in parallel, automatically generate a subdivision surface structure according to the topology preservation conditions.

[0107] Also includes dynamic rendering enhancement:

[0108] Establish a color-deviation type mapping relationship:

[0109] Red channel intensity = production domain deviation intensity × 0.8 + supply chain deviation intensity × 0.2;

[0110] Blue channel intensity = finance domain deviation intensity × 0.6 + management domain deviation intensity × 0.4;

[0111] Green channel intensity = human resources domain deviation intensity × 0.7 + cross-domain coupling deviation × 0.3;

[0112] Overlay equal deviation lines on the surface of the curved surface, and the line width changes dynamically with the tidal height. The line width is amplified to 1.5 times during the flood tide period.

[0113] S4 specifically includes:

[0114] S41, embedding adjustable threshold parameters, setting dynamic adjustment panels at the four vertices of the visualization comparison curved surface, corresponding to respectively:

[0115] ① Production beat tolerance threshold (range [0.8, 1.2] times the benchmark beat);

[0116] ② Human resources saturation threshold (set in the range of [70%, 130%] according to job types);

[0117] ③ Supply chain risk diffusion coefficient (graded adjustment levels 1 - 10);

[0118] ④ Financial budget elasticity coefficient (continuous adjustment range 0.5 - 2.0);

[0119] The threshold parameters are dynamically bound to the color temperature of the curved surface vertices. When the threshold is adjusted, the vertex color rotates clockwise by the corresponding angle along the HSV color wheel;

[0120] S42, touch interaction logic design:

[0121] Time slice adjustment uses a two-finger pinch gesture:

[0122] ① Horizontal sliding controls the start and end points of the time window, with an accuracy of up to 15 minutes;

[0123] ② Vertically pinch and zoom to adjust the window density, supporting six levels of zoom from hourly to weekly;

[0124] The weight allocation ratio adjustment is achieved through the surface depression gesture:

[0125] ① Long - press the surface area with a single finger to trigger the weight editing mode;

[0126] ② The depth of pressing along the surface normal direction is proportional to the reduction amplitude of the weight (pressing 1 cm corresponds to a 10% reduction in weight);

[0127] ③ Sliding friction coefficient feedback mechanism: When the adjustment amplitude exceeds 3 times the standard deviation of historical data, a vibration alarm is triggered;

[0128] S43, Real - time update mechanism:

[0129] Establish an incremental recomputation pipeline:

[0130] ① After capturing the interaction instruction, preferentially update the subset of the feature matrix in the affected domain (the update granularity is controlled within the range of 10% of the data);

[0131] ② Use a lightweight convolution kernel (3×3×3) for local weight convolution, skipping the previously mentioned depth - separable convolution;

[0132] ③ The interpolation operation reuses the historical surface control point topology and only updates the Kriging interpolation patch for the changed area;

[0133] S44, Critical path warning generation:

[0134] Set the triggering conditions for three - level warnings:

[0135] ① Yellow warning: The deviation intensity of a single domain is continuously > 2 times the standard deviation of the benchmark value in 3 consecutive window periods;

[0136] ② Orange warning: The product of the associated deviation intensities of two domains > 80% of the historical maximum value;

[0137] ③ Red warning: The deviation intensity of the production domain × the supply chain risk value > 10 and the human resource saturation < 65%;

[0138] The warning signal output includes:

[0139] ① Generate a pulsating circular ripple diffusion special effect in the abnormal surface area;

[0140] ② Automatically capture the abnormal time slice to generate a PDF report, including:

[0141] The topological graph of the affected task nodes (referencing the feature data in S1);

[0142] The weight adjustment trend curve (associated with the window parameters in S1).

[0143] The present invention encompasses any alternatives, modifications, equivalent methods, and solutions made to the essence and scope of the present invention. For the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without the description of these details. Additionally, well-known methods, processes, flows, components, and circuits, etc. are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0144] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A visual analysis method for comparing multi-system progress data in a shipbuilding project, characterized in that, It includes the following steps: S1. Multi-system data standardization processing: Extract progress-related feature data from the management system, human resources system, production system, financial system, and supply chain system of the shipbuilding project, perform timestamp alignment and dimension unification processing on the feature data, and generate a standardized multi-dimensional progress feature matrix; S2. Dynamic weight allocation and progress comparison: Based on the progress impact factors of each system in the multi-dimensional progress feature matrix, use the adaptive sliding window algorithm to calculate the weight coefficients of each system in real time, perform convolution operation on the weight coefficients and the multi-dimensional progress feature matrix, and generate a comprehensive progress deviation cloud map with time series correlation; S3. Three-dimensional visualization model construction: Map the comprehensive progress deviation cloud map to a three-dimensional coordinate system, where the X-axis represents the project timeline, the Y-axis represents the correlation degree of each system, and the Z-axis represents the deviation impact intensity, and generate a visual comparison surface through the spatial interpolation algorithm; S4. Interactive intelligent analysis: Embed adjustable threshold parameters in the visual comparison surface, adjust the time slice range and weight allocation ratio through touch interaction, update the surface form in real time and output the critical path warning signal.

2. A visual analysis method for comparing multi-system progress data in a shipbuilding project according to claim 1, characterized in that The specific content of S1 includes: S11. Extract the task node completion rate, approval process response duration, and project milestone deviation value from the management system; extract the work type man-hour saturation, skill matching degree, and personnel turnover rate from the human resources system; extract the section construction completion degree, equipment overall efficiency, and quality inspection pass rate from the production system; extract the budget execution rate, payment node achievement rate, and cost overrun coefficient from the financial system; extract the material kit completion rate and logistics on-time rate from the supply chain system; S12. For timestamp alignment, use the task node number as the correlation key to perform two-way matching between the section construction timestamp of the production system and the task node timestamp of the management system: When the deviation between the hoisting completion time recorded by the production system and the node deadline set by the management system exceeds the predetermined time, based on the production system timestamp, synchronously update the actual completion time of the corresponding node in the management system; S13. Perform dimension unification processing and execute outlier processing, and finally generate a standardized multi-dimensional progress feature matrix. The row vector of the matrix represents the time series segment, and the column vector is arranged by domain as: management domain, human domain, production domain, financial domain, supply chain domain.

3. A visual analysis method for comparing multi-system progress data in a shipbuilding project according to claim 1, characterized in that, The dimension unification processing includes converting man-hour data into standard man-days, normalizing the budget execution rate to a value in the range of [0, 1], binaryizing the equipment status data into a Boolean type, and mapping the supply chain material delay days to a risk level value in the range of [0, 10] through a piecewise function; the outlier processing includes performing outlier cleaning on the processed data, setting the task node completion rate threshold range of [0, 1.2], and interpolating the data points outside the range with the average value of adjacent time periods.

4. A visual analysis method for comparing multi-system progress data in a shipbuilding project according to claim 1, characterized in that, The specific content of S2 includes: S21. Progress impact factor extraction: Separate the core impact factors from the multi-dimensional progress feature matrix by domain, including management domain factors, human domain factors, production domain factors, financial domain factors, and supply chain domain factors; S22. Adaptive sliding window algorithm execution: Initialize the window length based on the total project cycle, with the step size being the reciprocal of the human resource turnover rate; when it is detected that the overall equipment efficiency in the production domain has dropped too much for multiple window periods, automatically shorten the window length; if the supply chain risk level value breaks through the risk threshold, then superimpose the supply chain risk penalty factor when the window slides. The supply chain risk level value is mapped to a supply chain risk level value in the range of [0, 10] based on the supply chain material delay days through a piecewise function. S23. Convolution operation design: Construct a three-dimensional convolution kernel, whose time dimension length matches the adaptive sliding window, and the spatial dimension corresponds to the five-domain feature channels; perform depthwise separable convolution on the dynamic weight coefficient matrix and the multi-dimensional progress feature matrix, and initialize the convolution kernel weights using the inter-domain correlation strength matrix. S24. Generation of the comprehensive progress deviation cloud map: Perform temporal normalization processing on the convolution output, and separate the deviation and random fluctuation components through feature decoupling technology; map the deviation intensity to the RGB color space, where the red channel represents the dominant deviation in the production domain, the blue channel represents the dominant deviation in the supply chain domain, and the brightness of the green channel is positively correlated with the deviation intensity in the financial domain to form the comprehensive progress deviation cloud map.

5. A visual analysis method for comparing multi-system schedule data in a shipbuilding project according to claim 4, characterized in that, The supply chain risk penalty factor is calculated as: ; among which, is the supply chain risk penalty factor, is the number of days of material delay, is the risk conduction coefficient, is the supply chain risk level value, and the risk conduction coefficient is determined according to the Pearson correlation coefficient between material delay and schedule deviation in historical data.

6. The visual analysis method for multi-system progress data comparison in a shipbuilding project according to claim 4, characterized in that The management domain factor is the product of the task node completion rate and the milestone deviation value; the human domain factor takes the weighted harmonic mean of the work type man-hour saturation and the skill matching degree; the production domain factor is calculated by the geometric mean of the segmented construction completion degree, the overall equipment efficiency, and the quality inspection pass rate; the financial domain factor is the ratio of the budget execution rate to the cost overrun coefficient; the supply chain domain factor is based on the product of the material completeness rate and the logistics on-time rate.

7. A visual analysis method for multi-system schedule data comparison in a shipbuilding project according to claim 1, characterized in that, The mapping rule for mapping the comprehensive progress deviation cloud map to a three-dimensional coordinate system includes: The X-axis timeline uses a piecewise non-linear scale, compressing the project plan timeline by a ratio of 1:1, and the actual progress timeline dynamically expands and contracts according to the deviation intensity. The expansion and contraction factor is calculated as: ; wherein, is the time axis scaling factor, is the normalized deviation intensity from the Z-axis of the comprehensive schedule deviation cloud map; The Y-axis correlation degree calculation uses a cross-domain coupling algorithm: Construct a five-domain correlation matrix, set the basic correlation weight between the management domain and the production domain, and set the dynamic correlation weight between the supply chain domain and the financial domain to the square root of the budget execution rate; extract the eigenvectors through cluster analysis, and project the first principal component onto the Y-axis to form the correlation degree scale for each system. The Z-axis intensity mapping uses logarithmic processing, and sets the reference intensity value based on the historical project progress deviation. The spatial interpolation algorithm includes embedding dynamic constraint conditions in the standard Kriging interpolation process. The generation of the visualization comparison surface includes converting the interpolated three-dimensional point cloud data into a NURBS surface, and the number of surface control points takes the square root of the number of valid task nodes within the current time window, and special constraint conditions are set during the surface parameterization process.

8. A visual analysis method for comparing multi-system progress data in a shipbuilding project according to claim 7, characterized in that The dynamic constraint conditions include: ① When the overall equipment efficiency of the production domain equipment is lower than the efficiency threshold, a radial basis function penalty term is added to the interpolation equation, and the penalty coefficient λ is calculated as: ; ② For the area where the budget execution rate in the financial domain is lower than 70%, adopt an anisotropic interpolation strategy, and expand the search neighborhood along the time axis direction to a range of 2 times the standard deviation.

9. A visual analysis method for comparing multi-system progress data in a shipbuilding project according to claim 1, characterized in that, The interactive intelligent analysis in S4 includes embedding adjustable threshold panels at the four vertices of the visualization comparison surface, and respectively setting the production beat tolerance threshold, the human resource saturation threshold, the supply chain risk diffusion coefficient, and the financial budget flexibility coefficient. When the threshold is adjusted, the surface color temperature is driven to change dynamically according to the HSV color ring.

10. A visual analysis method for comparing multi-system schedule data in a shipbuilding project according to claim 9, characterized in that The interactive intelligent analysis also includes adjusting the time slice range and weight allocation ratio based on touch gestures, and using incremental recalculation to update the surface shape in real time. At the same time, a three-level critical path warning is generated according to the multi-domain deviation intensity and its correlation relationship, and an exception report is output.

Images