Railway construction data processing method and system

Abstract

The present application relates to the field of data processing technology, and discloses a method and system for processing railway construction data. The method comprises: semantically annotating track laying, line measurement and construction monitoring data through RDF semantic association to obtain a semantic data set; setting smoothness constraints based on gauge deviation and elevation deviation to filter qualified data; inputting qualified data into an improved fireworks algorithm, and optimizing track geometry parameters through a curvature adaptive explosion mechanism; using improved Kriging interpolation to complete track centerline, rail surface elevation and gauge change data; establishing a construction quality constraint matrix, and collaboratively adjusting track alignment, elevation control and gauge accuracy through a sequential quadratic programming algorithm. The present application solves the technical problems of the lack of semantic association of multi-source data, insufficient adaptability of professional algorithms, and insufficient parameter collaborative optimization capabilities in railway construction.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a railway construction data processing method and system. Background Art

[0002] Existing railway construction data processing technologies primarily rely on traditional data acquisition and analysis methods. These methods collect construction site measurement data using equipment such as total stations and GPS, and store and query them using database management systems. During data processing, statistical analysis methods are commonly used to assess track geometry quality, interpolation algorithms are used to complete missing data, and single-parameter optimization methods are used to adjust for construction deviations. These technologies play a vital role in railway construction quality control and progress management, providing data support for construction decision-making.

[0003] However, the data island phenomenon is serious, and data between different systems and departments are difficult to effectively integrate and share; data quality is uneven, and there are problems such as incomplete, inaccurate, and untimely data; data processing efficiency is relatively low, and it relies heavily on manual operations, and the degree of automation is not high; there is a lack of unified data standards and specifications, resulting in inconsistent data formats, making effective comparison and analysis difficult; the level of intelligence needs to be improved, and there is a lack of advanced data mining and artificial intelligence technology applications; there is mutual interference in the parameter adjustment process, and the independent adjustment of a single parameter often leads to the deterioration of the quality of other parameters.

[0004] Based on the analysis of the limitations of the above-mentioned existing technologies, we can infer deeper technical problems: due to the lack of semantic association mechanism for multi-source heterogeneous data, the logical relationship between data cannot be effectively established; due to the lack of dedicated optimization algorithms for the characteristics of railway engineering, data processing cannot adapt to the professional constraints of track geometry; due to the lack of multi-parameter coordinated adjustment mechanism, the problem of neglecting one thing while focusing on another occurs during the parameter optimization process, and the overall improvement of track geometry quality cannot be achieved. Summary of the Invention

[0005] The present application provides a railway construction data processing method and system for solving the technical problems of missing semantic association of multi-source data, insufficient adaptability of professional algorithms, and insufficient parameter collaborative optimization capabilities in railway construction.

[0006] In the first aspect, the present application provides a railway construction data processing method, which includes: semantically annotating track laying data, line measurement data and construction monitoring data through RDF semantic association to obtain a track construction semantic data set; based on the gauge deviation and elevation deviation in the track construction semantic data set, quality screening of the construction data is performed by setting track smoothness constraints to obtain qualified construction data; the qualified construction data is input into an improved fireworks algorithm, and the track geometric parameters are optimized through a track curvature adaptive explosion mechanism to obtain track parameter optimization data; based on the track parameter optimization data, the track centerline, rail surface elevation and gauge change are completed using an improved Kriging interpolation method to obtain complete track geometry data; a construction quality constraint matrix is ​​established based on the complete track geometry data, and the track alignment, elevation control and gauge accuracy are collaboratively adjusted through a sequential quadratic programming algorithm to obtain construction data results.

[0007] In a second aspect, the present application provides a railway construction data processing system, the railway construction data processing system comprising:

[0008] The annotation module is used to perform semantic annotation processing on track laying data, line measurement data, and construction monitoring data through RDF semantic association to obtain a track construction semantic dataset;

[0009] a screening module for performing quality screening on the construction data by setting track smoothness constraints based on the track gauge deviation and elevation deviation in the track construction semantic dataset to obtain qualified construction data;

[0010] An optimization module is used to input the qualified construction data into an improved fireworks algorithm, optimize the track geometric parameters through a track curvature adaptive explosion mechanism, and obtain track parameter optimization data;

[0011] A completion module is used to complete the track centerline, track surface elevation and track gauge changes using an improved Kriging interpolation method based on the track parameter optimization data to obtain complete track geometry data;

[0012] The collaborative module is used to establish a construction quality constraint matrix based on the complete track geometry data, and to coordinately adjust the track alignment, elevation control and gauge accuracy through a sequential quadratic programming algorithm to obtain construction data results.

[0013] In a third aspect, a railway construction data processing device is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the railway construction data processing device executes the above-mentioned railway construction data processing method.

[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned railway construction data processing method.

[0015] The technical solution provided in this application uses RDF semantic association technology to semantically annotate track laying data, line measurement data, and construction monitoring data, effectively solving the technical problem of difficult unified management of multi-source heterogeneous data in the railway construction field. It establishes logical associations between data and eliminates the data island phenomenon in traditional methods. At the same time, by setting track smoothness constraints to screen the quality of construction data, a unified data quality evaluation standard is established, avoiding the problem of uneven data quality. The improved fireworks algorithm combined with the application of the track curvature adaptive explosion mechanism enables the algorithm to dynamically adjust the search strategy according to the track alignment characteristics, performing fine searches in small curvature radius segments and coarse searches in straight segments, significantly improving the accuracy and efficiency of parameter optimization. The improved Kriging interpolation method dynamically adjusts the interpolation parameters based on the track curvature radius, making the interpolation process better adapted to the geometric characteristics of railway projects, effectively solving the problem of insufficient accuracy of traditional interpolation methods under complex alignment conditions. The introduction of the sequential quadratic programming algorithm realizes the coordinated adjustment of track alignment, elevation control, and gauge accuracy parameters, eliminating the mutual interference caused by single parameter adjustment, and ensuring the integrity and consistency of track geometric quality.

[0016] The triple structure of the RDF semantic association algorithm is particularly suitable for describing the complex relationships between entities in railway engineering. Its subject-predicate-object expression can accurately reflect the associations between objects such as track plates, measurement points, and construction processes, providing a structured semantic foundation for subsequent data processing. The core contribution of the improved track curvature adaptive mechanism in the Fireworks algorithm lies in combining the algorithm's search behavior with the professional constraints of railway engineering. This gives the algorithm domain expertise when processing track geometric parameters, avoiding the limitations of general algorithms that are difficult to adapt to professional needs. The dynamic parameter adjustment feature of the improved Kriging interpolation method enables the interpolation accuracy to adapt to the complexity of the track line shape, significantly improving the reliability of the interpolation results while ensuring computational efficiency. The iterative solution characteristics and constraint processing capabilities of the sequential quadratic programming algorithm make multi-parameter collaborative optimization possible. Its characteristic of gradually approaching the optimal solution is particularly suitable for handling the complex constraint relationships between parameters in railway construction, achieving a collaborative effect that cannot be achieved by traditional single-parameter optimization methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a schematic diagram of an embodiment of a railway construction data processing method in an embodiment of the present application;

[0019] Figure 2 This is a schematic diagram of an embodiment of a railway construction data processing system in an embodiment of the present application;

[0020] Figure 3 It is a schematic block diagram of the structure of the railway construction data processing equipment in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The embodiments of the present application provide a method and system for processing railway construction data. The terms "first," "second," "third," "fourth," and so on (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this way are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatus.

[0022] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 An embodiment of the railway construction data processing method in the embodiment of the present application includes:

[0023] Step S101: semantically annotating the track laying data, line measurement data, and construction monitoring data through RDF semantic association to obtain a track construction semantic dataset;

[0024] Step S102: Based on the track gauge deviation and elevation deviation in the track construction semantic dataset, the construction data is quality screened by setting track smoothness constraints to obtain qualified construction data;

[0025] Step S103: Input the qualified construction data into the improved fireworks algorithm, optimize the track geometric parameters through the track curvature adaptive explosion mechanism, and obtain track parameter optimization data;

[0026] Step S104: Using the improved Kriging interpolation method based on the track parameter optimization data, the track centerline, track surface elevation, and track gauge changes are completed to obtain complete track geometry data;

[0027] Step S105: Establish a construction quality constraint matrix based on the complete track geometry data, and coordinately adjust the track alignment, elevation control, and gauge accuracy through a sequential quadratic programming algorithm to obtain construction data results.

[0028] It is understandable that the execution subject of this application can be a railway construction data processing system, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0029] Specifically, unified semantic annotation is performed on multi-source heterogeneous railway construction data through RDF semantic associations. RDF, or Resource Description Framework, uses a subject-predicate-object triple structure to describe relationships between data. Track laying data, which includes information such as track plate location coordinates and laying time series, is converted into semantic labels through ontology category mapping. For example, "track plate number TB001 is located at mileage K10+500" is mapped to a semantic triple. Line measurement data covers spatial information such as mileage coordinates and elevation coordinates. A spatiotemporal relationship triple structure is established, mapping coordinate points to mileage pile numbers. Construction monitoring data includes quality parameters such as gauge measurements and elevation test results. Attribute value annotation is performed to associate numerical data with quality standards. After the three types of data are fused and processed in an RDF graph database, a unified multi-source data semantic mapping table is formed, ultimately establishing a track construction semantic dataset.

[0030] Quality screening is performed on the gauge deviation and elevation deviation in the semantic dataset. Gauge deviation refers to the difference between the measured gauge and the standard gauge of 1435 mm, and elevation deviation refers to the difference between the measured track surface elevation and the designed elevation. Through numerical range judgment processing, the deviation data is classified according to the amplitude. Track smoothness constraints include the allowable range of gauge deviation and the allowable range of elevation deviation, which are set based on railway technical standards. The deviation values ​​of each measuring point are compared and screened point by point, and data outside the allowable range is marked as constraint violation. The Boolean logic judge performs binary evaluation on the identification data, marking qualified data as true and unqualified data as false. Based on the evaluation results, qualified construction data that meets the quality requirements is extracted from the original data.

[0031] An improved fireworks algorithm is used to optimize the track geometry parameters. The fireworks algorithm is a swarm intelligence optimization algorithm that performs a global search by simulating the fireworks explosion process. The track geometry parameters in the qualified construction data are used as the initial position coordinates of the fireworks individuals to form a population. The track curvature adaptive explosion mechanism dynamically adjusts the explosion radius according to the track curvature radius. Small curvature radius sections use a smaller explosion radius for a fine search, while large curvature radius sections use a larger explosion radius to expand the search range. Each firework individual randomly generates multiple spark positions within its explosion radius to form a set of candidate solutions. The track superelevation gradient constraint condition is used to evaluate the fitness of the spark position. Sparks with superelevation gradient rates exceeding the limit are assigned lower fitness values. Excellent sparks are selected according to fitness ranking to update the fireworks position. After multiple iterations, the track parameter optimization data is obtained.

[0032] The improved Kriging interpolation method is used to complete the track geometry data. Kriging interpolation is a spatial interpolation method based on the theory of regionalized variables, which uses the spatial correlation of known points to predict the values ​​of unknown points. First, the track centerline coordinates, track surface elevation and gauge change data are separated and extracted from the optimized data. The Kriging interpolation parameters are dynamically adjusted according to the track curvature radius. The range parameter controls the effective distance of spatial correlation, and the nugget effect parameter reflects the influence of measurement error. A semi-variance function is established to describe the spatial correlation structure, and the spatial correlation matrix between known measuring points is calculated. The interpolation weight coefficient is solved through matrix operation, and the weight reflects the contribution of each known point to the interpolation point. The missing positions on the track line are weighted averaged according to the weight coefficient to obtain the completed track geometry data.

[0033] Establish a construction quality constraint matrix for coordinated adjustment. Extract track alignment parameters, elevation control parameters, and gauge accuracy parameters from the complete geometric data and group them. There are mutual constraints between the parameters. For example, changes in the track centerline position will affect the gauge value, and elevation adjustments will affect the track superelevation. Organize these constraints into a matrix form, and the matrix elements represent the constraint coefficients between the parameters. The sequential quadratic programming algorithm is a numerical method for dealing with constrained optimization problems. It gradually approaches the optimal solution by constructing quadratic programming sub-problems. Set the track centerline coordinate constraint range, the track surface elevation constraint range, and the gauge change constraint range as optimization boundary conditions. The algorithm obtains the adjustment increment value of each parameter through iterative calculation, superimposes the increment on the original parameter value to complete the numerical update, and finally obtains construction data results that meet quality requirements.

[0034] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0035] Perform ontology category mapping on the track plate position information and laying sequence information in the track laying data to obtain the track entity semantic label;

[0036] Based on the mileage coordinates and elevation coordinates in the line measurement data, a spatiotemporal relationship triple structure is established to obtain a semantic relationship graph of the measurement data;

[0037] Based on the quality inspection parameters and construction process parameters in the construction monitoring data, attribute value annotation processing is performed to obtain the construction process semantic attribute set;

[0038] The track entity semantic labels, measurement data semantic relationship graph and construction process semantic attribute set are input into the RDF graph database for fusion processing to obtain the multi-source data semantic mapping table;

[0039] According to the multi-source data semantic mapping table, a subject-predicate-object relationship description is established for each data source to obtain the track construction semantic dataset.

[0040] Specifically, the ontology category mapping process for track plate location information and installation sequence information utilizes a predefined railway engineering ontology library for data conversion. Track plate location information includes attributes such as track plate number, installation coordinates, and mileage pile number, while installation sequence information records the track plate installation sequence and timestamp. The ontology category mapping reorganizes this raw data according to semantic classification standards: the track plate number is mapped to an entity identifier, the installation coordinates are mapped to spatial attributes, the mileage pile number is mapped to a location attribute, and the installation time is mapped to a temporal attribute. Using the ontology mapping rules, the raw data "Track plate TB001 installed at mileage K15+200, coordinates (125.6, 89.3)" is converted into the semantic labels "Entity: TB001 Attribute: Location Value: K15+200" and "Entity: TB001 Attribute: Coordinate Value: (125.6, 89.3)." This mapping process converts unstructured text descriptions into standardized semantic representations, establishing a clear correspondence between track entities and their attributes.

[0041] Mileage coordinates and elevation coordinates establish a spatiotemporal relationship. A triplet structure combines spatial location information with time information to form a four-dimensional data model. Mileage coordinates represent the longitudinal position on the track, elevation coordinates indicate the vertical height of the track surface relative to the datum, and time information records the specific moment of measurement or construction. The triplet structure uses a "subject-relationship-object" representation, where the subject is typically the mileage station number, the relationship describes the spatial or temporal connection, and the object is a specific coordinate value or time stamp. For example, the elevation measurement data at mileage K10+500 is constructed as the triplet "K10+500-elevation value-245.67 meters" and "K10+500-measurement time-March 15, 2024, 10:30." Multiple triples form an association network through common subjects or objects, forming a semantic relationship graph for measurement data. This relationship graph clearly expresses the spatial adjacency and temporal sequence between different measurement points, resolving the issue of ambiguous spatial relationships in traditional data tables. The attribute value annotation processing of quality inspection parameters and construction process parameters uses a preset attribute classification system to semantically describe numerical data. Quality inspection parameters include geometric indicators such as gauge measurement, track deviation, height deviation, and horizontal deviation. Construction process parameters cover process information such as track slab laying process, fine-tuning operation process, and inspection and acceptance process. Attribute value annotation associates numerical data with quality standards and process specifications. For example, the gauge measurement value of 1437 mm is annotated as "Deviation Type: Positive Deviation Deviation Amplitude: 2 mm Quality Grade: Qualified." The fine-tuning operation in the construction process parameters is annotated as "Process Type: Geometric Adjustment Adjustment Object: Elevation Adjustment Amplitude: 3 mm Adjustment Direction: Upward Adjustment." Through attribute annotation processing, the originally isolated numerical values ​​have acquired clear engineering meaning and quality evaluation, forming a structured set of construction process semantic attributes.

[0042] The RDF graph database fusion process integrates three types of semantic data into a unified knowledge graph structure. The semantic labels of track entities serve as nodes in the graph, the semantic relationship graph of measurement data serves as edges in the graph, and the semantic attribute sets of construction processes serve as attribute information of nodes and edges. The fusion process first identifies duplicate records describing the same track entity in different data sources and eliminates data redundancy through an entity alignment algorithm. Then, a cross-reference relationship is established between data sources, such as establishing an association link between the track plate entity and its corresponding measurement data and construction process data. The fusion algorithm uses graph merging technology to combine scattered semantic fragments into a connected knowledge network, forming a multi-source data semantic mapping table. This mapping table records the correspondence and attribute inheritance relationships between entities in each data source, supporting semantic queries and reasoning across data sources.

[0043] Subject-predicate-object relationship description processing converts the relationship information in the mapping table into the standard RDF triple format. The subject represents specific entities in track construction, such as track slabs, measurement points, construction operations, etc.; the predicate describes the type of relationship between entities, such as "is located at", "is measured at", "is constructed at", etc.; the object represents the target object or attribute value of the relationship. The relationship description process traverses each record in the mapping table, extracts the entity identifier, relationship type, and associated object, and generates triples according to the RDF specification. For example, "Track slab TB001 is located at mileage K15+200" is described as the triple <TB001, is located at, K15+200>, and "The elevation of mileage K15+200 is 245.67 meters" is described as <K15+200, elevation, 245.67>. Through relationship description processing, all track construction data is converted into a unified triple representation, forming a track construction semantic dataset. This dataset has good semantic expression ability and query and reasoning ability, and solves the problems of inconsistent original data formats and unclear semantic relationships.

[0044] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0045] Extract the gauge deviation value and elevation deviation value from the track construction semantic dataset for numerical range determination processing to obtain the deviation parameter classification result;

[0046] Set the allowable range of gauge deviation and the allowable range of elevation deviation according to the deviation parameter classification result for constraint condition establishment processing to obtain the track smoothness constraint condition set;

[0047] Based on the track smoothness constraint condition set, perform point-by-point comparison and screening processing on the gauge deviation value and elevation deviation value to obtain the constraint violation identification data;

[0048] Input the constraint violation identification data into a Boolean logic judge for qualification evaluation processing to obtain the construction data quality evaluation result; <G

[0049] Extract qualified data from the original construction data according to the construction data quality evaluation result to obtain qualified construction data.

[0050] Specifically, the extraction of gauge deviation and elevation deviation values ​​identifies and extracts key geometric parameters from the track construction semantic dataset. The gauge deviation value refers to the difference between the measured track gauge and the standard gauge of 1435 mm. It is obtained by parsing the gauge measurement triples in the semantic dataset. For example, a deviation value of +2 mm is calculated from "<measurement point K20+300, gauge measurement value, 1437>." The elevation deviation value refers to the difference between the measured track surface elevation and the designed elevation. It is obtained by comparing the semantic data of the measured elevation with the designed elevation. The value range determination process classifies data according to the magnitude of the deviation: small deviation data is classified as fine-tuning range, medium deviation data is classified as adjustment range, and large deviation data is classified as rework range. The determination algorithm traverses all deviation values ​​and automatically classifies them according to preset threshold intervals, generating a deviation parameter classification result. This result includes the deviation magnitude, deviation direction, and category information for each measurement point. The set value boundaries for the allowable gauge and elevation deviation ranges are determined based on railway technical standards and construction specifications. The permissible range of track gauge deviation is determined by the line grade and train speed. The track gauge deviation for high-speed railways is controlled within plus or minus 2 mm, while that for conventional railways is relaxed to plus or minus 3 mm. The permissible range of elevation deviation is set according to the track type and accuracy requirements. The elevation deviation for ballastless tracks is controlled within plus or minus 1 mm, while that for ballasted tracks is relaxed to plus or minus 2 mm. The constraint establishment process converts these permissible ranges into computer-recognizable logical expressions to establish a set of track smoothness constraints. This set of constraints includes three types: upper limit constraints, lower limit constraints, and combined constraints. Upper limit constraints limit the maximum value of the deviation, lower limit constraints limit the minimum value of the deviation, and combined constraints simultaneously consider the mutual influence between track gauge and elevation.

[0051] The point-by-point comparison and screening process compares the deviation value of each measuring point with the constraint condition set one by one. The comparison algorithm reads the gauge deviation and elevation deviation values ​​of the measuring point, and compares them with the corresponding allowable ranges to determine whether they exceed the constraint boundary. The measuring points that exceed the allowable range of gauge deviation are marked as gauge constraint violations, and the measuring points that exceed the allowable range of elevation deviation are marked as elevation constraint violations. The measuring points that violate both constraints are marked as composite constraint violations. The screening process uses a point-by-point scanning method to check the deviation of each measuring point in mileage order, and record the specific type of constraint violation and the deviation value. The constraint violation identification data is represented by binary coding, with gauge violation marked as 1, elevation violation marked as 2, composite violation marked as 3, and qualified data marked as 0, forming a digital quality evaluation mark.

[0052] The Boolean logic judger performs logical operations on constraint violation identification data, converting numeric identifications into Boolean quality assessments. The judger uses basic operations such as logical AND, logical OR, and logical NOT to establish quality assessment rules. The conformity assessment process inputs identification data into pre-set logical judgment rules. Data with an identification value of 0 outputs a true value, indicating conformity, while data with a non-zero identification value outputs a false value, indicating failure. The judger also performs complex logical operations. For example, if multiple consecutive points within a measurement point segment exhibit deviation violations, the entire segment is marked as unconformity. The evaluation algorithm considers the spatial continuity and numerical magnitude of the deviations, establishing a graded evaluation system where minor violations are marked as warnings and severe violations as failures, generating the construction data quality assessment results. The qualified data extraction process uses the quality assessment results to filter out data records that meet the requirements from the raw construction data. The extraction algorithm iterates through the evaluation results of all measurement points, retaining data from points that evaluate to true and removing data from points that evaluate to false. The extraction process considers not only the conformity of individual points but also the continuity between adjacent points, avoiding data sequence interruptions caused by the removal of individual outliers. The algorithm uses sliding window technology to maintain the spatial continuity of the data while ensuring data quality. Qualified construction data includes gauge measurements and elevation measurements that have passed quality screening, along with their corresponding mileage location information.

[0053] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0054] The track geometry parameters in the qualified construction data are used as the initial positions of the fireworks individuals to perform population initialization processing to obtain the initial fireworks population;

[0055] According to the numerical value of the trajectory curvature radius of each firework in the initial firework population, the corresponding explosion radius is adaptively adjusted to obtain the curvature adaptive explosion radius;

[0056] Based on the curvature adaptive explosion radius, each firework individual is subjected to random position explosion generation processing in the search space to obtain a set of spark position coordinates;

[0057] Substitute the spark position coordinate set into the track superelevation gradient constraint condition to perform fitness numerical evaluation processing and obtain the spark fitness evaluation result;

[0058] According to the spark fitness evaluation results, the optimal spark is selected according to the order of merit for position update and algorithm iteration to obtain the orbit parameter optimization data.

[0059] Specifically, the population initialization process uses track geometric parameters as the initial positions of individual fireworks, converting qualified construction data into a numerical vector that the algorithm can process. Track geometric parameters include the horizontal and vertical coordinates of the track centerline, the track surface elevation, and the track gauge value. The geometric parameters of each measurement point form a multidimensional vector, which is considered a firework individual in the algorithm. The population initialization process arranges the geometric parameter vectors of qualified measurement points in mileage order to form a collection of firework individuals. The position coordinates of each firework individual consist of four components, corresponding to the spatial geometric characteristics of the track. The determination of the initial position directly affects the algorithm's search starting point and convergence direction. Therefore, population initialization adopts a uniform distribution strategy to ensure good dispersion of firework individuals in the solution space. The population size is determined based on the length of the construction section and the density of measurement points, typically set to one-tenth the number of measurement points, to ensure search adequacy while limiting computational complexity. The adaptive adjustment of the numerical calculation of the track curvature radius to the explosion radius reflects the invention's specialized focus on railway engineering. The track curvature radius is calculated from the coordinates of three adjacent measurement points and reflects the curvature of the track line; a smaller curvature radius indicates a sharper curve. An adaptive adjustment mechanism dynamically sets the explosion radius of each individual firework based on the curvature radius. Smaller curvature radii correspond to smaller explosion radii, while larger curvature radii correspond to larger explosion radii. The adjustment algorithm first calculates the track curvature radius at each individual firework's location and then determines the explosion radius using a preset mapping relationship. This mapping relationship uses a piecewise linear function. When the curvature radius is less than the straight segment threshold, the explosion radius is proportionally reduced. When the curvature radius is greater than the transition curve threshold, the explosion radius is proportionally increased. This adaptive mechanism enables the algorithm to perform a detailed search in sharp curves and a coarse search in straight sections, which is consistent with the engineering practices of railway geometric design.

[0060] The randomly positioned explosion generation process is the core operation of the fireworks algorithm. It explores the solution space by generating randomly distributed sparks around each individual firework. The explosion generation process randomly generates new position coordinates within the four-dimensional geometric parameter space, centered on the current position of the firework individual and within the curvature-adaptive explosion radius. The random generation algorithm uses a Gaussian distribution to ensure that the spark positions exhibit a normal distribution within the explosion radius, with higher spark density in the center and lower density in the edges. The number of sparks generated by each individual firework is dynamically adjusted based on its fitness, with individuals with higher fitness generating more sparks and those with lower fitness generating fewer sparks. The spark position coordinates must meet the physical constraints of the track geometry, such as the track gauge must not exceed technical standards and the elevation must not produce excessive slope changes. Sparks that fall outside the constraints are regenerated or corrected to a reasonable range.

[0061] The track superelevation gradient constraint condition undergoes a fitness evaluation process, converting the spark's location coordinates into quality evaluation metrics. Track superelevation refers to the amount by which the outer edge of the track is raised relative to the inner edge, used to balance centrifugal forces when a train is operating on a curve. Superelevation gradient refers to the rate of change of superelevation along the longitudinal direction of the track. The fitness evaluation algorithm calculates track geometric indicators corresponding to each spark location, including linear continuity, elevation smoothness, and gauge consistency. The evaluation process first calculates track geometric parameters such as curvature, slope, and twist based on the spark's coordinate data, and then compares these parameters to railway technical standards. The superelevation gradient constraint requires that superelevation changes between adjacent measurement points do not exceed specified limits. Sparks that violate this constraint are assigned a lower fitness value. The fitness calculation uses a weighted summation method, combining multiple geometric indicators into a single value, with the weight coefficient determined based on the indicator's importance. A higher fitness value indicates better track geometric quality at the spark location, while a lower fitness value indicates poorer geometric quality.

[0062] The evolutionary mechanism of the Fireworks algorithm involves sorting the sparks by their fitness scores, selecting the best sparks for position updates and algorithm iteration. The sorting algorithm ranks all sparks from highest to lowest fitness, selecting the top-ranked sparks as candidates for the next generation of fireworks. The selection strategy employs an elitist principle, retaining the sparks with the highest fitness to ensure that excellent solutions are not lost during the evolutionary process. A random selection mechanism is also introduced, randomly selecting individuals from sparks with medium fitness to maintain population diversity. The position update process assigns the coordinates of the selected sparks to the corresponding fireworks individuals, completing one iteration. Iteration termination criteria include reaching a preset number of iterations, improving fitness by less than a threshold, or lack of significant improvement over multiple generations. After the algorithm converges, the positions of the fireworks individuals with the highest fitness become the trajectory parameter optimization data, representing the optimal geometric parameter combination under the given constraints.

[0063] In a specific embodiment, the process of calculating the adaptive adjustment of the explosion radius according to the trajectory curvature radius of each individual firework in the initial firework population may specifically include the following steps:

[0064] Extracting the trajectory curvature radius value corresponding to each individual firework from the initial firework population and performing numerical reading processing to obtain a curvature radius parameter set;

[0065] The curvature type classification is performed according to the numerical values ​​in the curvature radius parameter set to obtain the curvature classification identification result;

[0066] Based on the curvature classification identification result, different explosion radius scaling coefficients are set for the small curvature radius segment and the large curvature radius segment to perform coefficient allocation processing to obtain the curvature adaptive scaling coefficient;

[0067] The curvature adaptive scaling coefficient is multiplied by the basic explosion radius parameter to obtain the individual explosion radius value;

[0068] The explosion radius of each firework is assigned according to its unique explosion radius value to obtain the curvature-adaptive explosion radius.

[0069] Specifically, the reading process of the track curvature radius value calculates the geometric curvature characteristics from the position coordinates of each individual firework. The position coordinates of the individual firework contain the horizontal and vertical coordinate information of the track centerline, and the track curvature radius at that position is calculated through the coordinate relationship of three adjacent points. The calculation process adopts the curvature calculation formula in geometry and uses the principle of determining the arc of a circle with three points to obtain the curvature radius value. The reading process traverses each individual in the initial firework population, extracts its position coordinates one by one and calculates the corresponding curvature radius, and organizes the calculation results into a curvature radius parameter set according to the numbering order of the individual fireworks. This parameter set not only contains numerical information, but also retains the corresponding relationship with the position of the individual firework, ensuring the consistency of the curvature information and spatial position in subsequent processing.

[0070] The curvature type classification and determination process divides the curvature radius into different levels according to the line classification standards in railway engineering. Railway lines are usually divided into types such as straight segments, transition curve segments, and circular curve segments, and different types correspond to different curvature radius ranges. The determination process sets a curvature classification threshold and compares the value in the curvature radius parameter set with the threshold. The curvature radius of a straight segment approaches infinity, the curvature radius of a transition curve segment varies within a certain range, and the curvature radius of a circular curve segment is a fixed value. The classification algorithm uses an interval determination method to classify each curvature radius value into the corresponding line type. The curvature classification identification result is represented by a digital code, with straight segments identified as type 1, transition curve segments identified as type 2, and small radius circular curve segments identified as type 3. Each individual firework obtains a corresponding curvature type identification.

[0071] The coefficient allocation process determines the explosion radius adjustment strategy based on the characteristics of different curvature types. Small curvature radius segments correspond to sharp bends in the track, where the adjustment of geometric parameters requires higher precision. Therefore, a smaller scaling coefficient is assigned to reduce the explosion radius and concentrate the search range near the current position. Large curvature radius segments correspond to straight or gently curved areas of the track, where geometric constraints are relatively loose. Larger scaling coefficients are assigned to expand the explosion radius and cover a wider range of space. Coefficient allocation adopts a piecewise function form, and the corresponding scaling coefficient value is determined by looking up the table based on the curvature classification identification results. The scaling coefficient of small radius circular curve segments is set to a smaller value, the scaling coefficient of straight line segments is set to a larger value, and the scaling coefficient of gentle curve segments is set to a medium value. The curvature adaptive scaling coefficient set contains the scaling value corresponding to each individual firework, reflecting the algorithm's differentiated processing strategy for different linear features.

[0072] The product operation multiplies the scaling factor by the base explosion radius parameter to obtain an individual explosion radius value. The base explosion radius parameter is the standard search range preset in the fireworks algorithm and represents the algorithm's general search capability. The product operation calculates the unique explosion radius of each individual firework by multiplying each firework individually. The result maintains the search characteristics of the original algorithm while incorporating the specialized constraints of orbital geometry. The size of the individual explosion radius value directly affects the search range of the next explosion of that firework. A smaller value indicates a more detailed search, while a larger value indicates a more extensive search. The operation maintains numerical precision to prevent calculation errors from affecting subsequent search results.

[0073] The explosion radius assignment process assigns the calculated, unique explosion radius value to the corresponding individual firework. This assignment is performed sequentially according to the firework's individual numbering, ensuring that each individual receives a explosion radius that matches its location. Once assigned, firework individuals in different locations possess varying search capabilities: individuals in segments with smaller curvature radii will perform a more refined search, while those in segments with larger curvature radii will perform a more coarse search. This curvature-adaptive explosion radius becomes a crucial attribute of each individual firework, playing a key role in subsequent explosion operations and enabling the algorithm's search behavior to adapt to complex changes in trajectory shape.

[0074] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0075] Extract the track centerline coordinate points, track surface elevation values ​​and track gauge change values ​​from the track parameter optimization data, perform data separation processing, and obtain geometric parameter classification data;

[0076] According to the track curvature radius value in the geometric parameter classification data, the Kriging interpolation range parameter and the nugget effect parameter are dynamically adjusted to obtain the interpolation parameter configuration result;

[0077] Based on the interpolation parameter configuration results, a semivariogram function structure is established to calculate the spatial correlation between interpolation points and obtain a spatial correlation matrix.

[0078] The spatial correlation matrix and the known measurement point data are processed by weight coefficient solution operation to obtain an interpolation weight coefficient set;

[0079] The orbital geometry parameters of the missing positions are weighted interpolated according to the interpolation weight coefficient set to obtain the complete orbital geometry data.

[0080] Specifically, the data separation processing of the track centerline coordinate points, rail surface elevation values, and gauge change values ​​classifies and organizes multidimensional geometric parameters according to attribute types. The track parameter optimization data contains multiple geometric attributes for each measuring point, and data separation decomposes the mixed data into independent parameter sequences through an attribute recognition algorithm. The track centerline coordinate points contain two components, the horizontal coordinate and the vertical coordinate, which reflect the spatial position of the track in the horizontal plane; the rail surface elevation value represents the vertical height of the track surface relative to the reference plane, reflecting the longitudinal section characteristics of the track; the gauge change value describes the change in the inner spacing between the two rails, reflecting the cross-sectional characteristics of the track. The separation process establishes a classification index according to the data attributes, and merges the parameter values ​​of the same type into the corresponding data sequence to form three independent geometric parameter classification data sets. Each data set contains the parameter value, the corresponding mileage position, and the measurement time information, so that the correlation between the data is not destroyed. The dynamic adjustment processing of the track curvature radius value to the Kriging interpolation range parameter and the nugget effect parameter reflects the professional adaptability of the present invention to railway engineering. Kriging interpolation is an interpolation method based on spatial statistics. The range parameter controls the distance over which spatial correlation occurs, while the nugget effect parameter reflects the influence of measurement error and small-scale variation. A dynamic adjustment mechanism determines the values ​​of the interpolation parameters based on the track's alignment characteristics, with larger range parameters used for straight segments and large-radius curves and smaller range parameters for small-radius curves and transition segments. The adjustment algorithm first calculates the track curvature radius at each location in the geometric parameter classification data and then determines the corresponding interpolation parameter value based on a preset mapping function. The nugget effect parameter for ballastless track is set to a smaller value, reflecting its higher construction accuracy; the nugget effect parameter for ballasted track is set to a larger value, reflecting its relatively lower construction accuracy. The interpolation parameter configuration results include the range parameter, nugget effect parameter, and crown height parameter for each interpolation segment. The combination of these parameters determines the accuracy and adaptability of the interpolation algorithm.

[0081] The calculation and processing of spatial correlation between interpolation points using the semivariance function structure is the core step of kriging interpolation. The semivariance function describes the statistical characteristics of the numerical differences between two points at a certain distance in space, reflecting the spatial continuity and variation of the data. The calculation process first determines the mathematical model of the semivariance function. Commonly used models include spherical models, exponential models, and Gaussian models. The appropriate model type is selected based on the spatial distribution characteristics of the orbital geometry data. The spherical model is suitable for situations where spatial correlation has clear boundaries, the exponential model is suitable for situations where the correlation gradually decays, and the Gaussian model is suitable for situations where the correlation changes smoothly. The semivariance calculation uses the empirical semivariance estimation method to count the numerical differences between pairs of measurement points within different distance intervals and establish a relationship curve between distance and semivariance. The spatial correlation matrix is ​​calculated using the semivariance function. The matrix elements represent the degree of spatial correlation between any two known measurement points. The higher the degree of correlation, the more similar the values ​​of the two points are.

[0082] The spatial correlation matrix and the weight coefficient solution operation for known measurement point data convert spatially relevant information into weight distribution for interpolation calculations. The weight coefficient reflects the contribution of each known measurement point to the interpolation point value. Measurement points with close proximity and strong correlation receive greater weights, while measurement points with distant proximity and weak correlation receive smaller weights. The solution operation utilizes the matrix solution method of the Kriging equation system, establishing a linear equation system with the spatial correlation matrix as the coefficient matrix. The solution of the equation system is the weight coefficient of each measurement point. The operation process includes basic mathematical operations such as matrix inversion, matrix multiplication, and vector operations. The set of interpolation weight coefficients is obtained through numerical calculation. The weight coefficients have a normalized property, that is, the sum of all coefficients is equal to 1, ensuring the unbiased interpolation result. The weight distribution must also meet the constraints of Kriging interpolation to ensure that the interpolation process meets the theoretical requirements of spatial statistics.

[0083] The implementation phase of data completion involves weighted interpolation of the track geometry parameters at the missing locations using a set of interpolation weight coefficients. This weighted interpolation process calculates the weighted average of the parameter values ​​at each known measurement point according to the corresponding weight coefficients to produce parameter estimates for the missing locations. The calculation process iterates over all locations requiring interpolation, calculating the track centerline coordinates, track elevation, and track gauge for each location. The interpolation of the track centerline coordinates is performed independently for both the horizontal and vertical coordinates to ensure geometric continuity of the interpolated alignment. The interpolation of track elevation takes into account the continuity of longitudinal slope changes to avoid sudden changes in slope. The interpolation of track gauge maintains numerical stability to avoid outliers that exceed technical standards. The interpolation calculation also includes error estimation, using kriging variance to calculate confidence intervals for the interpolation results and assess the reliability of the interpolation accuracy. The complete track geometry data combines the original measurement point data with the interpolated data, forming a continuous sequence of track geometry parameters.

[0084] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0085] Extract track alignment parameters, elevation control parameters, and gauge accuracy parameters from the complete track geometry data, perform parameter grouping processing, and obtain a set of coordinated adjustment parameters;

[0086] According to the mutual constraint relationship between the parameters in the collaborative adjustment parameter set, a constraint condition table is established to perform matrix arrangement processing to obtain the construction quality constraint matrix;

[0087] Based on the construction quality constraint matrix, the track centerline coordinate constraint range, track surface elevation constraint range, and track gauge change constraint range are set to establish the optimization target and obtain the multi-parameter collaborative optimization target;

[0088] The multi-parameter collaborative optimization target is input into the sequential quadratic programming algorithm for step-by-step iterative solution processing to obtain the parameter adjustment increment value;

[0089] According to the parameter adjustment increment value, the track alignment, elevation control and gauge accuracy parameters are numerically updated and adjusted to obtain construction data results.

[0090] Specifically, the parameter grouping process for track alignment parameters, elevation control parameters, and gauge accuracy parameters categorizes and organizes complete track geometry data according to engineering attributes. Track alignment parameters include geometric quantities describing alignment characteristics, such as the track centerline azimuth, curvature, and torsion. These parameters control the track's planar and vertical orientation. Elevation control parameters encompass values ​​reflecting track elevation changes, such as track surface elevation, longitudinal slope, and vertical curve radius, and determine the track's longitudinal cross-sectional shape. Gauge accuracy parameters include cross-sectional characteristics such as gauge value, gauge change rate, and gauge deviation, which influence the track's transverse geometric quality. The grouping process uses an attribute recognition algorithm to extract and categorize various parameters from the complete data, establishing a correspondence between parameter type and numerical sequence. Within each parameter group, parameters are arranged in mileage order to maintain spatial continuity. Logical relationships between parameters are also recorded to form a collaboratively adjusted parameter set. This set contains not only parameter values ​​but also their importance and adjustment priority, laying the data foundation for subsequent collaborative optimization.

[0091] The matrix permutation process of the constraint table, which establishes mutual constraints, converts the engineering constraints between parameters into mathematical expressions. Track engineering involves a variety of parameter constraints. For example, changes in the track centerline position affect the gauge measurement benchmark, and adjustments to the track surface elevation affect the calculation of track superelevation and lateral level. The constraint table records these inter-influencing relationships in matrix form, with rows corresponding to the constrained parameters and columns corresponding to the parameters from which the constraints originate. The matrix elements represent the strength and type of the constraint relationships. The permutation process determines the values ​​of the matrix elements based on the tightness and impact of the constraints, assigning larger values ​​to strong constraints and smaller values ​​to weaker ones. The matrix also contains information about the directionality of the constraints: positive values ​​indicate positively correlated constraints, negative values ​​indicate negatively correlated constraints, and zero indicates no constraints. The construction quality constraint matrix combines these various constraint relationships through matrix operations to form a comprehensive matrix that describes the constraint characteristics of the entire track geometry system. This matrix provides the mathematical basis for the constraints in the collaborative optimization algorithm.

[0092] The optimization objective establishment process for track centerline coordinate constraints, track surface elevation constraints, and gauge variation constraints converts engineering technical standards into boundary conditions for mathematical optimization. The track centerline coordinate constraint range is determined based on the track design alignment and allowable construction error. These constraints limit the deviation of the centerline coordinates, preventing the track alignment from deviating from the design requirements. The track surface elevation constraint range is based on the track design elevation and elevation control accuracy, constraining the track surface elevation to within a reasonable range around the design value. The gauge variation constraint range is established based on gauge technical standards and measurement accuracy requirements, controlling the gauge value within the allowable deviation range around the standard gauge. The optimization objective establishment process integrates these constraints into the objective function of a multi-objective optimization problem, which consists of an error minimization term and a constraint satisfaction term. The error minimization term seeks to minimize the deviation of the adjusted parameters from the ideal design value, while the constraint satisfaction term ensures that the adjusted parameters meet all engineering constraints. The multi-parameter collaborative optimization objective is formed by weighting the individual objectives to form a comprehensive objective function. The weight coefficients are determined based on the engineering importance and adjustment difficulty of the parameters.

[0093] The sequential quadratic programming algorithm, a stepwise iterative solution process, is a numerical method for constrained optimization problems. It decomposes the original nonlinear constrained optimization problem into a series of quadratic programming subproblems, approaching the optimal solution of the original problem by gradually solving these subproblems. The iterative solution process first establishes a quadratic approximation model at the current iteration point. This model comprises a quadratic approximation of the objective function and a linear approximation of the constraint functions. The quadratic programming subproblems are then solved to determine a search direction that minimizes the objective function and improves the constraints. A line search is then performed to determine the step size, which takes into account both the magnitude of the objective function reduction and the degree of constraint violations. The algorithm handles equality constraints using Lagrange multipliers and inequality constraints using penalty functions to ensure that the constraints are satisfied during the iterative process. Convergence criteria include multiple metrics, such as the magnitude of objective function improvement, the degree of constraint violation, and the gradient norm. The algorithm terminates when all metrics meet convergence requirements. The parameter adjustment increment is the difference between the current and initial parameter values ​​after convergence, reflecting the parameter adjustment required to satisfy the constraints and optimize the goal.

[0094] The implementation phase of collaborative optimization involves incremental parameter adjustments to track alignment, elevation control, and gauge accuracy parameters. These updates utilize an incremental overlay method, adding the adjusted incremental values ​​to the original parameter values ​​to produce the adjusted parameter values. Track alignment parameter adjustments prioritize the continuity and smoothness of curve elements, ensuring that the adjusted alignment meets geometric continuity requirements. Elevation control parameter adjustments consider the rationality of longitudinal grade changes and the smoothness of vertical curves, avoiding excessively sharp gradients or unreasonable vertical curve radii. Gauge accuracy parameter adjustments maintain gauge values ​​within technical standards and control the gauge change rate within permitted limits. The adjustment process also includes parameter rationality checks and an engineering feasibility assessment of the adjusted parameters. Parameter values ​​outside the reasonable range require re-optimization or manual intervention. The resulting construction data includes all collaboratively adjusted track geometric parameters, ensuring that these parameters not only meet their respective technical requirements but also maintain consistency with each other.

[0095] The above describes the railway construction data processing method in the embodiment of the present application. The following describes the railway construction data processing system in the embodiment of the present application. Figure 2 In one embodiment of the railway construction data processing system of the present application, the system includes:

[0096] The annotation module is used to perform semantic annotation processing on track laying data, line measurement data, and construction monitoring data through RDF semantic association to obtain a track construction semantic dataset;

[0097] The screening module is used to perform quality screening on the construction data based on the gauge deviation and elevation deviation in the track construction semantic dataset by setting track smoothness constraints to obtain qualified construction data;

[0098] An optimization module is used to input the qualified construction data into an improved fireworks algorithm, optimize the track geometric parameters through a track curvature adaptive explosion mechanism, and obtain track parameter optimization data;

[0099] A completion module is used to complete the track centerline, track surface elevation and track gauge changes using an improved Kriging interpolation method based on the track parameter optimization data to obtain complete track geometry data;

[0100] The collaborative module is used to establish a construction quality constraint matrix based on the complete track geometry data, and to coordinately adjust the track alignment, elevation control and gauge accuracy through a sequential quadratic programming algorithm to obtain construction data results.

[0101] above Figure 2The railway construction data processing system in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The railway construction data processing equipment in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0102] Reference Figure 3 In the embodiment of the present invention, a railway construction data processing device is also provided. The railway construction data processing device can be a server, and its internal structure can be as follows: Figure 3 As shown. The railway construction data processing equipment includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The computer-designed processor is used to provide computing and control capabilities. The memory of the railway construction data processing equipment includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the railway construction data processing equipment is used to store the corresponding data in this embodiment. The network interface of the railway construction data processing equipment is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0103] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the railway construction data processing equipment to which the solution of the present invention is applied.

[0104] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the railway construction data processing method.

[0105] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0106] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a railway construction data processing device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A railway construction data processing method, characterized in that: The method comprises: The track laying data, line measurement data and construction monitoring data are semantically annotated through RDF semantic association to obtain the track construction semantic dataset. According to the track gauge deviation and elevation deviation in the track construction semantic dataset, the construction data is quality screened by setting track smoothness constraints to obtain qualified construction data; The qualified construction data is input into the improved fireworks algorithm, and the track geometric parameters are optimized through the track curvature adaptive explosion mechanism to obtain track parameter optimization data, including: using the track geometric parameters in the qualified construction data as the initial positions of fireworks individuals to perform population initialization processing to obtain an initial fireworks population; according to the numerical value of the track curvature radius of each firework individual in the initial fireworks population, the corresponding explosion radius size is calculated and adaptively adjusted to obtain a curvature adaptive explosion radius; based on the curvature adaptive explosion radius, each firework individual is subjected to random position explosion generation processing in the search space to obtain a spark position coordinate set; the spark position coordinate set is substituted into the track superelevation gradient constraint condition to perform fitness numerical evaluation processing to obtain a spark fitness evaluation result; according to the spark fitness evaluation result, the optimal spark is selected according to the merit ranking to perform position update and algorithm iteration processing to obtain track parameter optimization data; According to the track parameter optimization data, an improved Kriging interpolation method is used to complete the track centerline, track surface elevation and track gauge change to obtain complete track geometry data, including: extracting the track centerline coordinate point, track surface elevation value and track gauge change value from the track parameter optimization data, performing data separation processing, and obtaining geometric parameter classification data; dynamically adjusting the Kriging interpolation range parameter and the nugget effect parameter according to the track curvature radius value in the geometric parameter classification data to obtain an interpolation parameter configuration result; establishing a semivariogram function structure based on the interpolation parameter configuration result to calculate the spatial correlation between interpolation points to obtain a spatial correlation matrix; performing weight coefficient solution operation processing on the spatial correlation matrix and known measurement point data to obtain an interpolation weight coefficient set; performing weighted interpolation calculation processing on the track geometry parameters of the missing positions according to the interpolation weight coefficient set to obtain complete track geometry data; A construction quality constraint matrix is ​​established based on the complete track geometry data, and the track alignment, elevation control and gauge accuracy are coordinated and adjusted through a sequential quadratic programming algorithm to obtain construction data results.

2. The railway construction data processing method according to claim 1, characterized in that: The track construction semantic dataset is obtained by semantically annotating the track laying data, line measurement data, and construction monitoring data through RDF semantic association, including: Performing ontology category mapping processing on the track plate position information and laying time sequence information in the track laying data to obtain a track entity semantic label; Establishing a spatiotemporal relationship triple structure based on the mileage coordinates and elevation coordinates in the line measurement data to obtain a measurement data semantic relationship graph; Performing attribute value annotation processing based on the quality inspection parameters and construction process parameters in the construction monitoring data to obtain a construction process semantic attribute set; Inputting the track entity semantic label, the measurement data semantic relationship graph, and the construction process semantic attribute set into an RDF graph database for fusion processing to obtain a multi-source data semantic mapping table; According to the multi-source data semantic mapping table, a subject-predicate-object relationship description process is established for each data source to obtain a track construction semantic data set.

3. The railway construction data processing method according to claim 1, characterized in that: The method of performing quality screening on the construction data based on the gauge deviation and elevation deviation in the track construction semantic dataset by setting track smoothness constraints to obtain qualified construction data includes: Extracting the track gauge deviation value and the elevation deviation value from the track construction semantic data set, performing value range determination processing, and obtaining a deviation parameter classification result; According to the deviation parameter classification result, the allowable range of gauge deviation and the allowable range of elevation deviation are set to perform constraint condition establishment processing to obtain a track smoothness constraint condition set; Based on the track smoothness constraint condition set, the track gauge deviation value and the elevation deviation value are compared and screened point by point to obtain constraint violation identification data; Inputting the constraint violation identification data into a Boolean logic judge to perform qualification evaluation processing to obtain a construction data quality evaluation result; According to the construction data quality evaluation result, qualified data extraction processing is performed on the original construction data to obtain qualified construction data.

4. The railway construction data processing method according to claim 1, characterized in that: The adaptive adjustment process of calculating the corresponding explosion radius according to the trajectory curvature radius of each individual firework in the initial firework population to obtain the curvature adaptive explosion radius includes: Extracting the track curvature radius value corresponding to each individual firework from the initial firework population and performing numerical reading processing to obtain a curvature radius parameter set; Performing a curvature type classification and determination process according to the numerical values ​​in the curvature radius parameter set to obtain a curvature classification identification result; Based on the curvature classification identification result, different explosion radius scaling coefficients are set for the small curvature radius segment and the large curvature radius segment to perform coefficient allocation processing to obtain a curvature adaptive scaling coefficient; Performing a product operation on the curvature adaptive scaling coefficient and the basic explosion radius parameter to obtain an individual-specific explosion radius value; An explosion radius assignment process is performed on each individual firework according to the individual-specific explosion radius value to obtain a curvature-adaptive explosion radius.

5. The railway construction data processing method according to claim 1, characterized in that: The construction quality constraint matrix is ​​established based on the complete track geometry data, and the track alignment, elevation control and gauge accuracy are coordinated and adjusted through a sequential quadratic programming algorithm to obtain construction data results, including: Extracting track alignment parameters, elevation control parameters, and gauge accuracy parameters from the complete track geometry data, performing parameter grouping processing, and obtaining a collaborative adjustment parameter set; Establish a constraint condition table based on the mutual constraint relationship between the parameters in the collaborative adjustment parameter set and perform matrix arrangement processing to obtain a construction quality constraint matrix; Based on the construction quality constraint matrix, the track centerline coordinate constraint range, the track surface elevation constraint range, and the track gauge change constraint range are set to perform optimization target establishment processing to obtain a multi-parameter collaborative optimization target; Inputting the multi-parameter collaborative optimization target into a sequential quadratic programming algorithm for step-by-step iterative solution processing to obtain parameter adjustment increment values; According to the parameter adjustment increment value, the track alignment, elevation control and gauge accuracy parameters are numerically updated and adjusted to obtain construction data results.

6. A railway construction data processing system, characterized in that: For implementing the railway construction data processing method according to any one of claims 1 to 5, the railway construction data processing system comprises: The annotation module is used to perform semantic annotation processing on track laying data, line measurement data, and construction monitoring data through RDF semantic association to obtain a track construction semantic dataset; a screening module for performing quality screening on the construction data by setting track smoothness constraints based on the track gauge deviation and elevation deviation in the track construction semantic dataset to obtain qualified construction data; An optimization module is used to input the qualified construction data into an improved fireworks algorithm, optimize the track geometric parameters through a track curvature adaptive explosion mechanism, and obtain track parameter optimization data, including: using the track geometric parameters in the qualified construction data as the initial positions of fireworks individuals to perform population initialization processing to obtain an initial fireworks population; calculating the corresponding explosion radius size based on the track curvature radius of each firework individual in the initial fireworks population, and adaptively adjusting the size to obtain a curvature adaptive explosion radius; performing random position explosion generation processing on each firework individual within a search space based on the curvature adaptive explosion radius to obtain a spark position coordinate set; substituting the spark position coordinate set into the track superelevation gradient constraint condition to perform fitness numerical evaluation processing to obtain a spark fitness evaluation result; selecting the optimal spark according to the spark fitness evaluation result in accordance with the merit ranking to perform position update and algorithm iteration processing to obtain track parameter optimization data; A completion module is used to complete the track centerline, track surface elevation and gauge change using an improved Kriging interpolation method based on the track parameter optimization data to obtain complete track geometry data, including: extracting the track centerline coordinate points, track surface elevation values ​​and gauge change values ​​from the track parameter optimization data for data separation processing to obtain geometric parameter classification data; dynamically adjusting the Kriging interpolation range parameter and the nugget effect parameter according to the track curvature radius value in the geometric parameter classification data to obtain an interpolation parameter configuration result; establishing a semivariogram function structure based on the interpolation parameter configuration result to calculate the spatial correlation between interpolation points to obtain a spatial correlation matrix; performing weight coefficient solution operation processing on the spatial correlation matrix and known measurement point data to obtain an interpolation weight coefficient set; performing weighted interpolation calculation processing on the track geometry parameters of the missing positions according to the interpolation weight coefficient set to obtain complete track geometry data; The collaborative module is used to establish a construction quality constraint matrix based on the complete track geometry data, and to coordinately adjust the track alignment, elevation control and gauge accuracy through a sequential quadratic programming algorithm to obtain construction data results.

7. A railway construction data processing device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the railway construction data processing method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is caused to execute the railway construction data processing method according to any one of claims 1 to 5.

Images