Data processing method and system for traffic engineering construction and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses a data processing method and system for traffic engineering construction and a storage medium. The method comprises the steps that according to multi-source data of a construction site, construction equipment and environment data are processed through self-adaptive filtering, and a quality score table and a preprocessing data set are obtained; carrying out segmented noise reduction and time-frequency analysis based on the data to obtain engineering indexes including equipment vibration, structural response and other characteristics; generating a quality parameter set and a process feature chain through feature recognition; optimizing model parameters by using a case library to obtain an evaluation standard; fusing the model and the parameter set to analyze the construction process to obtain quality features; and finally, optimizing resource configuration to form a decision scheme. The technical problems of insufficient data processing, inaccurate quality evaluation and unreasonable resource scheduling in a traditional construction quality control method are solved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a data processing method, system and storage medium for traffic engineering construction. Background Art

[0002] In the field of transportation engineering construction, as the scale and complexity of projects continue to increase, construction quality control faces higher requirements. Existing construction quality control technologies mainly rely on manual inspections and single-point monitoring, and evaluate construction quality through regular inspections and sampling tests. At the same time, various types of sensor equipment are deployed on the construction site to collect construction data, including structural displacement, vibration, temperature and other parameters, and a construction quality evaluation system is established. In terms of resource scheduling, traditional methods are mainly based on manual deployment based on experience, and project management software is used to assist in construction progress control and resource allocation.

[0003] However, the existing technology has the following shortcomings: First, there is a lack of effective processing methods for multi-source heterogeneous data collected at construction sites, resulting in uneven data quality, making it difficult to provide a reliable basis for construction quality control; second, construction quality assessment is too dependent on manual experience and lacks scientific data analysis methods and evaluation standards; third, construction resource scheduling mainly relies on manual decision-making, and fails to fully consider the relationship between resource allocation and construction quality, which can easily lead to resource waste or quality risks; fourth, quality risks in the construction process are not identified in a timely manner, and quality control measures lag behind, affecting construction efficiency and quality. Summary of the invention

[0004] The present application provides a data processing method, system and storage medium for traffic engineering construction, which are used to solve the technical problems of insufficient data processing, inaccurate quality assessment and unreasonable resource scheduling in traditional construction quality control methods.

[0005] In a first aspect, the present application provides a data processing method for traffic engineering construction, the data processing method for traffic engineering construction comprising: preprocessing the dynamic parameters of construction equipment and the construction environment status data through adaptive data filtering based on multi-source data collected at the construction site to obtain a construction data quality score sheet and a preprocessed data set; based on the preprocessed data set and the construction data quality score sheet, performing time-frequency domain processing on the traffic engineering construction data through segmented noise reduction to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data; based on the engineering Construction characteristic indicators, extract construction process characteristics through multi-dimensional process mapping and dynamic feature recognition, generate time-series-related engineering construction quality status parameter set and construction process spatiotemporal feature chain; according to the engineering construction quality status parameter set and construction process spatiotemporal feature chain, dynamically calibrate and optimize the construction model through the construction case knowledge base to obtain the traffic engineering construction evaluation standard model; fuse the characteristics of the traffic engineering construction evaluation standard model with the engineering construction quality status parameter set, analyze the construction process through the quality indicator extractor, and obtain the construction quality feature set; use the construction quality feature set to dynamically optimize the construction plan through the construction resource scheduling system to obtain the construction optimization decision plan.

[0006] In a second aspect, the present application provides a data processing system for traffic engineering construction, the data processing system for traffic engineering construction comprising: The acquisition module is used to pre-process the dynamic parameters of construction equipment and the state data of the construction environment through adaptive data filtering based on the multi-source data collected at the construction site, and obtain the construction data quality score sheet and pre-processed data set; A processing module is used to perform time-frequency domain processing on the traffic engineering construction data by segmented noise reduction according to the pre-processed data set and the construction data quality score table to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data; An extraction module is used to extract construction process features based on the engineering construction feature indicators through multi-dimensional process mapping and dynamic feature recognition to generate a time-series-related engineering construction quality state parameter set and a construction process spatiotemporal feature chain; An optimization module is used to dynamically calibrate the construction model and optimize the parameters based on the construction quality status parameter set and the spatiotemporal characteristic chain of the construction process through the construction case knowledge base to obtain a standard model for traffic engineering construction evaluation; A fusion module is used to fuse the traffic engineering construction evaluation standard model with the engineering construction quality status parameter set, analyze the construction process through a quality indicator extractor, and obtain a construction quality feature set; The optimization module is used to utilize the construction quality feature set to dynamically optimize the construction plan through the construction resource scheduling system to obtain a construction optimization decision plan.

[0007] A third aspect of the present application provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned data processing method for traffic engineering construction.

[0008] In the technical solution provided by the present application, the dynamic parameters of construction equipment and the construction environment status data are preprocessed by adaptive data filtering, which significantly improves the quality of the original data and provides a reliable data basis for subsequent analysis; the traffic engineering construction data is processed in the time and frequency domain by segmented noise reduction, and the engineering construction characteristic indicators including the vibration frequency characteristic values ​​of the construction equipment, the dynamic response parameters of the structure, the construction environment influencing factors, the engineering material performance indicators and the construction process monitoring data are obtained, so as to realize the comprehensive extraction of the multi-dimensional characteristics of the construction process; the construction process characteristics are extracted by multi-dimensional process mapping and dynamic feature recognition, and the time-series-related engineering construction quality status parameter set and the construction process spatiotemporal feature chain are generated, and the mapping relationship between the construction quality and the process progress is established; the construction model is dynamically calibrated and the parameters are optimized by using the construction case knowledge base, and the standard model for the construction evaluation of the traffic engineering is obtained, so as to improve the accuracy of the quality evaluation; the standard model for the construction evaluation of the traffic engineering is integrated with the engineering construction quality status parameter set, and the construction process is analyzed by the quality indicator extractor, so as to realize the accurate evaluation of the construction quality; finally, the construction plan is dynamically optimized by the construction resource scheduling system, and the construction optimization decision plan is obtained, so as to realize the reasonable allocation of construction resources and the effective control of the construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0010] Figure 1 A schematic diagram of an embodiment of a data processing method for traffic engineering construction in an embodiment of the present application; Figure 2 It is the environment-material characteristic distribution diagram in the embodiment of this application; Figure 3This is a schematic diagram of an embodiment of a data processing system for traffic engineering construction in an embodiment of the present application. DETAILED DESCRIPTION

[0011] The embodiments of the present application provide a data processing method, system and storage medium for traffic engineering construction. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. 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 device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0012] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the data processing method for traffic engineering construction in the embodiment of the present application includes: Step S101: pre-processing the dynamic parameters of construction equipment and the state data of the construction environment through adaptive data filtering according to the multi-source data collected at the construction site, and obtaining a construction data quality score sheet and a pre-processed data set; Step S102: Based on the preprocessed data set and the construction data quality score sheet, the traffic engineering construction data is processed in the time and frequency domain by segmented noise reduction to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data; Step S103: Based on the engineering construction characteristic indicators, the construction process characteristics are extracted through multi-dimensional process mapping and dynamic feature recognition to generate a time-series-related engineering construction quality state parameter set and a construction process spatiotemporal characteristic chain; Step S104: According to the engineering construction quality status parameter set and the spatiotemporal characteristic chain of the construction process, the construction model is dynamically calibrated and the parameters are optimized through the construction case knowledge base to obtain a standard model for traffic engineering construction evaluation; Step S105, feature fusion of the traffic engineering construction evaluation standard model and the engineering construction quality status parameter set, and analysis of the construction process through a quality index extractor to obtain a construction quality feature set; Step S106: Utilize the construction quality feature set to dynamically optimize the construction plan through the construction resource scheduling system to obtain a construction optimization decision plan.

[0013] It is understandable that the execution subject of the present application may be a data processing system for traffic engineering construction, or a terminal or a server, which is not limited here. The present application embodiment is described by taking a server as the execution subject as an example.

[0014] Specifically, in the data preprocessing stage, multi-source data are collected from the construction site, including construction equipment sensor data, environmental monitoring data, and structural response data. These raw data are preprocessed through adaptive data filtering. This process divides the data into time series and segments the continuous data stream into fixed time windows. The length of each time window is dynamically adjusted according to the data sampling frequency. For the dynamic parameters of construction equipment, the data quality is evaluated by calculating the mean, standard deviation, skewness, and kurtosis of the data to generate a data quality score. For the construction environment status data, the data is scored based on the three dimensions of completeness, consistency, and effectiveness to form a construction data quality score table.

[0015] The time-frequency domain processing is performed based on the preprocessed data set and the construction data quality score table. The segmented noise reduction method is used to segment the data according to the process characteristics, and the frequency domain analysis is performed on each segment of the data. The time domain signal is converted to the frequency domain through Fourier transform, the spectrum characteristics are extracted, and the characteristic values ​​of the vibration frequency of the construction equipment are obtained. At the same time, the phase analysis of the structural dynamic response data is performed to obtain the structural dynamic response parameters. For the construction environment data, the temperature, humidity, and wind speed change characteristics are extracted to form the construction environment influencing factors. The engineering material performance test data is statistically analyzed to establish the engineering material performance index. In addition, the real-time monitoring data of the construction process is supplemented and outliers are processed to generate the construction process monitoring data. Multi-dimensional process mapping is performed based on the engineering construction feature indicators. This process establishes the process-feature correspondence relationship and organizes different feature indicators according to the construction process. The construction process features are extracted by the dynamic feature recognition algorithm, which includes three steps: data standardization, feature dimension reduction, and feature selection. Data standardization converts features of different dimensions to a unified scale, feature dimension reduction reduces data redundancy, and feature selection retains key feature parameters. After processing, a time-series-related engineering construction quality status parameter set is formed, which contains key control indicators of construction quality. At the same time, the time-space feature chain of the construction process is established through the analysis of time-space feature association to describe the logical relationship and time-space dependency between the processes. The construction case knowledge base stores historical construction case data, including engineering features, quality parameters, and construction plans. Similar cases are retrieved from the knowledge base through feature matching, feature similarity is calculated, and cases with high matching degree are selected as references. Dynamic feature calibration is performed on the construction model, and model parameters are adjusted according to actual construction data to optimize model performance. The standard model for traffic engineering construction evaluation is obtained through parameter optimization, which can accurately evaluate the construction quality status. The standard model for traffic engineering construction evaluation and the parameter set for engineering construction quality status are fused by weighted fusion method, and the weight coefficient is determined by data correlation analysis. The quality indicator extractor analyzes the fused features, extracts key quality indicators, and establishes a quality evaluation indicator system. After data analysis, a construction quality feature set is formed, including quality control parameters, abnormal warning indicators, and risk assessment results.

[0016] Optimize the construction plan based on the construction quality feature set. Rationally allocate construction resources through the construction resource scheduling system, taking into account resource constraints, process dependencies, and quality control requirements. Dynamically optimize the construction plan, adjust the construction process, resource allocation, and schedule, and obtain the best construction optimization decision plan.

[0017] Taking the construction of viaduct as an example, the construction data of steel bar processing, concrete pouring, bracket installation, formwork installation and other processes are collected during the construction process. Outliers are eliminated through data preprocessing to evaluate data quality. The vibration data of concrete vibrating equipment is analyzed by spectrum analysis to extract vibration frequency characteristics. The temperature and humidity changes during concrete pouring are monitored to analyze the impact of environmental factors on concrete strength. A process quality status assessment model is established to dynamically evaluate the construction quality based on the monitoring data of the construction process. Based on historical case experience, the construction plan is optimized, construction resources are reasonably allocated, and construction quality control is ensured.

[0018] In the embodiment of the present application, the dynamic parameters of the construction equipment and the construction environment status data are preprocessed by adaptive data filtering, which significantly improves the quality of the original data and provides a reliable data basis for subsequent analysis; the traffic engineering construction data is processed in the time and frequency domain by segmented noise reduction, and the engineering construction characteristic indicators including the vibration frequency characteristic values ​​of the construction equipment, the structural dynamic response parameters, the construction environment influencing factors, the engineering material performance indicators and the construction process monitoring data are obtained, so as to realize the comprehensive extraction of the multi-dimensional characteristics of the construction process; the construction process characteristics are extracted by multi-dimensional process mapping and dynamic feature recognition, and the time-series-related engineering construction quality status parameter set and the construction process spatiotemporal feature chain are generated, and the mapping relationship between the construction quality and the process progress is established; the construction model is dynamically calibrated and the parameters are optimized by using the construction case knowledge base, and the traffic engineering construction evaluation standard model is obtained, so as to improve the accuracy of the quality evaluation; the traffic engineering construction evaluation standard model and the engineering construction quality status parameter set are feature-fused, and the construction process is analyzed by the quality indicator extractor, so as to realize the accurate evaluation of the construction quality; finally, the construction plan is dynamically optimized by the construction resource scheduling system, and the construction optimization decision plan is obtained, so as to realize the reasonable allocation of construction resources and the effective control of the construction quality.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Based on the multi-source data collected at the construction site, the multi-source data is segmented into time series using a data preprocessing analyzer to form a time series data sequence; (2) Perform quality assessment and classification of construction equipment dynamic parameters and construction environment status data based on the time series data sequence, and generate a construction data classification table; (3) Input the construction data classification table into the data quality scoring system, score it according to the scoring rules, and obtain the construction data quality scoring table; (4) Based on the construction data quality score sheet, the valid data is filtered through the data filter to generate a preprocessed data set; Among them, the time series data includes equipment operation status data, environmental monitoring data and engineering parameter data; (5) The construction data classification table is classified and labeled according to the data source and data characteristics; (6) The construction data quality score sheet includes data integrity score, data consistency score and data validity score.

[0020] Specifically, the data preprocessing analyzer performs time series segmentation processing on the multi-source data collected at the construction site. These multi-source data contain raw data from various sensor devices at the construction site. The time series segmentation processing uses a sliding time window method to divide the continuous data stream into multiple data segments at fixed time intervals. The size of the time window is determined according to the data sampling frequency. For the high-frequency sampling of equipment operation status data, a smaller time window such as 1 minute is used, and for the low-frequency sampling of environmental monitoring data, a larger time window such as 10 minutes is used. Through time series segmentation, a time series data sequence containing equipment operation status data, environmental monitoring data and engineering parameter data is formed. After obtaining the time series data sequence, the dynamic parameters of construction equipment and the construction environment status data are quality evaluated and classified. The quality evaluation checks the validity of the data and eliminates obviously abnormal data points, such as zero values ​​or out-of-range values ​​caused by sensor failure. Then, the data is statistically analyzed to calculate statistical quantities such as mean, standard deviation, skewness, and kurtosis to evaluate the distribution characteristics of the data. The classification process is based on the source and characteristics of the data, and the data is divided into different categories. For example, the dynamic parameters of construction equipment are classified according to equipment type, including vibration data, temperature data, and pressure data; environmental status data are classified according to monitoring objects, including air quality data, meteorological data, and noise data. Through quality assessment and classification, a construction data classification table is generated.

[0021] After the construction data classification table is input into the data quality scoring system, the system scores the data according to the preset scoring rules. The data integrity score mainly examines the missing data and is scored by calculating the data missing rate. The lower the data missing rate, the higher the integrity score. The data consistency score mainly examines the continuity and stability of the data and is scored by calculating the coefficient of variation and mutation degree of the data. The data validity score examines the accuracy and reliability of the data and is scored by data range check and outlier detection. The scores are weighted averaged to obtain a comprehensive score to form a construction data quality scoring table. Based on the construction data quality scoring table, the data is filtered through the data filter. The data filter sets multi-level filtering conditions, sets thresholds according to the comprehensive data quality score, and removes data with too low a score. Then, the data is filtered according to the time continuity of the data to remove time jumps or repeated data. Finally, the data is filtered according to the physical meaning of the data to remove data that does not conform to physical laws. After multi-level filtering, the preprocessed data set is obtained. The classification and labeling process in the construction data classification table adopts a multi-layer classification system. The first layer classifies according to the data source, distinguishing sensor data, detection equipment data, and manually recorded data. The second layer is classified according to data characteristics, including temporal data, spatial data, and attribute data. Each data record is marked with the data source category and feature category for subsequent processing.

[0022] The three scores in the construction data quality score sheet have their own specific calculation methods. The data integrity score is obtained by calculating the ratio of the actual number of data records to the theoretical number. The data consistency score is obtained by calculating the autocorrelation coefficient and trend index of the data sequence. The data validity score is obtained by calculating the signal-to-noise ratio and accuracy index of the data.

[0023] For example, the sensor equipment collects data such as concrete vibration frequency, concrete temperature, and ambient temperature and humidity. The data preprocessing analyzer divides the continuously collected data into time periods according to the pouring process to form a time series data sequence. The quality assessment of the operation data and environmental monitoring data of the vibration equipment was carried out, and it was found that some temperature sensor data had drift phenomenon, which was classified after data correction. The data quality scoring system scores various types of data. The concrete vibration frequency data obtained a higher integrity and consistency score due to stable sampling; the ambient temperature and humidity data was affected by the weather and had a lower consistency score. The data filter screens according to the scoring results and retains the data with better quality to form a preprocessing data set.

[0024] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Based on the preprocessed data set, the traffic engineering construction data is segmented according to the construction process time nodes to form process data segments; the process data segments are converted into equal-interval time series through resampling processing to generate construction time series; (2) Based on the data integrity score in the construction data quality score table, the local linear interpolation method is used to complete the missing values ​​in the construction time series; the median filter is used to process the values ​​outside the normal range to obtain the corrected data set; (3) Perform time-frequency domain analysis on the corrected data set, convert the continuous signal into a time-frequency spectrum, extract the frequency band energy distribution characteristics, and construct a time-frequency feature matrix; (4) Based on the time-frequency feature matrix, feature extraction is performed for different data types: the vibration frequency characteristic values ​​of the construction equipment are obtained through amplitude analysis, the dynamic response parameters of the structure are obtained through displacement calculation, the construction environment influencing factors are extracted based on the monitoring data, the performance indicators of the engineering materials are calculated based on the detection data, and the construction process monitoring data are sorted out based on the real-time monitoring data; (5) Divide the vibration frequency characteristic values ​​of construction equipment into 0-10 Hz, 10-50 Hz, and 50-100 Hz frequency bands according to the frequency range, calculate the energy value of each frequency band, and extract the main frequency characteristics; establish the displacement-time relationship based on the structural dynamic response parameters, and mark the abnormal response interval by comparing with the set threshold; use the construction environment influencing factors to construct the environmental parameter association map; establish the material performance evaluation sequence based on the engineering material performance indicators; sort the construction process monitoring data according to the collection time, and correspond it with the construction progress to generate the construction monitoring data stream; (6) Through feature recombination, the main frequency characteristics, response anomaly intervals, environmental parameter correlation maps, material performance evaluation sequences, and construction monitoring data streams are combined and processed to form engineering construction characteristic indicators.

[0025] Specifically, the data is divided according to the time nodes of the construction process, and each process corresponds to a data segment, such as pile foundation construction, beam and slab casting, road paving and other processes. For process data segments with different sampling frequencies, the sampling interval is unified through resampling, the high-frequency data is downsampled, and the low-frequency data is interpolated to convert it into an equally spaced time series. In response to the problem of missing data in the construction time series, the data interval that needs to be supplemented is determined based on the data integrity score in the construction data quality score table. The local linear interpolation method is used to calculate the interpolation based on the valid data before and after the missing point. For abnormal values ​​beyond the normal range, such as data jumps caused by sudden sensor failures, median filtering is used for smoothing, and the median in the data window is used to replace the abnormal value to obtain a corrected data set.

[0026] The corrected data set is processed by time-frequency domain analysis, and the short-time Fourier transform is used to decompose the time domain signal into time-frequency representation to obtain the frequency components of the signal at different time points. By calculating the energy of each frequency component, the energy distribution characteristics of the frequency band are obtained, and these characteristics are organized into a time-frequency feature matrix.

[0027] Multi-dimensional feature extraction is performed based on the time-frequency feature matrix. The structural dynamic response parameters are obtained through displacement calculation:

[0028] in, represents the dynamic response parameter, is the weight coefficient of the i-th measuring point, is the vibration frequency, is the horizontal displacement, is the vertical displacement, and n is the number of measuring points.

[0029] The extraction of construction environment influencing factors adopts:

[0030] in, represents the environmental impact factor, is the comprehensive environmental impact coefficient, are the weight coefficients of temperature, humidity and wind speed respectively, are the temperature, humidity, and wind speed values ​​at the jth time point, respectively, and m is the number of time points.

[0031] The calculation formula of engineering material performance index is:

[0032] in, Indicates material performance indicators. are the weight coefficients of strength, density and moisture content, respectively. are the strength, density and moisture content of the kth material respectively, The number of material types.

[0033] The vibration frequency characteristic values ​​of construction equipment are divided into frequency bands, which are low frequency band (0-10Hz), medium frequency band (10-50Hz) and high frequency band (50-100Hz), and the energy value of each frequency band is calculated. The displacement-time curve is drawn according to the structural dynamic response parameters, the displacement threshold is set, and the abnormal interval that exceeds the threshold is marked. The correlation between the factors affecting the construction environment is represented by a correlation map, which shows the mutual influence between the environmental parameters. The performance indicators of engineering materials are arranged in time series to form a performance evaluation sequence. The monitoring data of the construction process corresponds to the construction schedule to generate a monitoring data stream. Various features are combined through feature recombination. The main frequency characteristics, abnormal response intervals, environmental parameter correlation maps, material performance evaluation sequences and construction monitoring data streams are aligned in time order, and the corresponding relationship between the features is established to form engineering construction feature indicators.

[0034] For example, during the construction of viaduct deck paving, the vibration data of the asphalt paver, road surface temperature data, asphalt mixture performance data, etc. are segmented according to the paving sections. The high-frequency data collected by the vibration sensor is downsampled and unified with the temperature sensor data into a time series with a 1-minute interval. Local linear interpolation is used to supplement the missing values ​​in the temperature data due to poor sensor contact. The vibration characteristics of the paver are extracted through time-frequency analysis, and it is found that the main energy is concentrated in the 20-40Hz frequency band. The uneven compaction area is identified by combining the displacement monitoring data. At the same time, the correlation between material performance and construction quality is established by combining parameters such as ambient temperature, asphalt temperature, and oil content.

[0035] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Based on the characteristic indicators of engineering construction, the vibration frequency characteristic values ​​of construction equipment and the dynamic response parameters of the structure are spectrally decomposed through Fourier transform, the frequency domain characteristics are extracted, the frequency-amplitude relationship matrix is ​​established, and the equipment-structure characteristic association table is generated; (2) Based on the construction environment influencing factors and engineering material performance indicators, a spatial distribution network of monitoring points is constructed, the spatial correlation coefficient is calculated, and the interpolation method is used to supplement the monitoring blind area data to form an environment-material characteristic distribution map; (3) The construction process monitoring data is segmented according to the process nodes, and statistical features are extracted for each segment of data, including mean, variance, skewness, and kurtosis calculations, and a process-feature correspondence table is established; (4) Through multi-dimensional feature mapping, the equipment-structure feature association table and the environment-material feature distribution map are temporally and spatially aligned to generate a time-series-related engineering construction quality status parameter set; (5) Based on the process-feature correspondence table, a time series analysis of the construction quality status is performed to establish the correlation between processes and form a spatiotemporal feature chain of the construction processes.

[0036] Specifically, the spectral decomposition of the construction equipment vibration frequency characteristic values ​​and the structural dynamic response parameters is performed, and the time domain signal is converted to the frequency domain through Fourier transform. The amplitude spectrum and phase spectrum characteristics of the transformed frequency domain signal are extracted to establish a frequency-amplitude relationship matrix. This matrix reflects the correspondence between equipment vibration and structural response, and then generates an equipment-structure characteristic association table. In terms of environmental and material data processing, a spatial distribution network of monitoring points is constructed at the construction site based on the construction environment influencing factors and engineering material performance indicators. The spatial correlation coefficient is calculated by the distance between the monitoring points and the data similarity, and the Kriging interpolation method is used to supplement the data in the monitoring blind area. This process forms an environment-material characteristic distribution map, which reflects the spatial distribution law of environmental factors and material properties. Figure 2 As shown, it is the environment-material characteristic distribution diagram in the embodiment of the present application, which shows the monitoring network layout and data distribution of the construction site. Among them, the solid dots P1-P6 represent the monitoring points actually arranged, the dotted dots represent the supplementary monitoring points obtained by interpolation calculation, the dotted lines connect to represent the spatial correlation between the monitoring points, and the curve represents the contour distribution of the environment and material characteristics. The figure provides a legend for the monitoring points, interpolation points, spatial correlation, and characteristic contour lines, which intuitively reflects the spatial distribution law of the environmental factors and material properties at the construction site.

[0037] The statistical features of the construction process monitoring data are extracted using the following formula:

[0038] in, represents the statistical eigenvalue, is the weight coefficient of the i-th process, is the monitoring value of the i-th process at the j-th time point, are the weight coefficients of variance, skewness, and kurtosis, respectively. is the mean value of the ith process, is the standard deviation, k is the number of time points, and n is the number of processes.

[0039] The feature spatiotemporal registration uses the following formula:

[0040] in, is the registration matrix, and is the registration weight coefficient, is the device-structure feature, is the environmental-material characteristic, and and space coordinates respectively, represents the feature fusion operation, represents the coordinate matching operation, m and n are the number of features respectively.

[0041] For example, during the installation of bridge bearings during viaduct construction, the vibration data of the bearing installation equipment and the structural response data of the bearing position are collected. Through spectrum analysis, the correspondence between the main vibration frequency of the equipment and the structural response frequency is found, and abnormal vibrations during the bearing installation process are identified. At the same time, temperature and humidity sensors and material performance detection points are arranged around the bearings to form a monitoring network. The monitoring data is divided according to the bearing installation process, and the statistical characteristics of each process are extracted. Through spatiotemporal registration, the equipment vibration, structural response, environmental conditions and material performance data are mapped to a unified spatiotemporal coordinate system to establish a process quality status parameter set. Based on the logical order and quality dependency between processes, a spatiotemporal feature chain of the construction process is constructed.

[0042] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) According to the engineering construction quality status parameter set, data matching is performed in the construction case knowledge base, and the historical construction case feature set is screened out by calculating parameter similarity, spatiotemporal feature correlation, and process logic relationship; (2) Based on the spatiotemporal characteristic chain of the construction process and the feature set of historical construction cases, the process analysis is performed to extract the process time nodes, resource consumption, construction progress, and quality control point parameters, and to construct a construction feature association matrix; (3) Divide the construction feature association matrix into multiple time windows according to the process flow, perform statistical analysis on the feature data in each window, calculate the feature mean, standard deviation, and data distribution characteristics, and obtain the feature calibration parameter table; (4) Dynamically calibrate the construction process time series data according to the characteristic calibration parameter table, calculate the calibration coefficient, correct the parameters that deviate from the standard range, and generate a construction parameter optimization table; (5) The construction parameter optimization table and the process calibration parameters are integrated through feature combination, and the feature sequence is reconstructed according to the construction process sequence to generate a standard model for traffic engineering construction evaluation.

[0043] Specifically, based on the engineering construction quality status parameter set, the construction case knowledge base is matched with data, and the similarity calculation is performed for the engineering parameters, including the matching evaluation of key features such as engineering scale, structure type, and construction technology. Then the correlation of spatiotemporal features is analyzed, and the similarity of factors such as construction environment conditions, geographical location characteristics, and construction seasons is compared. At the same time, the logical relationship of the process is examined to evaluate whether the organization method of the construction process and the process connection mode are comparable. Through multi-dimensional matching analysis, a collection of cases similar to the current engineering characteristics is screened out from the historical case library. The spatiotemporal feature chain analysis of the construction process is the basis for a deep understanding of the construction process. The process is analyzed using the historical construction case feature set to extract the process time node information, including the start time, end time, duration, and key milestone nodes of each process. Secondly, the resource consumption of each process is counted, involving data such as human resource allocation, equipment usage time, and material consumption. At the same time, the construction progress information is recorded, including the planned progress, actual progress, and progress deviation. Quality control points are set for each process, and quality inspection data and quality abnormalities are recorded. These features are organized into a construction feature association matrix to describe the association and dependence between processes.

[0044] The analysis of the construction feature association matrix adopts the time window division method, and the entire construction process is divided into several time windows according to the natural division of the construction process. In each time window, the characteristic data is statistically analyzed, and the calculated mean reflects the central trend of the characteristics, the standard deviation represents the degree of dispersion of the data, and the quantile describes the distribution characteristics of the data. The characteristic calibration parameter table is obtained through statistical analysis, which contains the standard interval and fluctuation range of each characteristic parameter. Dynamic calibration is performed based on the characteristic calibration parameter table, and the calibration coefficient is calculated for each parameter in the construction process time series data. The calibration coefficient reflects the degree of deviation between the actual parameter and the standard parameter. For parameters that deviate from the standard range, they are corrected according to the calibration coefficient. The correction process takes into account the mutual influence and constraint relationship between the parameters to avoid the chain reaction of other parameters caused by the correction of a single parameter. After the parameter correction, the construction parameter optimization table is generated, which contains the corrected construction parameter values.

[0045] The construction parameter optimization table is fused with the process calibration parameters by combining features. The fusion process reconstructs the feature sequence according to the logical order of the construction process, and establishes the correspondence and conversion rules between the features. The standard model for traffic engineering construction evaluation is formed by feature reorganization, which can accurately reflect the construction quality status and guide the construction process control.

[0046] In the installation and construction of the steel box girder of the cross-sea bridge, similar engineering cases are retrieved from the construction case library. By comparing the characteristics of the bridge span, structural form, construction technology, etc., historical cases with high similarity are selected. The installation process of the steel box girder is analyzed, and the time node data of the processes such as hoisting preparation, main beam lifting, temporary fixation, and welding connection are extracted. The resource consumption data such as the use time of large lifting equipment, the amount of welding materials, and the number of professional welders in each process are counted. The comparison between the actual construction progress and the planned progress is recorded, and quality control points such as weld quality and geometric dimensions are set. The process data is divided into time windows according to the construction stage, and the change law of characteristic parameters is analyzed in each window. Abnormal data, such as the working parameters of the hoisting equipment and the welding process parameters, are corrected through parameter calibration. The calibrated parameters are reorganized according to the construction process to form a construction quality assessment model.

[0047] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Based on the standard model for traffic engineering construction evaluation, the data of the engineering construction quality status parameter set is standardized, the parameter mean and standard deviation are calculated, the construction quality evaluation index system is established, and a quality evaluation parameter table is formed; (2) Through correlation analysis, the characteristic correlation degree of the indicator data in the quality evaluation parameter table is calculated, including the correlation coefficient, contribution degree, and influence weight between the parameters, and the quality indicator correlation matrix is ​​generated; (3) The quality indicator correlation matrix is ​​segmented according to the construction progress nodes, the quality control parameters of each construction stage are calculated, the key quality control points are extracted, and the construction quality control sequence is constructed; (4) Analyze the deviation between the construction quality control sequence and the standard value, calculate the quality deviation value, mark the quality abnormality interval, and form a quality assessment report; (5) The key indicators in the quality assessment report are classified and summarized through feature reorganization, and the features are combined according to the sequence of construction processes to obtain the construction quality feature set.

[0048] Specifically, the original parameter data is normalized to eliminate the influence of dimension and order of magnitude. Statistical characteristics are calculated for different types of parameters, including the mean value reflecting the average level of the parameter and the standard deviation representing the degree of fluctuation of the parameter. On this basis, a construction quality evaluation index system is established, covering multiple dimensions such as construction process indicators, material performance indicators, structural quality indicators, and environmental impact indicators to form a quality evaluation parameter table. The index data in the quality evaluation parameter table are subjected to correlation analysis to calculate the correlation coefficient matrix between the parameters. The correlation coefficient reflects the linear correlation strength between the parameters, and the contribution of each parameter to the overall quality is determined by principal component analysis. At the same time, the hierarchical analysis method is used to calculate the influence weight of the parameters, taking into account the comprehensive evaluation of expert experience and engineering practice. The correlation coefficient, contribution, and influence weight are combined to form a quality index association matrix, which describes the intrinsic connection between quality parameters.

[0049] The construction quality control parameters are calculated using the following formula:

[0050] in, is the quality control parameter value, is the weight coefficient of the i-th construction stage, and are the weights of process parameters and material parameters, is the process control parameter, is the material quality parameter, is the environmental impact weight, is the environmental condition parameter, is the environmental impact index, n is the number of construction stages, m is the number of control parameters, and p is the number of environmental parameters.

[0051] According to the calculation results of quality control parameters, the construction quality control sequence is obtained. Deviation analysis is performed on the sequence and the quality standard value to calculate the difference between the actual value and the standard value. By setting the deviation threshold, the quality abnormality interval that exceeds the allowable range is marked. The analysis results are summarized to form a quality assessment report, which records in detail the changing trend of quality parameters, abnormal conditions and their cause analysis. The key indicators in the quality assessment report are classified and sorted. According to the logical order of the construction process, the relevant indicators are recombined to establish the corresponding relationship between the indicators. The construction quality feature set is obtained through feature recombination, which fully reflects the quality status of the construction process.

[0052] For example, during highway pavement construction, parameters such as asphalt mixture temperature, compaction, and flatness are standardized, and an evaluation index system is established based on specification requirements. Through correlation analysis, it is found that there is a significant correlation between compaction and temperature, and the ambient temperature has an important impact on construction quality. Quality control points are set in key processes such as paving and compaction to monitor construction parameters in real time. When it is found that the compaction of a section of pavement is lower than the standard requirements, the cause of the quality abnormality is found out by analyzing the temperature field distribution and construction process parameters, and corresponding adjustment measures are taken. The various quality indicators are sorted according to the construction process to form a quality feature set.

[0053] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) Decompose the construction quality feature set, extract key quality control parameters and construction process node parameters, and establish a process quality association sequence; (2) Conduct a correlation analysis between the construction resource demand and the construction process time in the process quality association sequence, calculate the resource allocation weight coefficient, and obtain the construction resource allocation table; (3) Through resource scheduling analysis, the construction resource allocation table is used to calculate the resource balance between processes, identify resource conflict points, mark key time nodes for resource allocation, and generate a resource scheduling optimization table; (4) Based on the resource scheduling optimization table, quality constraint analysis is performed on the construction process, a mapping diagram between construction resources and process quality is established, and a construction plan quality evaluation sequence is formed; (5) Optimize the construction plan quality assessment sequence according to the construction progress requirements, adjust the resource allocation plan, and obtain the construction resource optimization matrix; (6) Dynamically adjust the construction resource optimization matrix through comprehensive scheme evaluation, reconstruct the process resource allocation according to quality control requirements, and obtain the construction optimization decision-making plan.

[0054] Specifically, data decomposition is performed to separate key quality control parameters from the construction quality feature set, including material performance indicators, process parameters, and quality inspection data. At the same time, construction process node parameters are extracted to record the start and end time, duration, and quality control points of each process. These parameters are arranged in the order of construction processes to establish a process quality association sequence, which reflects the corresponding relationship between construction quality and process progress. On the basis of the process quality association sequence, the correlation between construction resource demand and process time is analyzed. The human resources, equipment resources, and material resources required for each process are counted, and the proportional relationship between the total amount of resources and the process workload is calculated. The importance of each type of resource is determined through correlation analysis, and the resource allocation weight coefficient is calculated. These coefficients reflect the degree of influence of resource input on process quality, and a construction resource allocation table is generated based on this, which lists the specific resource allocation schemes required for each process.

[0055] Resource scheduling analysis is an important part of optimizing resource allocation. For the construction resource allocation table, the resource balance calculation method is used to check whether there is a conflict in the use of resources between each process. When multiple processes require the same resources in the same time period, it is marked as a resource conflict point. At the same time, the key time nodes for resource allocation are determined, including resource entry time, transition time, and withdrawal time. By optimizing the timing of resource use, resource conflicts are eliminated and a resource scheduling optimization table is formed. Quality constraint analysis is performed based on the resource scheduling optimization table to study the impact of resource allocation plans on construction quality. A mapping relationship diagram between construction resources and process quality is established, which shows the corresponding relationship between resource input level and quality control indicators. For example, the relationship between the number of mechanical equipment and construction efficiency, and the relationship between construction personnel configuration and quality control accuracy. By analyzing these mapping relationships, a construction plan quality evaluation sequence is formed.

[0056] Compare the construction plan quality assessment sequence with the construction schedule, and adjust the process arrangement and resource allocation plan. Under the premise of ensuring quality requirements, optimize the efficiency of resource use and avoid idle or over-concentrated resources. The adjusted plan is recorded in the construction resource optimization matrix, which contains the optimal resource allocation plan for each process. Through comprehensive evaluation of the plan, the construction resource optimization matrix is ​​dynamically adjusted. According to quality control requirements, fine-tune the process resource allocation to ensure that the resource allocation meets quality standards. Integrate the optimized resource allocation plan to form a construction optimization decision plan.

[0057] Taking the pile foundation construction of a bridge as an example, quality control parameters such as concrete strength, steel cage processing accuracy, pile verticality, and process node parameters such as drilling rig placement, steel cage installation, and concrete pouring are extracted from the quality feature set. The demand for equipment resources such as drilling rigs, cranes, and concrete pump trucks in each process is analyzed, and the relationship between equipment usage time and engineering volume is calculated. Through resource balance calculation, it is found that there is a conflict in the use of equipment between steel cage hoisting and concrete pouring, and the process arrangement needs to be adjusted. According to quality requirements, the concrete pouring speed and the configuration standards of pumping equipment are determined to optimize the construction plan. The decision-making plan formed clearly stipulates the resource allocation quantity and scheduling sequence of each process, which not only meets quality requirements but also avoids resource waste.

[0058] In a specific embodiment, the process of performing the quality constraint analysis step on the construction process based on the resource scheduling optimization table may specifically include the following steps: (1) Based on the resource scheduling optimization table, the correlation analysis of resource allocation between processes is performed, and the process quality constraint matrix is ​​generated through key parameter calculation; (2) Divide the process quality constraint matrix into multiple quality control blocks according to the construction sequence, calculate the quality index threshold of each block, and form a process quality control sequence; (3) Analyze the construction resource matching degree of the process quality control sequence, establish the corresponding relationship between resource input and quality output, and obtain the resource-quality mapping table; (4) Assign weights to the parameters in the resource-quality mapping table through correlation calculation, identify key influencing factors, and construct a quality influencing factor matrix; (5) Based on the quality impact factor matrix, perform quality assessment calculations for each construction process node, mark quality risk points, and generate a process quality assessment table; (6) Rearrange the evaluation results in the process quality evaluation table in time sequence, integrate the quality evaluation data according to the construction progress, and form a construction plan quality evaluation sequence.

[0059] Specifically, based on the resource scheduling optimization table, the resource allocation of each process is analyzed to extract key parameters reflecting the efficiency of resource utilization, including equipment utilization, staffing efficiency, material consumption rate, etc. By calculating the degree of correlation between these parameters, a process quality constraint matrix is ​​established, which describes the constraint relationship between resource allocation and process quality. The process quality constraint matrix is ​​divided according to the construction sequence, and the continuous construction process is divided into multiple quality control blocks. Each block corresponds to one or more related processes with similar quality control requirements. For each quality control block, the thresholds of quality indicators are calculated, including qualified standard values ​​and warning values. The determination of these thresholds is based on specification requirements and engineering experience to form a process quality control sequence.

[0060] The construction resource matching degree analysis is conducted on the process quality control sequence to study the correspondence between the quantity and quality of resource input and the construction quality output. The analysis content includes the correspondence between equipment model and construction accuracy, the relationship between personnel skill level and construction quality, and the relationship between material performance and engineering quality. Through data analysis, a resource-quality mapping table is established, which reflects the quality output level under different resource input conditions. Based on the resource-quality mapping table, the weight of each parameter is determined through correlation calculation. The degree of influence of different resource types on quality is analyzed, and the key factors that have the most significant impact on quality are identified. According to the results of the correlation analysis, a quality influencing factor matrix is ​​constructed, which quantifies the influence of each resource factor on construction quality.

[0061] According to the quality influencing factor matrix, quality assessment is conducted on each node of the construction process. The assessment content includes whether the resource input meets the quality requirements, whether the construction process is standardized, whether the quality control measures are in place, etc. Through the evaluation calculation, the nodes with higher quality risks are marked to form a process quality assessment table. This table records the quality assessment results and risk level of each node in detail. The assessment results in the process quality assessment table are reorganized in chronological order to correspond to the construction schedule. The quality assessment data of each time period are integrated, the quality change trend is analyzed, and a construction plan quality assessment sequence is formed. This sequence fully reflects the changes in quality status during the construction process.

[0062] Taking tunnel construction as an example, the resource allocation of tunnel excavation, support, lining and other processes is analyzed in correlation. The influence of different types of support materials and construction equipment on tunnel deformation control is calculated to generate a process quality constraint matrix. The construction process is divided into quality control blocks such as excavation section, primary support section, and secondary lining section. Thresholds for quality indicators such as surrounding rock deformation, support thickness, and concrete strength are set for each block. The corresponding relationship between tunnel boring machine performance and excavation quality, jetting machine parameters and concrete strength, and steel support specifications and support effects is analyzed to establish a resource-quality mapping relationship. Through data analysis, it is found that support timing and support strength are key influencing factors, and these parameters are controlled in particular. Quality assessment is conducted on each construction section, and risk points such as surrounding rock grade changes and groundwater inrush are marked. The quality assessment results of each section are integrated to form a construction quality assessment sequence to guide quality control during the construction process.

[0063] The above describes the data processing method for traffic engineering construction in the embodiment of the present application. The following describes the data processing system for traffic engineering construction in the embodiment of the present application. Figure 3 , an embodiment of the data processing system for traffic engineering construction in the embodiment of the present application includes: The acquisition module 201 is used to pre-process the dynamic parameters of the construction equipment and the construction environment status data through adaptive data filtering based on the multi-source data collected at the construction site to obtain a construction data quality score sheet and a pre-processed data set; The processing module 202 is used to perform time-frequency domain processing on the traffic engineering construction data by segmented noise reduction according to the pre-processed data set and the construction data quality score table to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data; Extraction module 203, used to extract construction process features based on the engineering construction feature indicators through multi-dimensional process mapping and dynamic feature recognition, and generate a time-series-related engineering construction quality state parameter set and a construction process spatiotemporal feature chain; The optimization module 204 is used to dynamically calibrate the construction model and optimize the parameters through the construction case knowledge base according to the engineering construction quality status parameter set and the spatiotemporal characteristic chain of the construction process, so as to obtain a standard model for traffic engineering construction evaluation; A fusion module 205 is used to perform feature fusion on the traffic engineering construction evaluation standard model and the engineering construction quality status parameter set, analyze the construction process through a quality index extractor, and obtain a construction quality feature set; The optimization module 206 is used to utilize the construction quality feature set to dynamically optimize the construction plan through the construction resource scheduling system to obtain a construction optimization decision plan.

[0064] Through the collaborative cooperation of the above components, the dynamic parameters of construction equipment and the construction environment status data are pre-processed through adaptive data filtering, which significantly improves the quality of the original data and provides a reliable data basis for subsequent analysis; the segmented noise reduction is used to process the traffic engineering construction data in the time and frequency domain, and the engineering construction characteristic indicators including the vibration frequency characteristic values ​​of the construction equipment, the dynamic response parameters of the structure, the construction environment influencing factors, the engineering material performance indicators and the construction process monitoring data are obtained, realizing the comprehensive extraction of the multi-dimensional characteristics of the construction process; the construction process characteristics are extracted through multi-dimensional process mapping and dynamic feature recognition, and the time-series-related engineering construction quality status parameter set and the construction process spatiotemporal feature chain are generated, and the mapping relationship between construction quality and process progress is established; the construction model is dynamically calibrated and parameter optimized using the construction case knowledge base to obtain the traffic engineering construction evaluation standard model, thereby improving the accuracy of quality evaluation; the traffic engineering construction evaluation standard model and the engineering construction quality status parameter set are feature-fused, and the construction process is analyzed through the quality indicator extractor, realizing the accurate evaluation of construction quality; finally, the construction plan is dynamically optimized through the construction resource scheduling system to obtain the construction optimization decision plan, realizing the reasonable allocation of construction resources and the effective control of construction quality.

[0065] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the data processing method for traffic engineering construction.

[0066] Those skilled in the art can 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.

[0067] If the integrated unit is implemented in the form of 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 application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer 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 application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0068] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 embodiments of the present application.

Claims

1. A data processing method for traffic engineering construction, characterized in that: The data processing method for traffic engineering construction comprises: Based on the multi-source data collected at the construction site, the dynamic parameters of the construction equipment and the construction environment status data are preprocessed through adaptive data filtering to obtain the construction data quality score sheet and preprocessed data set; According to the preprocessed data set and the construction data quality score sheet, the traffic engineering construction data is processed in the time-frequency domain by segmented noise reduction to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data; Based on the engineering construction characteristic indicators, the construction process characteristics are extracted through multi-dimensional process mapping and dynamic feature recognition to generate a time-series-related engineering construction quality state parameter set and a construction process spatiotemporal characteristic chain; According to the engineering construction quality status parameter set and the spatiotemporal characteristic chain of the construction process, the construction model is dynamically calibrated and the parameters are optimized through the construction case knowledge base to obtain a standard model for traffic engineering construction evaluation; The traffic engineering construction evaluation standard model is integrated with the engineering construction quality status parameter set, and the construction process is analyzed by a quality index extractor to obtain a construction quality feature set; By utilizing the construction quality feature set, the construction plan is dynamically optimized through a construction resource scheduling system to obtain a construction optimization decision plan.

2. The data processing method for traffic engineering construction according to claim 1, characterized in that: The method pre-processes the dynamic parameters of construction equipment and the state data of the construction environment through adaptive data filtering based on the multi-source data collected at the construction site to obtain a construction data quality score sheet and a pre-processed data set, including: According to the multi-source data collected at the construction site, the multi-source data is segmented into time series by a data preprocessing analyzer to form a time series data sequence; Performing quality assessment and classification on the construction equipment dynamic parameters and the construction environment status data according to the time series data sequence, and generating a construction data classification table; Input the construction data classification table into the data quality scoring system, score according to the scoring rules, and obtain the construction data quality scoring table; Based on the construction data quality score table, valid data is filtered through a data filter to generate a preprocessed data set; Wherein, the time series data sequence includes equipment operation status data, environmental monitoring data and engineering parameter data; The construction data classification table is classified and labeled according to data sources and data characteristics; The construction data quality score sheet includes a data integrity score, a data consistency score and a data validity score.

3. The data processing method for traffic engineering construction according to claim 1, characterized in that: According to the pre-processed data set and the construction data quality score table, the traffic engineering construction data is processed in the time-frequency domain by segmented noise reduction to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data, including: Based on the preprocessed data set, the traffic engineering construction data is segmented according to the construction process time nodes to form process data segments; the process data segments are converted into equal-interval time series through resampling processing to generate a construction time series; According to the data integrity score in the construction data quality score table, the local linear interpolation method is used to complete the missing values ​​in the construction time series; the median filter is used to process the values ​​outside the normal range to obtain a corrected data set; Performing time-frequency domain analysis on the modified data set, converting the continuous signal into a time-frequency spectrum, extracting frequency band energy distribution characteristics, and constructing a time-frequency feature matrix; Based on the time-frequency feature matrix, feature extraction is performed for different data types: the vibration frequency characteristic value of the construction equipment is obtained through amplitude analysis, the dynamic response parameters of the structure are obtained through displacement calculation, the construction environment influencing factors are extracted based on the monitoring data, the engineering material performance indicators are calculated based on the detection data, and the construction process monitoring data is sorted out according to the real-time monitoring data; The vibration frequency characteristic values ​​of the construction equipment are divided into 0-10Hz, 10-50Hz, and 50-100Hz frequency bands according to the frequency range, the energy value of each frequency band is calculated, and the main frequency characteristics are extracted; the displacement-time relationship is established according to the structural dynamic response parameters, and the abnormal response interval is marked by comparing with the set threshold; the environmental parameter association map is constructed using the construction environment influencing factors; a material performance evaluation sequence is established based on the engineering material performance indicators; the construction process monitoring data is sorted according to the collection time, and corresponds to the construction progress to generate a construction monitoring data stream; Through feature recombination, the main frequency characteristics, abnormal response intervals, environmental parameter correlation maps, material performance evaluation sequences and construction monitoring data streams are combined and processed to form engineering construction characteristic indicators.

4. The data processing method for traffic engineering construction according to claim 1, characterized in that: Based on the engineering construction characteristic index, the construction process characteristics are extracted through multi-dimensional process mapping and dynamic feature recognition to generate a time-series-related engineering construction quality state parameter set and a construction process spatiotemporal characteristic chain, including: Based on the engineering construction characteristic index, the construction equipment vibration frequency characteristic value and the structural dynamic response parameter are subjected to spectrum decomposition through Fourier transform, the frequency domain characteristics are extracted, the frequency-amplitude relationship matrix is ​​established, and the equipment-structure characteristic association table is generated; According to the construction environment influencing factors and engineering material performance indicators, a monitoring point spatial distribution network is constructed, the spatial correlation coefficient is calculated, and the interpolation method is used to supplement the monitoring blind area data to form an environment-material characteristic distribution map; The construction process monitoring data is segmented according to process nodes, and statistical features are extracted for each segment of data, including mean, variance, skewness, and kurtosis calculations, and a process-feature correspondence table is established; Through multi-dimensional feature mapping, the equipment-structure feature association table and the environment-material feature distribution map are temporally and spatially aligned to generate a time-series-associated engineering construction quality status parameter set; Based on the process-feature correspondence table, a time series analysis of the construction quality status is performed, and a correlation relationship between processes is established to form a spatiotemporal feature chain of the construction processes.

5. The data processing method for traffic engineering construction according to claim 1, characterized in that: According to the engineering construction quality status parameter set and the spatiotemporal characteristic chain of the construction process, the construction model is dynamically calibrated and the parameters are optimized through the construction case knowledge base to obtain the traffic engineering construction evaluation standard model, including: According to the engineering construction quality status parameter set, data matching is performed in the construction case knowledge base, and the historical construction case feature set is screened out by calculating parameter similarity, spatiotemporal feature correlation, and process logic relationship; For the spatiotemporal characteristic chain of the construction process, process analysis is performed based on the feature set of historical construction cases, process time nodes, resource consumption, construction progress, and quality control point parameters are extracted, and a construction feature association matrix is ​​constructed; Divide the construction feature association matrix into multiple time windows according to the process flow, perform statistical analysis on the feature data in each window, calculate the feature mean, standard deviation, and data distribution characteristics, and obtain a feature calibration parameter table; Dynamically calibrate the construction process time series data according to the characteristic calibration parameter table, calculate the calibration coefficient, correct the parameters that deviate from the standard range, and generate a construction parameter optimization table; The construction parameter optimization table is integrated with the process calibration parameters through feature combination, and the feature sequence is reconstructed according to the construction process sequence to generate a standard model for traffic engineering construction evaluation.

6. The data processing method for traffic engineering construction according to claim 1, characterized in that: The traffic engineering construction evaluation standard model is subjected to feature fusion with the engineering construction quality status parameter set, and the construction process is analyzed by a quality index extractor to obtain a construction quality feature set, including: Based on the traffic engineering construction evaluation standard model, the data of the engineering construction quality status parameter set is standardized, the parameter mean and standard deviation are calculated, a construction quality evaluation index system is established, and a quality evaluation parameter table is formed; By correlation analysis, characteristic correlation degree calculation is performed on the indicator data in the quality evaluation parameter table, including correlation coefficient, contribution degree and influence weight between parameters, to generate a quality indicator correlation matrix; The quality indicator correlation matrix is ​​segmented according to the construction progress nodes, the quality control parameters of each construction stage are calculated, the key quality control points are extracted, and a construction quality control sequence is constructed; Perform deviation analysis on the construction quality control sequence and the standard value, calculate the quality deviation value, mark the quality abnormality interval, and form a quality assessment report; The key indicators in the quality assessment report are classified and summarized through feature reorganization, and the features are combined according to the sequence of construction procedures to obtain a construction quality feature set.

7. The data processing method for traffic engineering construction according to claim 1, characterized in that: The construction quality feature set is used to dynamically optimize the construction plan through the construction resource scheduling system to obtain a construction optimization decision plan, including: Decomposing the construction quality feature set, extracting key quality control parameters and construction process node parameters, and establishing a process quality association sequence; Performing a correlation analysis on the construction resource demand and construction process time in the process quality association sequence, calculating the resource allocation weight coefficient, and obtaining a construction resource allocation table; Through resource scheduling analysis, the construction resource allocation table is used to calculate resource balance between processes, identify resource conflict points, mark key time nodes for resource allocation, and generate a resource scheduling optimization table; Based on the resource scheduling optimization table, quality constraint analysis is performed on the construction process, a mapping relationship diagram between construction resources and process quality is established, and a construction plan quality evaluation sequence is formed; Optimize the construction plan quality assessment sequence according to the construction progress requirements, adjust the resource allocation plan, and obtain a construction resource optimization matrix; The construction resource optimization matrix is ​​dynamically adjusted through comprehensive scheme evaluation, and the process resource allocation is reconstructed according to quality control requirements to obtain a construction optimization decision-making scheme.

8. The data processing method for traffic engineering construction according to claim 7, characterized in that: Based on the resource scheduling optimization table, quality constraint analysis is performed on the construction process, a mapping diagram between construction resources and process quality is established, and a construction plan quality evaluation sequence is formed, including: Based on the resource scheduling optimization table, a correlation analysis is performed on resource allocation between processes, and a process quality constraint matrix is ​​generated through key parameter calculation; Dividing the process quality constraint matrix into a plurality of quality control blocks according to the construction sequence, calculating the quality index threshold of each block, and forming a process quality control sequence; Performing construction resource matching analysis on the process quality control sequence, establishing a corresponding relationship between resource input and quality output, and obtaining a resource-quality mapping table; By calculating the correlation, weights are assigned to the parameters in the resource-quality mapping table, key influencing factors are identified, and a quality influencing factor matrix is ​​constructed; According to the quality impact factor matrix, quality assessment calculation is performed on each construction process node, quality risk points are marked, and a process quality assessment table is generated; The evaluation results in the process quality evaluation table are reorganized in time sequence, and the quality evaluation data are integrated according to the construction progress to form a construction plan quality evaluation sequence.

9. A data processing system for traffic engineering construction, used to implement the data processing method for traffic engineering construction as claimed in any one of claims 1 to 8, characterized in that: The data processing system for traffic engineering construction comprises: The acquisition module is used to pre-process the dynamic parameters of construction equipment and the state data of the construction environment through adaptive data filtering based on the multi-source data collected at the construction site, and obtain the construction data quality score sheet and pre-processed data set; A processing module is used to perform time-frequency domain processing on the traffic engineering construction data by segmented noise reduction according to the pre-processed data set and the construction data quality score table to obtain engineering construction characteristic indicators; wherein the engineering construction characteristic indicators include: construction equipment vibration frequency characteristic values, structural dynamic response parameters, construction environment influencing factors, engineering material performance indicators and construction process monitoring data; An extraction module is used to extract construction process features based on the engineering construction feature indicators through multi-dimensional process mapping and dynamic feature recognition to generate a time-series-related engineering construction quality state parameter set and a construction process spatiotemporal feature chain; An optimization module is used to dynamically calibrate the construction model and optimize the parameters based on the construction quality status parameter set and the spatiotemporal characteristic chain of the construction process through the construction case knowledge base to obtain a standard model for traffic engineering construction evaluation; A fusion module is used to fuse the traffic engineering construction evaluation standard model with the engineering construction quality status parameter set, analyze the construction process through a quality indicator extractor, and obtain a construction quality feature set; The optimization module is used to utilize the construction quality feature set to dynamically optimize the construction plan through the construction resource scheduling system to obtain a construction optimization decision plan.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the data processing method for traffic engineering construction as described in any one of claims 1-8 is implemented.

Images