Asphalt pavement compactness multi-source sensing fusion detection and quality evaluation system

Abstract

The invention relates to the technical field of pavement compactness detection, and discloses an asphalt pavement compactness multi-source sensing fusion detection and quality evaluation system, which comprises a data processing module for filtering and standardizing synchronously acquired multi-dimensional physical parameter data of an asphalt pavement to generate a standardized data stream; the data fusion module is used for carrying out fusion calculation on the standardized data flow by adopting a self-adaptive weighted fusion algorithm to obtain consistent fusion data; the quality evaluation module is used for generating a compaction degree evaluation result according to the consistency fusion data and a preset compaction degree calculation model; and the result output module is used for converting the compaction degree evaluation result into a graphical interface and a digital report and outputting the graphical interface and the digital report. The method can effectively solve the problems that a traditional coring method is high in destructiveness and low in efficiency, data of a single sensor is one-sided, and data of multiple sources are inconsistent, achieves efficient and accurate compaction degree quality evaluation, and remarkably improves the efficiency and reliability of construction quality monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road surface compaction degree detection, and in particular to a multi-source sensing fusion detection and quality evaluation system for asphalt pavement compaction degree. BACKGROUND

[0002] In the field of road construction and maintenance, the compaction degree of asphalt pavement is a key indicator to ensure the stability, bearing capacity and durability of the pavement structure. However, the existing detection technology has obvious limitations: on the one hand, the traditional coring method is destructive, has poor real-time performance and low efficiency, and is difficult to meet the quality monitoring needs of large-scale construction; on the other hand, the automatic detection method based on a single sensor cannot fully reflect the complex pavement compaction state, and the one-sidedness of the data limits the evaluation accuracy. In addition, although multi-source detection technology has been gradually applied, different sensor data lack effective fusion mechanisms, resulting in inconsistencies in the detection results, making it difficult to form reliable quality evaluation conclusions. These problems seriously restrict the widespread application and further improvement of pavement compaction degree detection technology.

[0003] Therefore, there is an urgent need to provide a technical solution to solve the above problems. SUMMARY

[0004] To solve the above technical problems, the present application provides a multi-source sensing fusion detection and quality evaluation system for asphalt pavement compaction degree.

[0005] In a first aspect, the present application provides a multi-source sensing fusion detection and quality evaluation system for asphalt pavement compaction degree, and the technical solution of the system is as follows:

[0006] A data processing module is configured to filter and standardize the multi-dimensional physical parameter data of the asphalt pavement collected synchronously, and generate a standardized data stream;

[0007] A data fusion module is configured to use an adaptive weighted fusion algorithm to perform fusion calculation on the standardized data stream, and obtain consistent fusion data;

[0008] A quality evaluation module is configured to generate a compaction degree evaluation result according to the consistent fusion data and a preset compaction degree calculation model;

[0009] A result output module is configured to convert the compaction degree evaluation result into a graphical interface and a digital report and output.

[0010] Preferably, the multi-dimensional physical parameter data includes dielectric constant value, temperature value and vibration acceleration value; and the system further comprises:

[0011] The data acquisition module is configured to acquire the dielectric constant values of different depths of the asphalt pavement through the dielectric constant sensor, acquire the temperature values of the construction area of the asphalt pavement through the temperature sensor, and acquire the vibration acceleration values of the asphalt pavement in the process of the roller operation through the vibration acceleration sensor.

[0012] Preferably, the data processing module is specifically configured to:

[0013] filter the dielectric constant values, the temperature values, and the vibration acceleration values respectively to obtain filtered multi-dimensional physical parameter data;

[0014] convert the filtered multi-dimensional physical parameter data into dimensionless values by using a normalization algorithm, and integrate the processed data into the standardized data stream in time sequence alignment.

[0015] Preferably, the data fusion module is specifically configured to:

[0016] calculate adaptive weight coefficients according to the measurement accuracy and real-time confidence of each parameter data source in the standardized data stream, the parameter data source including a dielectric constant value data source, a temperature value data source, and a vibration acceleration value data source;

[0017] perform weighted fusion calculation on each parameter data in the standardized data stream based on the adaptive weight coefficients to generate the consistency fusion data.

[0018] Preferably, the data fusion module is specifically configured to:

[0019] obtain historical measurement error statistical values of each parameter data source as the measurement accuracy, and calculate data fluctuation variances of each parameter data source in real time as the real-time confidence;

[0020] calculate the adaptive weight coefficients corresponding to each parameter data source according to the measurement accuracy and the real-time confidence of each parameter data source and by using a weight distribution formula.

[0021] Preferably, the weight distribution formula is: In the formula, denotes the adaptive weight coefficient of the i-th parameter data source; denotes the measurement accuracy of the i-th parameter data source; denotes the real-time confidence of the i-th parameter data source; denotes the total number of parameter data sources; denotes the sum of the measurement accuracy and the real-time confidence of all parameter data sources.

[0022] Preferably, the data fusion module is specifically configured to:

[0023] In the process of weighted fusion calculation of each parameter data in the standardized data stream based on the adaptive weight coefficient corresponding to each parameter data source, each parameter data is segmented and processed according to time sequence, and a dynamic weighted fusion algorithm is used to calculate the segment fusion result of data in each time segment, and the segment fusion results of all time segments are integrated into the consistency fusion data.

[0024] The formula of the dynamic weighted fusion algorithm is as follows: In the formula, denotes the segment fusion result of the kth time segment. denotes the adaptive weight coefficient of the ith parameter data source in the kth time segment. denotes the standardized data value of the ith parameter data source in the kth time segment. denotes the data change rate of the ith parameter data source in the kth time segment. denotes the data change rate correction factor; wherein, The weight distribution formula is obtained by calculating the measurement accuracy and real-time confidence of each parameter data source in the kth time segment.

[0025] Preferably, the quality evaluation module is specifically used for:

[0026] The consistency fusion data is input into the preset compaction degree calculation model, the initial compaction degree value is calculated through the mapping relationship between the consistency fusion data and the compaction degree standard value, the initial compaction degree value is compensated and corrected in combination with real-time environmental parameters, and the compaction degree evaluation result is generated.

[0027] Preferably, the result output module is specifically used for:

[0028] The compaction degree evaluation result and the spatial position information are associated and matched to generate the graphical interface containing the compaction degree distribution thermodynamic map and the compaction process waveform graph;

[0029] The key quality indicators are extracted from the compaction degree evaluation result to generate the digital report;

[0030] The graphical interface and the digital report are output to a local display device or a remote monitoring platform through wired or wireless transmission mode.

[0031] In a second aspect, the present application provides a multi-source sensing fusion detection and quality evaluation method for asphalt pavement compaction degree, and the technical scheme of the method is as follows:

[0032] The multi-dimensional physical parameter data of the asphalt pavement synchronously collected are filtered and standardized to generate a standardized data stream;

[0033] Adopt the adaptive weighted fusion algorithm to the standardized data stream Fusion calculation, obtain consistent fusion data;

[0034] According to the consistency fusion data and preset compaction degree calculation model, generate compaction degree evaluation result;

[0035] The compaction degree evaluation result is converted into a graphical interface and a digital report and output.

[0036] The technical scheme of the present application solves the problems of strong destructive and low efficiency of traditional coring method, and one-sided data of single sensor and inconsistency of multi-source data by real-time acquisition of multi-source physical parameters and adaptive weighted fusion algorithm, realizes efficient and accurate compaction degree quality evaluation, and significantly improves the efficiency and reliability of construction quality monitoring.

[0037] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application, which can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical scheme in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0039] The drawings are only used to show the embodiments, and are not considered as limitation of the present application. Moreover, the same reference signs are used to represent the same parts throughout the drawings. In the drawings:

[0040] Figure 1 The structure diagram of an embodiment of the present application, a multi-source sensing fusion detection and quality evaluation system for asphalt pavement compaction degree;

[0041] Figure 2 The flowchart of an embodiment of the present application, a multi-source sensing fusion detection and quality evaluation method for asphalt pavement compaction degree. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein.

[0043] Figure 1An embodiment of a structure schematic diagram of an asphalt pavement compaction degree multi-source sensing fusion detection and quality evaluation system provided by the present application is shown. As shown in Figure 1 The system comprises:

[0044] A data processing module 110 is configured to filter and standardize the multi-dimensional physical parameter data of the asphalt pavement synchronously collected, to generate a standardized data stream.

[0045] The asphalt pavement refers to a road surface layer structure formed by asphalt mixture paving, mainly serving to bear vehicle load, provide a flat driving surface, and protect the base layer. For example, the upper layer of the K123+500 to K124+000 section of a certain expressway is paved with AC-13 type asphalt mixture. The multi-dimensional physical parameter data refers to a set of multiple types of physical quantity data collected by different principle sensors, which can reflect the compaction state of the asphalt pavement. For example, the data combination of dielectric constant 8.5, temperature 155℃, and vibration acceleration 3.2g synchronously collected by the roller during the rolling process. The standardized data stream refers to a time series aligned and dimensionless data sequence formed after filtering and normalizing the original multi-dimensional physical parameter data. For example, the continuous data sequence formed by arranging the processed dielectric constant data 0.85, temperature data 0.62, and vibration acceleration data 0.78 according to the time stamp.

[0046] A data fusion module 120 is configured to perform fusion calculation on the standardized data stream by using an adaptive weighted fusion algorithm, to obtain consistent fusion data.

[0047] The adaptive weighted fusion algorithm refers to a calculation method for dynamically adjusting the weight coefficient according to the real-time quality of the data source for data fusion. For example, the real-time accuracy of the sensor is used to assign a weight of 0.6 to the dielectric constant data, a weight of 0.3 to the temperature data, and a weight of 0.1 to the vibration data for weighted calculation. The consistent fusion data refers to unified data output after eliminating contradictions and conflicts through multi-source data fusion processing. For example, the continuous numerical sequence [0.87, 0.89, 0.91...] representing the overall compaction state of the pavement is obtained after fusion.

[0048] A quality evaluation module 130 is configured to generate a compaction degree evaluation result according to the consistent fusion data and a preset compaction degree calculation model.

[0049] The preset compaction degree calculation model refers to a mathematical mapping relationship for calculating the compaction degree through the fusion data, which is established in advance. For example, the calculation model based on neural network training is compaction degree = 1.05 x dielectric fusion value + 0.8 x temperature compensation value. The compaction degree evaluation result refers to the quantitative compaction degree evaluation value finally output by the system. For example, the detection result of evaluating the compaction degree of a certain section as 98.2% and marking it as qualified.

[0050] The result output module 140 is configured to convert the compaction degree evaluation result into a graphical interface and a digital report and output the same.

[0051] The graphical interface refers to a man-machine interface in which the compaction degree data is visualized, for example, a heat distribution map and a waveform curve superimposed interface displayed on a tablet computer. The digital report refers to a structured compaction degree detection result document, for example, a PDF format report containing indicators such as a qualified rate and an average compaction degree.

[0052] The technical scheme of the embodiment effectively solves the problems of strong destructiveness and low efficiency of the traditional coring method, and one-sidedness of single sensor data and inconsistency of multi-source data, by collecting multi-source physical parameters in real time and using an adaptive weighted fusion algorithm, and realizes efficient and accurate compaction degree quality evaluation, thereby significantly improving the efficiency and reliability of construction quality monitoring.

[0053] In an optional mode, the multi-dimensional physical parameter data includes a dielectric constant value, a temperature value and a vibration acceleration value, and the system further includes:

[0054] The data collection module is configured to collect the dielectric constant value of the asphalt pavement at different depths through a dielectric constant sensor, collect the temperature value of the construction area of the asphalt pavement through a temperature sensor, and collect the vibration acceleration value of the asphalt pavement in the roller operation process through a vibration acceleration sensor.

[0055] The dielectric constant value refers to a physical quantity parameter reflecting the dielectric property of asphalt mixture, for example, a relative dielectric constant of 8.5 measured by a sensor. The temperature value refers to a real-time temperature measurement value of the construction area of the asphalt pavement, for example, a surface temperature of 155℃ measured by an infrared temperature sensor. The vibration acceleration value refers to a vibration acceleration quantitative value generated during the operation of the roller, for example, a vertical vibration value of 3.2g measured by an embedded accelerometer. The dielectric constant sensor refers to a sensing device for measuring the dielectric property of asphalt mixture, for example, an electromagnetic wave reflection type sensor installed on the side of the rolling wheel. The temperature sensor refers to a sensing device for detecting the surface temperature of the pavement, for example, an infrared non-contact temperature probe embedded in front of the rolling wheel. The construction area refers to a specific pavement section being compacted, for example, the 3rd lane being rolled from K123+500 to K124+000 of the highway. The vibration acceleration sensor refers to a sensing device for detecting the vibration intensity of the roller, for example, a three-axis MEMS accelerometer installed on the bearing seat of the steel wheel of the roller. The roller operation process refers to the complete construction process from starting rolling to reaching the compaction standard, for example, the whole process from initial rolling (125℃) to final rolling (90℃) of a certain road section.

[0056] In the optional mode, the comprehensive perception based on multi-dimensional physical parameters is further realized, the limitations of the single sensor method are avoided, and the comprehensiveness and accuracy of the road surface compactness detection are improved.

[0057] In an optional mode, the data processing module is specifically configured to:

[0058] The dielectric constant value, the temperature value and the vibration acceleration value are respectively filtered to obtain filtered multi-dimensional physical parameter data.

[0059] The filtered multi-dimensional physical parameter data refers to the original sensor data after noise reduction processing, for example, stable data of dielectric constant 8.5±0.2 and temperature 155℃±1℃ after removing high-frequency interference.

[0060] The normalized algorithm is used to convert the filtered multi-dimensional physical parameter data into dimensionless values, and the processed data is integrated into the standardized data stream aligned in time sequence.

[0061] The normalized algorithm refers to a mathematical processing method for converting data into a unified dimension range, for example, using Z-score standardization to convert the original data into a distribution with a mean of 0 and a variance of 1. The dimensionless value refers to a pure value after removing the physical unit after normalization processing, for example, the original value of dielectric constant 8.5 is converted into a dimensionless value of 0.85.

[0062] In the optional mode, the dimension difference and noise interference of the original data are eliminated through filtering and normalization processing, and the standardized data stream with higher quality and consistent time sequence is provided for subsequent fusion calculation.

[0063] In an optional mode, the data fusion module is specifically configured to:

[0064] According to the measurement accuracy and real-time confidence of each parameter data source in the standardized data stream, an adaptive weight coefficient is calculated, and the each parameter data source includes a dielectric constant value data source, a temperature value data source and a vibration acceleration value data source.

[0065] The parameter data source refers to a sensor channel that provides a specific type of measurement data; for example, a sensor channel that specifically collects dielectric constant is referred to as a dielectric constant value data source. The measurement accuracy refers to an index of the closeness of the sensor measurement result to the true value; for example, the accuracy benchmark of a certain dielectric sensor measurement error ≤±0.3. The real-time confidence refers to a real-time reliability index evaluated based on the data fluctuation degree; for example, the confidence index 0.92 corresponding to the current temperature data variance 0.8. The adaptive weight coefficient refers to a fusion weight value dynamically calculated according to real-time data quality; for example, the dielectric data weight 0.6 and the temperature data weight 0.3 in the current time slice. The dielectric constant value data source refers to a data source that specifically provides dielectric constant measurement; for example, a dielectric sensor measurement channel installed on the side of a road roller. The temperature value data source refers to a data source that specifically provides temperature measurement; for example, a measurement data channel of an infrared temperature sensor. The vibration acceleration value data source refers to a source that specifically provides vibration data; for example, an accelerometer data channel installed on the drive shaft of a road roller.

[0066] Based on the adaptive weight coefficient, each parameter data in the standardized data stream is weighted and fused to generate the consistency fusion data.

[0067] In the above optional mode, the weight is further dynamically adjusted according to the measurement accuracy and the real-time data quality, thereby improving the consistency and reliability of the fusion data and enhancing the adaptability of the system to different data sources.

[0068] In an optional mode, the data fusion module is specifically configured to:

[0069] The historical measurement error statistical value of each parameter data source is obtained as the measurement accuracy, and the data fluctuation variance of each parameter data source is calculated in real time as the real-time confidence.

[0070] The historical measurement error statistical value refers to a long-term accumulated sensor error distribution characteristic value; for example, the average measurement error of a dielectric sensor in the past 1000 times is 0.25. The data fluctuation variance refers to a quantized value of the dispersion degree of a real-time data sequence; for example, the variance of the last 10 temperature measurement values is 0.64.

[0071] Specifically, a historical measurement error database is established, and the error average of each parameter data source is calculated as the measurement accuracy; a current data sequence is extracted according to a set time window, and the variance value thereof is calculated as the real-time confidence.

[0072] According to the measurement accuracy and the real-time confidence of each parameter data source, and through a weight distribution formula, the adaptive weight coefficient corresponding to each parameter data source is calculated.

[0073] In the optional manner, the reliability index of the data source is quantified by introducing the historical measurement error statistics and real-time data fluctuation variance, thereby providing a precise basis for adaptive weight calculation.

[0074] In an optional manner, the weight distribution formula is: In the formula, represents the adaptive weight coefficient of the i-th parameter data source; represents the measurement accuracy of the i-th parameter data source; represents the real-time confidence of the i-th parameter data source; represents the total number of parameter data sources; represents the sum of the product of the measurement accuracy and the real-time confidence of all parameter data sources.

[0075] It should be noted that the construction principle of the weight distribution formula is based on the information entropy theory and the Bayesian estimation principle. The historical measurement accuracy and real-time data stability of each parameter data source are quantified to dynamically distribute the weight coefficient. The role is to eliminate the influence of single sensor error and improve the reliability of multi-source data fusion. The symbol represents the adaptive weight coefficient of the i-th parameter data source, which is a dimensionless ratio, the value range is 0-1, and the sum of all weight coefficients is 1. The default initial value is uniform distribution; represents the measurement accuracy, which is a dimensionless statistical probability value, the value range is 0-1, and the default value is 0.95 corresponding to a 95% confidence interval; represents the real-time confidence, which is a dimensionless ratio based on the inverse of the variance, the value range is 0.1-1, and the default value is 0.8; n represents the total number of parameter data sources, which is a dimensionless positive integer, and the default value is 3 corresponding to three types of sensors of dielectric constant, temperature and vibration acceleration.

[0076] In the optional manner, a dynamic weighted fusion algorithm is further used to process data in time segments and combine change rate correction, thereby improving the capture ability of abnormal fluctuations and enhancing the smoothness and real-time performance of the fusion result.

[0077] In an optional manner, the data fusion module is specifically used for:

[0078] In the adaptive weight coefficient corresponding to each parameter data source, the parameter data in the standardized data stream is weighted and fused, each parameter data is processed in time sequence, and a dynamic weighted fusion algorithm is used to calculate the segment fusion result in each time segment. All segment fusion results of the time segments are integrated into the consistency fusion data;

[0079] In the formula, the dynamic weighted fusion algorithm is: In the formula, a segment fusion result of the kth time segment; an adaptive weight coefficient of the ith parameter data source in the kth time segment; a normalized data value of the ith parameter data source in the kth time segment; a data change rate of the ith parameter data source in the kth time segment; a change rate correction factor; wherein, The weight distribution formula is obtained according to the measurement accuracy and real-time confidence of each parameter data source in the kth time segment.

[0080] The time segment refers to a fixed length interval divided on a continuous time axis; for example, a data processing time period divided at an interval of 500 milliseconds. The segment fusion result refers to the output result of data fusion in a single time segment; for example, a 0.87 compaction degree value obtained by fusion calculation in the kth 500 millisecond segment. The data change rate refers to the derivative approximation of the parameter value with respect to time; for example, a change rate of -2 corresponding to a current temperature decrease of 2℃ per second. The data change rate correction factor refers to a coefficient for adjusting the influence degree of the change rate; for example, an α=0.05 correction coefficient set according to the material type.

[0081] It should be noted that the construction principle of the dynamic weighted fusion algorithm is based on time series analysis theory and adaptive filtering theory. The data change rate is calculated in time segments, and a correction factor is introduced to capture the dynamic characteristics of the compaction process. Its role is to solve the lag problem of traditional weighted methods in non-stationary signal fusion and improve the real-time response capability. The symbol a segment fusion result of the kth time segment, which is a dimensionless fusion data value, and the value range is 0-1, and the default initial value is 0; a dynamic weight coefficient of the ith data source in the kth time segment, which is a dimensionless ratio, and the value range is 0-1, and the default value is the output value of the weight distribution formula; a normalized data value, which is a dimensionless value, and the value range is 0-1, and the default value is the output of the previous module; a data change rate, which is a dimensionless difference ratio, and the value range is -0.5 to 0.5, and the default value is 0; a change rate correction factor, which is an empirical dimensionless coefficient, and the value range is 0.01-0.2, and the default value is 0.05, which is used to balance the contribution of the change rate.

[0082] In the above optional mode, a time segment dynamic weighting algorithm is further adopted to optimize the fusion process and improve the dynamic adaptability and timeliness of the fusion result.

[0083] In an optional mode, the quality evaluation module is specifically configured to:

[0084] The consistency fusion data is input into the preset compaction degree calculation model, an initial compaction degree value is calculated through a mapping relationship between the consistency fusion data and a compaction degree standard value, the initial compaction degree value is compensated and corrected in combination with real-time environmental parameters, and the compaction degree evaluation result is generated.

[0085] The compaction degree standard value refers to a reference compaction degree value required by a specification; for example, a standard requirement that the surface layer compaction degree on a highway is not less than 96%. The initial compaction degree value refers to a non-compensated compaction degree value directly calculated by a model; for example, a 97.8% uncorrected value calculated according to fusion data. The real-time environmental parameter refers to a quantitative value of an external environmental factor affecting the compaction degree evaluation; for example, monitoring data of the current environmental temperature of 28 degrees Celsius and the humidity of 65%.

[0086] Specifically, the consistency fusion data is input into the preset compaction degree calculation model, a mapping relationship between the consistency fusion data and the compaction degree standard value is established and an initial compaction degree value is calculated through a linear regression algorithm, environmental temperature and humidity data are collected as real-time environmental parameters, a multivariate linear compensation algorithm is used to correct the initial compaction degree value, and finally the compaction degree evaluation result is generated.

[0087] In the optional manner described above, the accuracy and adaptability of the compaction degree evaluation are improved through standard value mapping and environmental parameter compensation correction.

[0088] In an optional manner, the result output module is specifically configured to:

[0089] The compaction degree evaluation result is associated and matched with spatial position information, and the graphical interface containing a compaction degree distribution heat map and a compaction process waveform graph is generated.

[0090] The spatial position information refers to geographic position coordinates associated with compaction data; for example, longitude 118.5°E and latitude 32.1°N obtained by GPS positioning. The compaction degree distribution heat map refers to a graph representing the spatial distribution of compaction degree by color depth; for example, a continuous color block distribution graph representing 98% in red and 96% in green. The compaction process waveform graph refers to a curve graph showing the change of compaction parameters over time; for example, a time-domain waveform showing the relationship between vibration acceleration and compaction degree change.

[0091] Specifically, the real-time latitude and longitude coordinates of the road roller are obtained as spatial position information, the spatial position information is data-bound with the compaction degree evaluation result corresponding to the time stamp, an interpolation algorithm is used to generate a spatially continuous compaction degree distribution matrix, a distribution heat map representing the compaction degree value by color gradient is drawn according to the compaction degree distribution matrix, compaction degree data of the time sequence corresponding to the spatial position information are extracted to generate a compaction process waveform graph, and finally the heat map and the waveform graph are integrated and displayed in the graphical interface.

[0092] extracting key quality indicators from the compaction degree evaluation results to generate the digital report.

[0093] wherein the key quality indicators refer to core evaluation parameters reflecting compaction quality; for example, statistical indicators such as average compaction degree 98.2%, qualified rate 100%, etc.

[0094] Specifically, the average compaction degree, compaction degree qualified rate and compaction degree standard deviation are extracted from the compaction degree evaluation results as key quality indicators, the key quality indicators are compared with preset quality thresholds to generate quality grade evaluation results, and the key quality indicators and quality grade evaluation results are integrated into a digital report according to a predefined report template.

[0095] The graphical interface and the digital report are output to a local display device or a remote monitoring platform through wired or wireless transmission.

[0096] wherein the local display device refers to a terminal device used for displaying results on site; for example, a shockproof tablet installed in the cab of a road roller. The remote monitoring platform refers to a system for receiving transmission data for remote supervision; for example, an asphalt pavement quality cloud monitoring platform managed by the project department.

[0097] Specifically, the graphical interface and the digital report are converted into JSON format data packets, wired Ethernet transmission or wireless Wi-Fi transmission is automatically selected according to the network connection state, TCP / IP protocol is used to establish network connection with the local display device and the remote monitoring platform, and the packaged data packets are transmitted to the display buffer area of the local display device and the data receiving interface of the remote monitoring platform, respectively.

[0098] In the above optional mode, the compaction degree evaluation results are visually displayed through the graphical interface and the digital report, thereby enhancing the ease of use and data readability of the system.

[0099] To better illustrate the technical solutions of the present embodiment, the following examples are used for illustration:

[0100] S10: The dielectric constant value 8.5 of the asphalt pavement at different depths is collected by the dielectric constant sensor, the temperature value 155℃ of the construction area is collected by the temperature sensor, and the vibration acceleration value 3.2g during the operation of the road roller is collected by the vibration acceleration sensor;

[0101] S20: The dielectric constant value 8.5, the temperature value 155℃ and the vibration acceleration value 3.2g are respectively filtered to obtain filtered multi-dimensional physical parameter data, and the normalized algorithm is used to convert the filtered data into dimensionless values 0.85, 0.62 and 0.78, and integrate them into a time-aligned standardized data stream;

[0102] S30: According to the measurement accuracy and real-time confidence of each parameter data source in the standardized data stream, the dielectric constant value data source weight 0.6, the temperature value data source weight 0.3, and the vibration acceleration value data source weight 0.1 are calculated by a weight distribution formula;

[0103] S40: The standardized data stream is segmented according to 500 millisecond time slices, and a dynamic weighted fusion algorithm is used to calculate the segment fusion result of each time slice, and consistent fusion data [0.87, 0.89, 0.91] is generated by integration;

[0104] S50: The consistent fusion data is input into a preset compaction degree calculation model, and the initial compaction degree value 97.8% is calculated by linear regression, and the environmental temperature 28℃ and humidity 65% are compensated and corrected to generate the compaction degree evaluation result 98.2%;

[0105] S60: The compaction degree evaluation result is associated and matched with the longitude 118.5°E and latitude 32.1°N obtained by GPS positioning, and a graphical interface of compaction degree distribution thermal map and compaction process waveform graph is generated;

[0106] S70: The average compaction degree 98.2% and qualified rate 100% and other key quality indicators are extracted from the compaction degree evaluation result to generate a PDF format digital report;

[0107] S80: The graphical interface and digital report are output to the road roller cab tablet computer and project department cloud monitoring platform through Wi-Fi transmission.

[0108] Figure 2 A flowchart of an embodiment of a multi-source sensing fusion detection and quality evaluation method for asphalt pavement compaction degree provided by the application is shown. As shown in Figure 2 , comprising the following steps:

[0109] S1, filtering and standardizing the multi-dimensional physical parameter data of the asphalt pavement synchronously collected, to generate a standardized data stream;

[0110] S2, using an adaptive weighted fusion algorithm to fuse and calculate the standardized data stream, to obtain consistent fusion data;

[0111] S3, generating a compaction degree evaluation result according to the consistent fusion data and a preset compaction degree calculation model;

[0112] S4, converting the compaction degree evaluation result into a graphical interface and a digital report and outputting.

[0113] The technical scheme of the embodiment effectively solves the problems of strong destructiveness and low efficiency of traditional coring methods, and one-sidedness of single sensor data and inconsistency of multi-source data, by collecting multi-source physical parameters in real time and using an adaptive weighted fusion algorithm, and realizes efficient and accurate compaction quality evaluation, thereby significantly improving the efficiency and reliability of construction quality monitoring.

[0114] In addition, the system provided by the above-mentioned embodiments is only exemplified by the division of the above-mentioned functional modules when realizing its functions, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the system is divided into different functional modules according to actual conditions to complete all or part of the above-described functions. In addition, the system and method embodiments provided by the above-mentioned embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0115] The above description is only the preferred embodiment of the present application and the explanation of the applied technical principles. Those skilled in the art should understand that the disclosed range in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and also covers other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the disclosed concept. For example, the technical solutions formed by replacing the above-mentioned features with the technical features disclosed in the present application (but not limited to) having similar functions.

[0116] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and represent a specific order or sequence. The order of use of similar objects can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described.

[0117] Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A multi-source sensor fusion detection and quality assessment system for asphalt pavement compaction degree, characterized in that, The system includes: The data processing module is used to filter and standardize the multi-dimensional physical parameter data of the synchronously collected asphalt pavement to generate a standardized data stream. The data fusion module is used to perform fusion calculations on the standardized data stream using an adaptive weighted fusion algorithm to obtain consistent fused data; The quality assessment module is used to generate compaction assessment results based on the consistency fusion data and the preset compaction calculation model. The results output module is used to convert the compaction evaluation results into a graphical interface and a digital report and output them.

2. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 1, characterized in that, The multi-dimensional physical parameter data includes: dielectric constant value, temperature value, and vibration acceleration value; the system also includes: The data acquisition module is used to acquire the dielectric constant values ​​of the asphalt pavement at different depths through a dielectric constant sensor, acquire the temperature values ​​of the construction area of ​​the asphalt pavement through a temperature sensor, and acquire the vibration acceleration values ​​of the asphalt pavement during the operation of the road roller through a vibration acceleration sensor.

3. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 2, characterized in that, The data processing module is specifically used for: The dielectric constant, temperature, and vibration acceleration values ​​are filtered to obtain filtered multi-dimensional physical parameter data. A normalization algorithm is used to convert the filtered multi-dimensional physical parameter data into dimensionless values, and the processed data is integrated into a time-aligned standardized data stream.

4. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 3, characterized in that, The data fusion module is specifically used for: Based on the measurement accuracy and real-time confidence of each parameter data source in the standardized data stream, an adaptive weighting coefficient is calculated. The parameter data sources include dielectric constant value data sources, temperature value data sources, and vibration acceleration value data sources. Based on the adaptive weighting coefficients, the parameter data in the standardized data stream are weighted and fused to generate the consistent fused data.

5. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 4, characterized in that, The data fusion module is specifically used for: Historical measurement error statistics for each parameter data source are obtained as measurement accuracy, and the data fluctuation variance of each parameter data source is calculated in real time as real-time confidence level. Based on the measurement accuracy and real-time confidence level of each parameter data source, the adaptive weight coefficient corresponding to each parameter data source is calculated using a weight allocation formula.

6. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 5, characterized in that, The weight allocation formula is as follows: In the formula, This represents the adaptive weight coefficient of the data source for the i-th parameter; This indicates the measurement accuracy of the data source for the i-th parameter; This represents the real-time confidence level of the data source for the i-th parameter; Indicates the total number of parameter data sources; This represents the sum of the products of the measurement accuracy and real-time confidence level of all parameter data sources.

7. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 6, characterized in that, The data fusion module is specifically used for: When performing weighted fusion calculation on each parameter data in the standardized data stream based on the adaptive weight coefficient corresponding to each parameter data source, each parameter data is processed in segments according to the time series, and the segment fusion result is calculated by a dynamic weighted fusion algorithm for the data in each time segment. The segment fusion results of all time segments are integrated into the consistent fusion data. The formula for the dynamic weighted fusion algorithm is as follows: In the formula, This represents the fragment fusion result of the k-th time segment; This represents the adaptive weight coefficient of the data source for the i-th parameter within the k-th time segment; This represents the standardized data value of the i-th parameter data source within the k-th time segment; This represents the rate of change of the data source for the i-th parameter within the k-th time segment; This represents the data change rate correction factor; where, The weight allocation formula is used to calculate the weights based on the measurement accuracy and real-time confidence of each parameter data source within the k-th time segment.

8. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 7, characterized in that, The quality assessment module is specifically used for: The consistent fusion data is input into the preset compaction calculation model. The initial compaction value is calculated through the mapping relationship between the consistent fusion data and the standard compaction value. The initial compaction value is compensated and corrected in combination with real-time environmental parameters to generate the compaction evaluation result.

9. The asphalt pavement compaction degree multi-source sensor fusion detection and quality assessment system according to claim 8, characterized in that, The result output module is specifically used for: The compaction degree assessment results are correlated and matched with spatial location information to generate the graphical interface containing a heat map of compaction degree distribution and a waveform diagram of the compaction process; The digital report is generated by extracting key quality indicators from the compaction assessment results. The graphical interface and the digital report are output to a local display device or a remote monitoring platform via wired or wireless transmission.

10. A method for multi-source sensor fusion detection and quality assessment of asphalt pavement compaction degree, characterized in that, The method includes: The multi-dimensional physical parameter data of the synchronously collected asphalt pavement are filtered and standardized to generate a standardized data stream; An adaptive weighted fusion algorithm is used to perform fusion calculations on the standardized data streams to obtain consistent fused data. Based on the consistent fusion data and the preset compaction degree calculation model, a compaction degree evaluation result is generated; The compaction assessment results are converted into a graphical interface and a digital report and output.

Images