A method and system for detecting the surface flatness of a bridge engineering road

Abstract

The present invention relates to the field of road detection technology, and specifically discloses a method and system for detecting the surface smoothness of a bridge engineering road. A benchmark feature set is generated by processing road section attributes and historical smoothness data; the degree of correlation between the smoothness of a target road section and adjacent road sections and similar structure road sections is evaluated to obtain a correlation value; trend feature one and trend feature two are generated based on correlation value statistics; trend feature two that meets the benchmark trend is marked as pre-processed detection data one. When the target road section and the adjacent road section have the same trend direction but deviate from the benchmark, or the trend direction is opposite but meets the benchmark, trend feature one data and measured data are integrated to generate pre-processed detection data two; a pre-processed feature data set is formed by integration; and a smoothness compliance index is calculated in combination with the environmental impact coefficient and the degree of compliance. The system implements the above modules accordingly. The present invention significantly improves the assessment accuracy and early warning reliability through multi-dimensional correlation analysis, dynamic data correction and environmental compensation mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of road detection, and in particular to a method and system for detecting the surface flatness of a bridge engineering road. Background Art

[0002] In the field of bridge engineering, road surface smoothness is a key indicator for measuring engineering quality and traffic safety, and directly affects vehicle driving stability, comfort, and the service life of bridge structures. With the continuous growth of traffic volume and the increase in the proportion of heavy-loaded vehicles, the load pressure faced by bridges and roads continues to increase, and the rate of smoothness degradation is accelerating. Therefore, higher requirements are placed on the accuracy, timeliness, and comprehensiveness of smoothness detection. Traditional smoothness detection methods mostly rely on single on-site measured data. This method can only reflect the local smoothness status at a specific point in time, and it is difficult to take into account the historical changes and overall trends of the road section. At the same time, this method often ignores the influence of key factors such as bridge structure type, traffic load level, and the correlation between adjacent road sections, resulting in limitations in the detection results. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method for detecting the surface flatness of a bridge engineering road, comprising the following steps:

[0004] S1. Generate a baseline feature set based on the bridge and road segment attribute data and historical roughness test data;

[0005] S2. Evaluate the smoothness correlation between the target detection section and the adjacent associated sections to obtain a first correlation value; evaluate the smoothness correlation between the target detection section and the similar structure section to obtain a second correlation value;

[0006] S3 is based on the first correlation value trend law statistics, generating a trend feature; based on the second correlation value trend law statistics, generating a trend feature two;

[0007] S4. The portion of the trend feature 2 that has the same trend pattern as the benchmark feature set is marked as pre-processed detection data 1; when the target detection segment and the adjacent associated segment have the same flatness change trend direction but the trend feature 1 deviates from the benchmark feature set, or when the target detection segment and the adjacent associated segment have different flatness change trend directions but the trend feature 1 conforms to the benchmark feature set, the detection data associated with the trend feature 1 is fused with the measured basic data of the target detection segment to generate pre-processed detection data 2;

[0008] S5. Generate a preprocessed feature data set based on the preprocessed test data 1, the preprocessed test data 2, and the trend feature 1; and obtain a flatness compliance index by combining the preprocessed feature data set, the environmental impact coefficient, and the flatness compliance level.

[0009] Furthermore, the generation of a benchmark feature set based on the bridge road section attribute data and historical roughness detection data includes:

[0010] Obtain the section attribute data of the bridge road, divide the section attribute data into structural characteristic data according to the section structure type, divide the section attribute data into load characteristic data according to the traffic load level, obtain the first smoothness benchmark feature set according to the structural characteristic data, obtain the second type of smoothness benchmark feature set to which the load characteristic data belongs according to the load characteristic data and load section statistics, and combine the first smoothness benchmark feature set and the second type of smoothness benchmark feature set into a benchmark feature set.

[0011] Furthermore, the first flatness reference feature set is obtained by processing and analyzing the structural feature data, including:

[0012] Extract the similar structure sections to which the structural feature data belongs, and mark other sections that are structurally associated with the similar structure sections as associated structure sections; evaluate the degree of smoothness correlation between similar structure sections and associated structure sections in different maintenance cycles to obtain a smoothness correlation dataset;

[0013] Acquire the smoothness detection data of the associated structural section to obtain auxiliary detection data, and establish a smoothness detection dataset based on the smoothness associated dataset and the auxiliary detection data; perform curve trend judgment on the smoothness detection dataset to obtain an auxiliary trend regularity feature map; extract trend regularity features with a variation amplitude less than or equal to a deviation threshold from the auxiliary trend regularity feature map to obtain a first smoothness benchmark feature set.

[0014] Furthermore, performing trend regularity statistics based on the first correlation value to generate trend feature 1; performing trend regularity statistics based on the second correlation value to generate trend feature 2 includes:

[0015] The first correlation value and the structural characteristic data are subjected to trend law statistics to obtain trend feature one; the second correlation value and the load characteristic data are subjected to trend law statistics to obtain trend feature two.

[0016] Furthermore, it also includes:

[0017] The target change trend is obtained by statistically analyzing the smoothness change trends of target detection sections in different maintenance cycles; the associated change trend is obtained by statistically analyzing the smoothness change trends of adjacent associated sections in different maintenance cycles; the target change trend is compared with the associated change trend, the trend feature 1 and the trend feature of the smoothness benchmark feature set to determine whether the conditions are met.

[0018] Furthermore, the method further includes: collecting environmental impact data of the target detection section; and evaluating the environmental impact of the smoothness of the target detection section according to the environmental impact data to obtain an environmental impact coefficient.

[0019] Furthermore, the method further includes comparing the measured flatness value of the target detection section with the flatness standard value to obtain the degree of compliance.

[0020] A bridge engineering road surface smoothness detection system, applying the bridge engineering road surface smoothness detection method, comprises: a processing module, a first evaluation module, a statistical module, a second evaluation module, an integration module and a result evaluation module;

[0021] The first evaluation module, statistical module, second evaluation module, integration module and result evaluation module are respectively connected to the processing module;

[0022] The processing module is used to process and analyze the bridge road section attribute data and historical smoothness detection data to obtain a benchmark feature set;

[0023] The first evaluation module is used to evaluate the degree of correlation of the flatness between the target detection section and the adjacent associated sections to obtain a first correlation value, and to evaluate the degree of correlation of the flatness between the target detection section and the sections of the same structure to obtain a second correlation value;

[0024] The statistical module is used to perform trend regularity statistics based on the first correlation value and the second correlation value to obtain trend feature 1 and trend feature 2;

[0025] The second evaluation module is used to mark the trend feature 2 that has the same trend law as the benchmark feature set as preprocessing detection data 1; when the conditions are met, the detection data to which the trend feature 1 belongs and the measured basic data of the target detection section are comprehensively evaluated to obtain preprocessing detection data 2;

[0026] The integration module is used to generate a preprocessing feature data set based on the preprocessing detection data 1, the preprocessing detection data 2 and the trend feature 1;

[0027] The result evaluation module is used to evaluate the surface smoothness detection results of the bridge engineering road according to the preprocessing feature data set, the environmental impact coefficient and the degree of compliance to obtain a smoothness compliance index.

[0028] The beneficial effects of the present invention are as follows: the present invention integrates the road section attribute data and the historical smoothness detection data to construct a benchmark feature set, and at the same time introduces the correlation value evaluation of adjacent road sections and similar structure sections to capture the interactive influence of smoothness between road sections. The trend feature one based on the correlation value of adjacent road sections reflects the evolution of smoothness under spatial interaction; the trend feature two based on the correlation value of similar structures reflects the change pattern dominated by structural commonality. The pre-processed feature data set integrates two types of trends and the corrected measured data, so that the detection results can not only reflect the long-term stable rules, but also adapt to the dynamic changes under complex working conditions, and comprehensively characterize the smoothness status. The environmental impact coefficient quantifies the interference of temperature, precipitation, etc. on smoothness, and the degree of compliance clearly shows the degree of fit between the measured value and the qualified threshold. The two are integrated with the pre-processed feature data set to construct a smoothness compliance index, which upgrades the detection evaluation from a single data comparison to a multi-dimensional comprehensive judgment, thereby considering the compliance with historical rules and the adaptability to environmental interference. Therefore, this application greatly improves the detection accuracy, comprehensiveness and engineering adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The figure is a flow chart of a method for detecting the surface smoothness of a bridge engineering road;

[0030] Figure 2 This is a schematic diagram of the principle of a bridge engineering road surface smoothness detection system;

[0031] Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention; wherein 610 is a processor; 620 is a communication interface; 630 is a memory; and 640 is a communication bus. DETAILED DESCRIPTION

[0032] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0033] The features and performance of the present invention are further described in detail below with reference to the embodiments.

[0034] like Figure 1 As shown, a method for detecting the surface flatness of a bridge engineering road comprises the following steps:

[0035] S1. Generate a baseline feature set based on the bridge and road segment attribute data and historical roughness test data;

[0036] S2. Evaluate the smoothness correlation between the target detection section and the adjacent associated sections to obtain a first correlation value; evaluate the smoothness correlation between the target detection section and the similar structure section to obtain a second correlation value;

[0037] S3 is based on the first correlation value trend law statistics, generating a trend feature; based on the second correlation value trend law statistics, generating a trend feature two;

[0038] S4. The portion of the trend feature 2 that has the same trend pattern as the benchmark feature set is marked as pre-processed detection data 1; when the target detection segment and the adjacent associated segment have the same flatness change trend direction but the trend feature 1 deviates from the benchmark feature set, or when the target detection segment and the adjacent associated segment have different flatness change trend directions but the trend feature 1 conforms to the benchmark feature set, the detection data associated with the trend feature 1 is fused with the measured basic data of the target detection segment to generate pre-processed detection data 2;

[0039] S5. Generate a preprocessed feature data set based on the preprocessed test data 1, the preprocessed test data 2, and the trend feature 1; and obtain a flatness compliance index by combining the preprocessed feature data set, the environmental impact coefficient, and the flatness compliance level.

[0040] The generation of a benchmark feature set based on the bridge road section attribute data and historical smoothness detection data includes:

[0041] Obtain the section attribute data of the bridge road, divide the section attribute data into structural characteristic data according to the section structure type, divide the section attribute data into load characteristic data according to the traffic load level, obtain the first smoothness benchmark feature set according to the structural characteristic data, obtain the second type of smoothness benchmark feature set to which the load characteristic data belongs according to the load characteristic data and load section statistics, and combine the first smoothness benchmark feature set and the second type of smoothness benchmark feature set into a benchmark feature set.

[0042] The first flatness reference feature set is obtained by processing and analyzing the structural feature data, including:

[0043] Extract the similar structure sections to which the structural feature data belongs, and mark other sections that are structurally associated with the similar structure sections as associated structure sections; evaluate the degree of smoothness correlation between similar structure sections and associated structure sections in different maintenance cycles to obtain a smoothness correlation dataset;

[0044] Acquire the smoothness detection data of the associated structural section to obtain auxiliary detection data, and establish a smoothness detection dataset based on the smoothness associated dataset and the auxiliary detection data; perform curve trend judgment on the smoothness detection dataset to obtain an auxiliary trend regularity feature map; extract trend regularity features with a variation amplitude less than or equal to a deviation threshold from the auxiliary trend regularity feature map to obtain a first smoothness benchmark feature set.

[0045] The performing trend regularity statistics based on the first correlation value to generate trend feature 1; and performing trend regularity statistics based on the second correlation value to generate trend feature 2, including:

[0046] The first correlation value and the structural characteristic data are subjected to trend law statistics to obtain trend feature one; the second correlation value and the load characteristic data are subjected to trend law statistics to obtain trend feature two.

[0047] It also includes: statistically analyzing the flatness change trends of target detection sections in different maintenance cycles to obtain target change trends; statistically analyzing the flatness change trends of adjacent related sections in different maintenance cycles to obtain related change trends; comparing the target change trend with the related change trend, the trend feature 1 and the trend feature of the flatness benchmark feature set to determine whether the conditions are met.

[0048] It also includes: collecting environmental impact data of the target detection section; evaluating the environmental impact of the smoothness of the target detection section based on the environmental impact data to obtain an environmental impact coefficient.

[0049] It also includes: comparing the measured flatness value of the target detection section with the flatness standard value to obtain the degree of compliance.

[0050] A bridge engineering road surface smoothness detection system, applying the bridge engineering road surface smoothness detection method, comprises: a processing module, a first evaluation module, a statistical module, a second evaluation module, an integration module and a result evaluation module;

[0051] The first evaluation module, statistical module, second evaluation module, integration module and result evaluation module are respectively connected to the processing module;

[0052] The processing module is used to process and analyze the bridge road section attribute data and historical smoothness detection data to obtain a benchmark feature set;

[0053] The first evaluation module is used to evaluate the degree of correlation of the flatness between the target detection section and the adjacent associated sections to obtain a first correlation value, and to evaluate the degree of correlation of the flatness between the target detection section and the sections of the same structure to obtain a second correlation value;

[0054] The statistical module is used to perform trend regularity statistics based on the first correlation value and the second correlation value to obtain trend feature 1 and trend feature 2;

[0055] The second evaluation module is used to mark the trend feature 2 that has the same trend law as the benchmark feature set as preprocessing detection data 1; when the conditions are met, the detection data to which the trend feature 1 belongs and the measured basic data of the target detection section are comprehensively evaluated to obtain preprocessing detection data 2;

[0056] The integration module is used to generate a preprocessing feature data set based on the preprocessing detection data 1, the preprocessing detection data 2 and the trend feature 1;

[0057] The result evaluation module is used to evaluate the surface smoothness detection results of the bridge engineering road according to the preprocessing feature data set, the environmental impact coefficient and the degree of compliance to obtain a smoothness compliance index.

[0058] Specifically, a method for detecting the surface flatness of a bridge engineering road proposed in the present invention is further described.

[0059] A method for detecting the surface smoothness of a bridge engineering road comprises the following steps:

[0060] The bridge road section attribute data and historical roughness detection data are processed and analyzed to obtain the benchmark feature set;

[0061] The degree of flatness correlation between the target detection section and adjacent associated sections is evaluated to obtain a first correlation value, and the degree of flatness correlation between the target detection section and sections of similar structure is evaluated to obtain a second correlation value;

[0062] Perform trend law statistics based on the first correlation value and the second correlation value to obtain trend feature 1 and trend feature 2;

[0063] The trend feature 2 having the same trend pattern as the benchmark feature set is marked as pre-processed detection data 1; when conditions are met, the detection data to which the trend feature 1 belongs and the measured basic data of the target detection section are comprehensively evaluated to obtain pre-processed detection data 2;

[0064] A preprocessing feature data set is generated based on the preprocessing detection data 1, the preprocessing detection data 2 and the trend feature 1;

[0065] The surface roughness test results of the bridge engineering road are evaluated based on the preprocessed feature data set, environmental impact coefficient and compliance level to obtain the smoothness compliance index.

[0066] This application first collects road section attribute data and historical smoothness test data for bridge roads. The road section attribute data includes the structural type, material parameters, and geometric dimensions of the road section, and the historical smoothness test data includes test results from different periods and environments. A benchmark feature set that reflects the long-term stability of the bridge road smoothness is then compiled, such as the smoothness decay curve of similar structural sections over time under normal load and environmental conditions, or the critical smoothness thresholds corresponding to different traffic load levels.

[0067] The interaction between the smoothness of the target detection section and other sections is explored from two dimensions: spatial correlation and structural correlation. The correlation between the smoothness changes of the target detection section and adjacent related sections is calculated to obtain the first correlation value. The smoothness decay rate of the target detection section and similar structural sections under the same maintenance cycle and traffic load is calculated to obtain the second correlation value.

[0068] Trend features are extracted based on the first and second correlation values. The temporal trend of the relationship between the roughness of the target section and adjacent sections is determined by combining the attribute differences of adjacent sections. This allows identification of the increasing or decreasing impact of adjacent sections on the target section's smoothness during situations such as peak traffic periods and seasonal changes. Based on the commonalities of similar structural sections, the smoothness trend of the target section with structural aging and load accumulation is refined. The smoothness decay curves of similar sections are then fitted to determine characteristic parameters such as initial smoothness and decay rate.

[0069] The part of trend feature 2 that is completely consistent with the trend law of the benchmark feature set is screened and marked as preprocessed detection data 1. When the flatness change trends of the target road section and the adjacent road section are in the same direction but trend feature 1 does not match the benchmark feature set, or in opposite directions but the benchmark features match, the detection data associated with trend feature 1 is fused with the measured basic data of the target road section, and preprocessed detection data 2 is generated through weighted calculation.

[0070] The preprocessed detection data 1 and the preprocessed detection data 2 are then integrated with the trend feature 1 to form a preprocessed feature data set. This data set brings together the flatness trend curves under different correlation relationships, the corrected measured data and historical trend matching results, as well as abnormal fluctuations and correction logic in special scenarios, providing comprehensive and layered information support for the final evaluation.

[0071] Environmental data is collected during testing, and the quantitative coefficient affecting the smoothness is determined based on the environmental data, such as the weight of the impact of high temperature on the softening of the asphalt pavement, which leads to a decrease in smoothness. The measured smoothness value is compared with the standard value to calculate the compliance ratio, deviation amplitude and other compliance levels. The smoothness compliance index is obtained by weighted summing and fusing the trend matching degree, environmental impact coefficient and compliance level of the preprocessed feature data set. The index reflects the degree to which the flatness meets the standard, and abnormalities trigger early warnings.

[0072] The road section attribute data and historical roughness detection data of the bridge road are processed and analyzed to obtain the roughness benchmark feature set, which specifically includes the following steps:

[0073] Obtaining the road section attribute data of the bridge road;

[0074] The road section attribute data is divided into structural characteristic data according to the road section structure type, and the road section attribute data is divided into load characteristic data according to the traffic load level;

[0075] Processing and analyzing the structural feature data to obtain a first flatness benchmark feature set;

[0076] According to the load characteristic data and the load section statistics, the second type of flatness benchmark characteristic set to which the load characteristic data belongs is obtained;

[0077] The first flatness reference feature set and the second type of flatness reference feature set are combined into a reference feature set.

[0078] This application obtains the section attribute data of the bridge road, and then classifies and sorts the section attribute data, dividing it into structural characteristic data according to the section structure type, such as the attributes corresponding to different bridge structures such as beam type and slab type; at the same time, it divides the load characteristic data according to the traffic load level, such as the section attributes corresponding to light and heavy loads.

[0079] The inherent patterns in smoothness across different structural types of road sections are explored, such as the typical patterns of smoothness changes over long-term use due to the mechanical properties and material distribution of a specific structure. Through statistical and fitting methods, a first-class smoothness benchmark feature set is extracted, which reflects the smoothness benchmark situation dominated by structural factors. Load characteristic data is combined with loaded road sections to determine the patterns in how the smoothness of a section is affected by different traffic load levels. For example, the characteristics of smoothness attenuation and deformation after repeated application of different loads are determined, thereby obtaining the second-class smoothness benchmark feature set to which the load characteristic data belongs.

[0080] The first type of flatness benchmark feature set and the second type of flatness benchmark feature set are combined to jointly construct a benchmark feature set that comprehensively reflects the correlation between bridge and road section attributes and flatness from the two key dimensions of structure and load.

[0081] The first flatness reference feature set is obtained by processing and analyzing the structural feature data, specifically comprising the following steps:

[0082] Extracting the same type of structural road segments to which the structural feature data belongs, and marking other road segments that are structurally associated with the same type of structural road segments as associated structural road segments;

[0083] The smoothness correlation degree between similar structure sections and associated structure sections with different maintenance cycles is evaluated to obtain a smoothness correlation dataset;

[0084] Acquire the smoothness detection data of the associated structure road section to obtain auxiliary detection data, and establish a smoothness detection data set based on the smoothness associated data set and the auxiliary detection data;

[0085] The curve trend of the flatness detection data set is judged to obtain an auxiliary trend regularity feature map;

[0086] The trend regularity features with a variation amplitude less than or equal to the deviation threshold are extracted from the auxiliary trend regularity feature graph to obtain a first flatness reference feature set.

[0087] This application extracts similar structural sections based on structural feature data, that is, sections with similar structural design, materials, construction, etc., and marks other sections that have structural associations with similar structural sections as associated structural sections. Structural associations are sections that have common supporting structures and connection structures and influence each other in terms of force or structural integrity.

[0088] The degree of correlation between the smoothness of similar and related structural sections at different maintenance cycles is determined. Because different maintenance cycles can lead to differences in the condition and performance of road sections, the smoothness correlation between these differences is evaluated, such as the synchronization of smoothness changes and the strength of their mutual influence. This creates a smoothness correlation dataset that records the smoothness correlation patterns between structurally related sections at different maintenance stages.

[0089] The roughness detection data of the associated structure road sections is obtained as auxiliary detection data, and combined with the roughness association dataset to create a roughness detection dataset. This dataset contains both the association relationship information of the roughness between road sections and the actual detected roughness values.

[0090] The curve trend of the flatness detection data set is judged, and the data is converted into an intuitive auxiliary trend regularity characteristic diagram, which shows the trend of flatness changes with time, maintenance cycle and other factors through graphics.

[0091] From the auxiliary trend regularity feature graph, trend regularity features with a variation amplitude less than or equal to the deviation threshold are selected. These features represent relatively stable, low-fluctuation flatness variation patterns, and are extracted to form the first flatness benchmark feature set.

[0092] Performing trend law statistics based on the first correlation value and the second correlation value to obtain trend feature 1 and trend feature 2 specifically includes the following steps:

[0093] Perform trend regularity statistics on the first correlation value and the structural feature data to obtain trend feature 1;

[0094] The second correlation value and the load characteristic data are statistically analyzed to obtain the trend characteristic 2.

[0095] The first correlation value reflects the degree of correlation between the smoothness of the target detection section and the adjacent correlated sections. The first correlation value and the structural feature data are combined to perform trend law statistics to determine how the first correlation value changes with the differences in the structural feature data, and then obtain trend feature 1, which reflects the changing trend of the smoothness correlation under the joint action of the adjacent correlation relationship and the structural feature.

[0096] The second correlation value represents the degree of smoothness correlation between the target road section and similar structural sections. This is then integrated with load characteristic data, which can be traffic load level information. Trend analysis of these two factors reveals how the second correlation value changes under different load characteristic data (such as load magnitude and load frequency), as well as the development trend of this correlation over different stages. This yields the second trend feature, which reflects the changing state of smoothness correlation under the combined influence of similar structural correlations and load characteristics.

[0097] The method further includes the following steps: performing statistics on the flatness change trends of target detection sections in different maintenance cycles to obtain target change trends; performing statistics on the flatness change trends of adjacent associated sections in different maintenance cycles to obtain associated change trends;

[0098] Compare the target change trend with the associated change trend, the trend feature 1 and the trend feature of the flatness benchmark feature set to see if they meet the conditions.

[0099] This application collects statistics on the smoothness changes of target road sections over different maintenance cycles, identifying target smoothness trends, such as whether the smoothness increases, decreases, or fluctuates as the maintenance cycle progresses. This clearly presents the evolution of the smoothness of the target road section itself. At the same time, the smoothness changes of adjacent, related road sections over different maintenance cycles are also counted. Because adjacent sections are affected by traffic flow conduction and structural linkage, which leads to potential correlations in smoothness changes, the associated change trends are derived, clarifying the direction of smoothness changes in adjacent sections.

[0100] The target change trend is then compared with the associated change trend, while Trend Feature 1 is also compared with the trend features of the roughness benchmark feature set. These two comparisons are used to determine whether specific conditions are met. This is done to determine whether the correlation between the target section's roughness changes and adjacent sections is abnormal, and whether the target section's own correlation trend deviates from the benchmark pattern, based on the maintenance cycle. This provides a basis for subsequent comprehensive evaluation of the roughness test results based on trend comparisons, ensuring that abnormal roughness changes caused by factors such as maintenance and section correlation can be identified.

[0101] Compare the target change trend with the associated change trend, the trend feature 1 and the trend feature of the flatness benchmark feature set to see if they meet the conditions;

[0102] If the target change trend and the associated change trend have the same change trend direction, and the trend feature 1 does not match the trend feature of the flatness benchmark feature set, then it is determined to meet the conditions;

[0103] If the target change trend and the associated change trend have different change trend directions, and the trend feature 1 is consistent with the trend feature of the flatness reference feature set, then it is determined that the condition is met.

[0104] This application first focuses on the relationship between the change trends of the target detection segment and adjacent associated segments, and also considers the fit between Trend Feature 1 and the roughness benchmark feature set. When the target change trend and the associated change trend align, but Trend Feature 1 does not match the trend features of the benchmark feature set, this indicates that while the segments are changing in the same direction, they have deviated from the historically stable correlation pattern.

[0105] When the target change trend and the associated change trend diverge, the link between the road sections may be weak under normal circumstances. However, if Trend Feature 1 matches the trend features of the baseline feature set, this means that despite the diverging directions, the associated logic still aligns with the historical baseline pattern. This situation is also considered qualified and may be caused by short-term environmental disturbances or local maintenance differences, requiring special case analysis. These two conditions capture the extent of roughness changes and provide a basis for subsequent comprehensive evaluation.

[0106] The method also includes the following steps: collecting environmental impact data of the target detection section; and evaluating the environmental impact of the smoothness of the target detection section according to the environmental impact data to obtain an environmental impact coefficient.

[0107] This application collects environmental impact data for the target inspection section. This data covers various environmental information that may affect road smoothness, such as temperature, humidity, precipitation, and wind. Based on the collected environmental impact data, the mechanism by which different environmental conditions affect the smoothness of the target inspection section is determined. For example, high temperatures may cause asphalt pavement to soften and deform, while rainfall may cause roadbed settlement and affect road smoothness. The environmental impact coefficient is evaluated by quantifying the correlation between these environmental factors and changes in smoothness.

[0108] It also includes: comparing the measured flatness value of the target detection section with the flatness standard value to obtain the degree of compliance.

[0109] This application obtains the measured flatness value of the target detection section. This is the data obtained by actual measurement on the road section using professional detection equipment, such as a flatness meter, which truly reflects the flatness of the current road section surface. Then the flatness standard value is determined. This standard value is set according to the specifications and design requirements of relevant bridge projects and road projects, and represents the qualified level of flatness that the road section should achieve. The measured flatness value is compared with the standard value, and the difference is calculated to determine whether the measured value is higher, lower or equal to the standard value, and then the degree of compliance is obtained, which clearly shows whether the flatness of the road section meets the standard, and provides a key basic judgment basis for the subsequent comprehensive evaluation of whether the road surface flatness is compliant.

[0110] Example 2 further illustrates a bridge engineering road surface flatness detection system proposed by the present invention.

[0111] A bridge engineering road surface smoothness detection system, comprising:

[0112] Processing module: Processing and analyzing the bridge road section attribute data and historical smoothness detection data to obtain a benchmark feature set;

[0113] A first evaluation module is configured to evaluate the degree of correlation between the flatness of the target detection section and adjacent associated sections to obtain a first correlation value, and to evaluate the degree of correlation between the flatness of the target detection section and sections of similar structures to obtain a second correlation value;

[0114] Statistics module: performing trend regularity statistics based on the first correlation value and the second correlation value to obtain trend feature 1 and trend feature 2;

[0115] The second evaluation module: Marks the trend feature 2 that has the same trend pattern as the benchmark feature set as pre-processed detection data 1; When the conditions are met, the detection data to which the trend feature 1 belongs and the measured basic data of the target detection section are comprehensively evaluated to obtain pre-processed detection data 2;

[0116] Integration module: generates a preprocessing feature data set based on preprocessing detection data 1, preprocessing detection data 2 and trend feature 1;

[0117] Result evaluation module: The surface roughness test results of the bridge engineering road are evaluated based on the preprocessed feature data set, environmental impact coefficient and compliance level to obtain the roughness compliance index.

[0118] An electronic device includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, a method for detecting the surface flatness of a bridge engineering road is implemented.

[0119] like Figure 3 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call logic instructions in the memory 630 to execute a method for detecting the surface flatness of a bridge engineering road.

[0120] Furthermore, the logic instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as a standalone product, stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for causing a computer device (such as a personal computer, server, or network device) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0121] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a method for detecting the surface flatness of a bridge engineering road.

[0122] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is used to implement a method for detecting the surface flatness of a bridge engineering road when the computer program is executed by a processor.

[0123] The foregoing description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein and should not be construed as excluding other embodiments. Rather, the present invention can be used in various other combinations, modifications, and environments and can be modified within the scope of the concept described herein through the above teachings or techniques or knowledge in the relevant field. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention are intended to be protected by the appended claims.

Claims

1. A method for detecting the surface flatness of a bridge engineering road, characterized in that: The following steps are involved: S1. Generate a baseline feature set based on the bridge and road segment attribute data and historical roughness test data; S2. Evaluate the smoothness correlation between the target detection section and the adjacent associated sections to obtain a first correlation value; evaluate the smoothness correlation between the target detection section and the similar structure section to obtain a second correlation value; S3 based on the first correlation value trend regularity statistics, generating a trend feature; Perform trend regularity statistics based on the second correlation value to generate trend feature 2; S4. The trend feature of the second part of the same trend law as the benchmark feature set is marked as pre-processed detection data one; When the roughness change trend direction of the target detection section and the adjacent associated section is the same but the trend feature 1 deviates from the benchmark feature set, or the roughness change trend direction of the target detection section and the adjacent associated section is different but the trend feature 1 conforms to the benchmark feature set, the detection data associated with the trend feature 1 is fused with the measured basic data of the target detection section to generate preprocessed detection data 2; S5. Based on the preprocessed detection data, preprocessed detection data and trend characteristics of the second, generate a preprocessed feature data set; The flatness compliance index is obtained by combining the preprocessed feature data set, the environmental impact coefficient and the flatness compliance degree.

2. A method for detecting the surface flatness of a bridge engineering road according to claim 1, characterized in that: The generation of a benchmark feature set based on the bridge road section attribute data and historical smoothness detection data includes: Obtain the section attribute data of the bridge road, divide the section attribute data into structural characteristic data according to the section structure type, divide the section attribute data into load characteristic data according to the traffic load level, obtain the first smoothness benchmark feature set according to the structural characteristic data, obtain the second type of smoothness benchmark feature set to which the load characteristic data belongs according to the load characteristic data and load section statistics, and combine the first smoothness benchmark feature set and the second type of smoothness benchmark feature set into a benchmark feature set.

3. A method for detecting the surface flatness of a bridge engineering road according to claim 2, characterized in that: The method of obtaining the first flatness reference feature set according to the structural feature data includes: Extract the similar structure sections to which the structural feature data belongs, and mark other sections that are structurally associated with the similar structure sections as associated structure sections; evaluate the degree of smoothness correlation between similar structure sections and associated structure sections in different maintenance cycles to obtain a smoothness correlation dataset; Acquire the smoothness detection data of the associated structural section to obtain auxiliary detection data, and establish a smoothness detection dataset based on the smoothness associated dataset and the auxiliary detection data; perform curve trend judgment on the smoothness detection dataset to obtain an auxiliary trend regularity feature map; extract trend regularity features with a variation amplitude less than or equal to a deviation threshold from the auxiliary trend regularity feature map to obtain a first smoothness benchmark feature set.

4. A method for detecting the surface flatness of a bridge engineering road according to claim 2, characterized in that: performing trend regularity statistics based on the first correlation value to generate trend feature 1; Performing trend regularity statistics based on the second correlation value to generate trend feature 2 includes: Perform trend regularity statistics on the first correlation value and the structural feature data to obtain trend feature 1; The second correlation value and the load characteristic data are statistically analyzed to obtain the trend characteristic 2.

5. A method for detecting the surface flatness of a bridge engineering road according to claim 1, characterized in that: Also includes: The target change trend is obtained by statistically analyzing the flatness change trend of target detection sections in different maintenance cycles; The correlation change trend is obtained by statistically analyzing the roughness change trend of adjacent related road sections in different maintenance cycles; Compare the target change trend with the associated change trend, trend feature 1 and the trend feature of the flatness benchmark feature set to determine whether the conditions are met.

6. A method for detecting the surface flatness of a bridge engineering road according to claim 1, characterized in that: Also includes: Collect environmental impact data of target detection sections; The environmental impact coefficient is obtained by evaluating the environmental impact of the smoothness of the target detection section based on the environmental impact data.

7. A method for detecting the surface flatness of a bridge engineering road according to claim 1, characterized in that: Also includes: The measured roughness value of the target detection section is compared with the standard roughness value to obtain the degree of compliance.

8. A bridge engineering road surface flatness detection system, characterized in that: The application claims are to a method for detecting the surface flatness of a bridge engineering road as described in any one of 1-7, comprising: a processing module, a first evaluation module, a statistical module, a second evaluation module, an integration module and a result evaluation module; The first evaluation module, statistical module, second evaluation module, integration module and result evaluation module are respectively connected to the processing module; The processing module is used to process and analyze the bridge road section attribute data and historical smoothness detection data to obtain a benchmark feature set; The first evaluation module is used to evaluate the degree of correlation of the flatness between the target detection section and the adjacent associated sections to obtain a first correlation value, and to evaluate the degree of correlation of the flatness between the target detection section and the sections of the same structure to obtain a second correlation value; The statistical module is used to perform trend regularity statistics based on the first correlation value and the second correlation value to obtain trend feature 1 and trend feature 2; The second evaluation module is used to mark the trend feature 2 that has the same trend law as the benchmark feature set as preprocessing detection data 1; when the conditions are met, the detection data to which the trend feature 1 belongs and the measured basic data of the target detection section are comprehensively evaluated to obtain preprocessing detection data 2; The integration module is used to generate a preprocessing feature data set based on the preprocessing detection data 1, the preprocessing detection data 2 and the trend feature 1; The result evaluation module is used to evaluate the surface smoothness detection results of the bridge engineering road according to the preprocessing feature data set, the environmental impact coefficient and the degree of compliance to obtain a smoothness compliance index.

Images