CN118656773B - Roadbed compaction quality intelligent monitoring method, device and system - Google Patents

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent monitoring method, device and system for roadbed compaction quality, which comprises the following steps: obtaining a plurality of data sequences; obtaining the road surface smoothness index of each elevation data in each data sequence; combining the numerical value of each elevation data to obtain the elevation outlier of each elevation data; according to the distribution of the elevation outliers of the elevation data in each data sequence, each data sequence is divided into a plurality of fluctuation intervals, fluctuation kurtosis parameters of each elevation data in each fluctuation interval are obtained, elevation fluctuation interference degree of each elevation data is obtained, abnormal distances between each elevation data and other elevation data are obtained, abnormal data are further obtained, and the road surface to be detected is detected. The invention aims to solve the problem that when the elevation data of the pavement to be detected is removed, partial undisturbed data is removed.

Description

A roadbed compaction quality intelligent monitoring method, device and system

Technical Field

The present invention relates to the technical field of data processing, and in particular to a method, device and system for intelligently monitoring roadbed compaction quality.

Background Art

As an important part of the highway, compaction of the roadbed and pavement is an important part of the construction process and is also the key to the overall quality of the highway. The roadbed and pavement compaction technology uses equipment such as rollers to squeeze the roadbed and pavement construction materials to reduce their volume, increase the density structure, improve the stability and service life of the roadbed and pavement, and reduce the safety hazards of vehicle driving. After the roadbed is compacted, multiple tests including compaction test, flatness test, and deflection value test are required to evaluate the compaction quality. Among them, the test of pavement flatness is an important step in verifying the compaction quality. Once there is a problem with the flatness of the roadbed and pavement, the probability of settlement and cracks will increase during the use of the highway, reducing vehicle driving safety and increasing unnecessary maintenance costs. Therefore, the flatness of the roadbed and pavement is monitored.

The existing monitoring method uses a road surface laser roughness meter to detect and analyze the roughness of the roadbed and road surface. After analyzing the road data, the instrument obtains a variety of road surface roughness evaluation indicators. However, in the actual detection process, it will be interfered by external factors, so the collected data needs to be cleaned. However, the existing data cleaning algorithm is difficult to distinguish between abnormal data caused by external factors and abnormal data caused by uneven road compaction. For example, the change in measurement height caused by the shaking of the vehicle body during driving is similar to the change of the uneven compacted road surface, which makes it easy to ignore the data changes of some of the above factors in the road roughness data cleaning process, which leads to inaccurate road surface roughness evaluation indicators.

Summary of the invention

The present invention provides a method, device and system for intelligently monitoring roadbed compaction quality to solve the existing problems.

The intelligent monitoring method, device and system for roadbed compaction quality of the present invention adopt the following technical solutions:

The present invention proposes a roadbed compaction quality intelligent monitoring method, which comprises the following steps:

Acquire the elevation data of each acquisition position on the road surface to be detected, construct a two-dimensional coordinate system, obtain the elevation data of each data point in the two-dimensional coordinate system, and then obtain a plurality of data sequences; each data point in the two-dimensional coordinate system corresponds to a acquisition position on the road surface to be detected;

According to the numerical difference between each elevation data and the adjacent elevation data in each data sequence, the road surface smoothness index of each elevation data in each data sequence is obtained; according to the numerical values of all elevation data in each data sequence and the road surface smoothness index, the elevation outlier of each elevation data is obtained;

According to the distribution of elevation outliers of elevation data in each data sequence, each data sequence is divided into several fluctuation intervals; according to the values of elevation data in each fluctuation interval and the difference between the elevation outliers of adjacent elevation data, the fluctuation kurtosis parameter of each elevation data in each fluctuation interval is obtained; according to the fluctuation kurtosis parameters and their distribution of all elevation data in each fluctuation interval, the elevation fluctuation interference of each elevation data is obtained;

According to the value of each elevation data, the elevation fluctuation interference, the elevation outlier and the coordinates of the corresponding data points, the abnormal distance between each elevation data and other elevation data is obtained, and then the abnormal local factor of each elevation data is obtained; according to the local abnormal factor of each elevation data, the abnormal data is obtained, and the road surface to be inspected is inspected.

Furthermore, the obtaining of the plurality of data sequences includes the following specific methods:

In the two-dimensional coordinate system The elevation data corresponding to all data points in the column is used as the Elements in a data sequence;

According to the vertical coordinate of the data point corresponding to the elevation data, Arrange the elevation data in the data sequence in ascending order and get the A data sequence.

Furthermore, the road surface smoothness index of each elevation data in each data sequence is obtained according to the numerical difference between each elevation data in each data sequence and the adjacent elevation data, including the specific method of:

The first In the data sequence The elevation data minus the The difference of the elevation data is taken as the In the data sequence The left slope of the elevation data;

Get the In the data sequence The specific calculation formula for the road surface smoothness index of elevation data is as follows:

In the formula, Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The left slope of the elevation data, Indicates In the data sequence The left slope of the elevation data, represents the absolute value function, is an exponential function with a natural constant as its base.

Furthermore, the elevation outlier of each elevation data is obtained according to the values of all elevation data in each data sequence and the road surface smoothness index, including the specific method of:

In the formula, Indicates In the data sequence The elevation outlier of the elevation data, Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The value of the elevation data, Represents the number of data points contained in each row in the two-dimensional coordinate system. Represents the number of data points contained in each column in the two-dimensional coordinate system. Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The value of the elevation data, represents the absolute value function, Represents the softmax normalization function.

Furthermore, the method of dividing each data sequence into a number of fluctuation intervals according to the distribution of the elevation outliers of the elevation data in each data sequence includes the following specific methods:

In the In a data sequence, if the The elevation outlier of the first elevation data is greater than that of the The elevation outlier of the elevation data is The first The elevation data is recorded as The suspected interval starting point in the data sequence;

The first The suspected interval starting point whose elevation outlier degree in a data sequence is less than or equal to the elevation outlier degree of the previous suspected region starting point is recorded as the non-suspected interval starting point;

From Remove the non-suspected interval starting points from the suspected interval starting points in the data sequence, and record the other suspected interval starting points as Possible interval starting points within a data sequence;

According to The height outlier of the possible interval starting point in the data sequence is The possible interval starting points in the data sequence are arranged in ascending order to obtain the The possible interval sequence of a data sequence;

Calculate the The possible interval sequence of a data sequence The absolute value of the difference in elevation outlier between the starting point of the first possible interval and the starting point of the next interval is recorded as The possible interval sequence of a data sequence differences;

The first The minimum value of the height outlier of the two possible interval starting points corresponding to the maximum difference in the possible interval sequence of the data sequence is recorded as The starting point threshold of a data sequence;

The first The height outlier degree in the data series is greater than The possible interval starting point of the starting point threshold of the data sequence, The first and last elevation data in a data sequence are recorded as The final interval starting point in the data sequence; The first The starting point of the final interval is The elevation data within the starting point of the final interval and the The final interval starting point is The first elements within the fluctuation range; The data series is divided into several fluctuation intervals.

Furthermore, the fluctuation kurtosis parameter of each elevation data in each fluctuation interval is obtained according to the value of the elevation data in each fluctuation interval and the difference between the elevation outliers of adjacent elevation data, including the specific method of:

Any fluctuation interval in any data sequence is recorded as the target fluctuation interval, and the specific calculation formula for obtaining the fluctuation kurtosis parameter of each elevation data in the target fluctuation interval is as follows:

In the formula, Indicates the target fluctuation range. The fluctuation kurtosis parameter of the elevation data, Indicates the target fluctuation range. The value of the elevation data, Indicates the target fluctuation range. The value of the elevation data, Represents the mean of all elevation data within the target fluctuation range. Indicates the target fluctuation range. The elevation outlier of the elevation data, Indicates the target fluctuation range. The elevation outlier of the elevation data, represents the absolute value function, Represents the first adjustment coefficient.

Furthermore, the elevation fluctuation interference degree of each elevation data is obtained according to the fluctuation kurtosis parameter and its distribution of all elevation data in each fluctuation interval, including the specific method of:

In the formula, Indicates the elevation fluctuation interference degree of the target fluctuation range, Indicates the number of elevation data contained in the target fluctuation range. Indicates the target fluctuation range. The fluctuation kurtosis parameter of the elevation data, It represents the mean value of the fluctuation kurtosis parameter of all elevation data within the target fluctuation range. is an exponential function with a natural constant as base;

The elevation fluctuation interference degree of the target fluctuation interval is recorded as the elevation fluctuation interference degree of each elevation data within the target fluctuation interval.

Furthermore, the abnormal distance between each elevation data and other elevation data is obtained according to the value of each elevation data, the elevation fluctuation interference, the elevation outlier and the coordinates of the corresponding data point, including the specific method of:

The first The data point corresponding to the elevation data is The square of the Euclidean distance between the data points corresponding to the first elevation data is recorded as The elevation data and The first distance of the elevation data;

The calculation formula for calculating the abnormal distance between each elevation data and other elevation data is as follows:

In the formula, Indicates The elevation data and The abnormal distance of the elevation data, Indicates The elevation data and The mean of the elevation outliers of the elevation data, Indicates The elevation fluctuation interference of the elevation data is Indicates The elevation fluctuation interference of the elevation data is Indicates The elevation data and The first distance of the elevation data, Indicates The value of the elevation data, Indicates The value of the elevation data.

The present invention also proposes a roadbed compaction quality intelligent monitoring device, which includes:

A data acquisition module, a data analysis module and a pavement detection module; wherein the data acquisition module and the data analysis module obtain abnormal pavement elevation data by calling a computer program to implement the steps of an intelligent monitoring method for roadbed compaction quality, and the pavement detection module obtains the international roughness index of the pavement to be detected based on other elevation data after removing the abnormal pavement elevation data.

The present invention also proposes an intelligent monitoring system for roadbed compaction quality, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above method.

The beneficial effects of the technical solution of the present invention are as follows: in the process of removing the elevation data disturbed by external factors in the road surface to be detected, the present invention obtains the road surface flatness index of each elevation data in each data sequence according to the numerical difference between each elevation data and the adjacent elevation data in each data sequence, based on the characteristic that the elevation data change obtained due to the normal height change of the road surface is a relatively stable process, so that the elevation outlier of the elevation data of the normal road surface is significantly different from the elevation outlier of the elevation data disturbed by external factors and the unqualified surface quality; in the process of dividing each data sequence into intervals, based on the characteristic that the elevation influence of the elevation data affected by the pebbles on the ground is relatively small, the elevation outlier of the elevation data affected by the pebbles on the ground is relatively small. The affected elevation data is not the starting point of the final interval, which reduces the number of intervals and the amount of calculation; when the vehicle shakes due to external interference factors, the vehicle is still driving on a stable road, so that the vehicle body gradually recovers its balance during the shaking process, and road defects usually do not cause the vehicle body to continue shaking. According to the value of the elevation data in each fluctuation interval and the difference between the elevation outliers of adjacent elevation data, the elevation fluctuation interference degree of each elevation data is obtained, so that the elevation data disturbed by external factors and the elevation data affected by road defects have a more obvious difference, the local anomaly factor of the elevation data disturbed by external factors is larger, and the elevation data disturbed by external factors is easier to distinguish, thereby improving the accuracy of the road surface detection results.

BRIEF DESCRIPTION OF THE DRAWINGS

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

FIG1 is a flow chart of the steps of a method for intelligently monitoring roadbed compaction quality according to the present invention;

FIG. 2 is a schematic diagram of a vehicle-mounted laser roughness meter and a two-dimensional coordinate system.

DETAILED DESCRIPTION

In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a roadbed compaction quality intelligent monitoring method, device and system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

The specific scheme of the intelligent monitoring method, device and system for roadbed compaction quality provided by the present invention is described in detail below with reference to the accompanying drawings.

Please refer to FIG1 , which shows a flowchart of a method for intelligent monitoring of roadbed compaction quality provided by an embodiment of the present invention. The method includes the following steps:

Step S001: obtain the elevation data of each acquisition position in the road surface to be detected, construct a two-dimensional coordinate system, obtain the elevation data of each data point in the two-dimensional coordinate system, and then obtain a number of data sequences.

This embodiment detects the flatness of the road surface to be detected, so the elevation data of each acquisition position in the road surface to be detected is obtained.

Specifically, the elevation data of each acquisition position in the road surface to be detected is obtained by using a vehicle-mounted laser roughness meter. A two-dimensional coordinate system is obtained by taking the horizontal coordinate as the position of the acquisition position in the roughness meter and the vertical coordinate as the relative position of the roughness meter and the initial position when the roughness meter passes through the acquisition position. The vehicle-mounted laser roughness meter and the two-dimensional coordinate system are shown in FIG2. The acquisition position in the road surface to be detected is mapped to the two-dimensional coordinate system to obtain several data points in the two-dimensional coordinate system. The data point in the two-dimensional coordinate system corresponds to a acquisition position in the road surface to be detected.

Furthermore, the first The elevation data corresponding to all data points in the column is used as the The elements in the data sequence are compared according to the ordinate of the data point corresponding to the elevation data. Arrange the elevation data in the data sequence in ascending order and get the data sequence. And, One elevation data in a data sequence corresponds to a collection position on the road surface to be detected.

Step S002: Obtain the road surface smoothness index of each elevation data in each data sequence according to the numerical difference between each elevation data and the adjacent elevation data in each data sequence; obtain the elevation outlier of each elevation data according to the numerical values of all elevation data in each data sequence and the road surface smoothness index.

It should be noted that, for the elevation data of the road to be tested, the abnormal data to be cleaned are the elevation data disturbed by external factors during the collection process. Since the values of the elevation data disturbed by external factors, the elevation data affected by unqualified road quality, and the elevation data affected by the change in road height are all significantly different from the values of normal elevation data, it is not possible to directly judge whether each elevation data is the abnormal data to be cleaned based on the value of each elevation data.

It should be further explained that, since the height change of normal road surface is usually a continuous process, the change of elevation data obtained by vehicle body tilt due to normal road surface height change is a relatively stable process; however, due to unqualified road surface quality or interference by external factors, the change of acquired elevation data is not a relatively stable process. Therefore, according to the numerical difference between each elevation data and the surrounding elevation data in each data sequence, the road surface flatness index of each elevation data is calculated. According to the numerical value of each elevation data and the road surface flatness index, the elevation outlier of each elevation data is obtained, so that the elevation outlier of the elevation data affected by the change of road surface height is significantly different from the elevation outlier of the elevation data interfered by external factors and the elevation data affected by unqualified road surface quality.

Specifically, the In the data sequence The elevation data minus the The difference of the elevation data is taken as the In the data sequence The left slope of the elevation data; in particular, let The value of the left slope of the first elevation data in a data sequence is In the data sequence The value of the left slope of the elevation data. In the data sequence The specific calculation formula for the road surface smoothness index of elevation data is as follows:

In the formula, Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The left slope of the elevation data, Indicates In the data sequence The left slope of the elevation data, represents the absolute value function, is an exponential function with a natural constant as the base. Model to present inverse proportional relationship and normalization, As the input of the model, the implementer can set the inverse proportional function and normalization function according to the actual situation.

It should be noted that The smaller the value, the In the data sequence The smaller the difference in elevation data changes on both sides of the first elevation data, the more consistent it is with the fact that the elevation data changes obtained due to the vehicle body tilt caused by the change in road height are a relatively stable feature. In the data sequence The larger the road surface flatness index of an elevation data is, the greater the possibility that it is normal elevation data.

Further, get the The specific calculation formula for the elevation outlier of each elevation data in a data sequence is as follows:

In the formula, Indicates In the data sequence The elevation outlier of the elevation data, Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The value of the elevation data, Represents the number of data points contained in each row in the two-dimensional coordinate system. Represents the number of data points contained in each column in the two-dimensional coordinate system. Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The value of the elevation data, represents the absolute value function, Represents the softmax normalization function, and the normalized object is the road surface smoothness index of all elevation data in all data sequences.

It should be noted that The larger the value, the In the data sequence The greater the possibility that the elevation data is disturbed by external factors or affected by unqualified road quality, the greater the possibility that the In the data sequence The smaller the possibility that the elevation data is normal elevation data; The larger the value, the In the data sequence The greater the possibility that the elevation data is normal elevation data; It means that when calculating the overall elevation value of the road surface, the weight of normal elevation data is increased and the weight of abnormal elevation data is reduced; The larger the value, the In the data sequence The greater the difference between the elevation value of the first elevation data and the overall elevation value of all data points in the two-dimensional coordinate system, the greater the difference between the first elevation data and the overall elevation value of all data points in the two-dimensional coordinate system. In the data sequence The probability that the elevation data is normal elevation data is smaller.

At this point, the elevation outlier of each elevation data in each data sequence is obtained.

Step S003: According to the distribution of elevation outliers of elevation data in each data sequence, each data sequence is divided into several fluctuation intervals; according to the value of elevation data in each fluctuation interval and the difference between the elevation outliers of adjacent elevation data, the fluctuation kurtosis parameter of each elevation data in each fluctuation interval is obtained; according to the fluctuation kurtosis parameters and their distribution of all elevation data in each fluctuation interval, the elevation fluctuation interference degree of each elevation data is obtained.

It should be noted that, through the above analysis and calculation, the elevation outlier of normal elevation data is significantly different from that of elevation data disturbed by external factors or affected by unqualified road surface. Therefore, all elevation data are further analyzed to distinguish the elevation data affected by external interference factors from the elevation data with unqualified road surface quality.

It should be further explained that when the vehicle shakes due to external interference factors, the vehicle is still driving on a stable road, so that the vehicle body gradually recovers its balance during the shaking process, that is, the elevation data generated during the shaking process caused by external interference factors recovers to normal elevation data after a long time, and the elevation data recovers to normal elevation data after multiple ups and downs with gradually decreasing amplitudes during the recovery process. For the compacted roadbed and pavement, there are no serious potholes and other diseases on the pavement, and general flatness defects usually do not cause the vehicle body to shake continuously, which makes the recovery process of elevation data disturbed by external factors and the recovery process of elevation data affected by pavement quality have great differences. Therefore, each sequence is divided into several fluctuation intervals, and the elevation fluctuation interference degree of each elevation data is obtained according to the changes in the elevation data in each fluctuation interval, that is, the possibility that each elevation data is abnormal data.

It should be further explained that the elevation outlier of the elevation data caused by interference from external factors or unqualified road surface is greater than the elevation outlier of the normal elevation data. Therefore, whether each elevation data is the suspected interval starting point of the fluctuation sequence is determined according to whether the elevation outlier of each elevation data in each data sequence is greater than the elevation outlier of the adjacent elevation data on its left. The elevation data disturbed by external factors is restored to normal elevation data after multiple up and down fluctuations with gradually decreasing fluctuation amplitudes; that is, in the process of restoring an elevation data disturbed by external factors, there may be multiple elevation outliers of elevation data greater than the elevation outliers of the adjacent elevation data on its left, that is, in the process of restoring an elevation data disturbed by external factors, there may be multiple suspected interval starting points, so some non-interval periods are screened out from the suspected interval starting points. Since the elevation value of the elevation data disturbed by external factors is greater than the elevation value of the elevation data in the process of restoring the elevation data disturbed by external factors, the elevation outlier of the elevation data disturbed by external factors is greater than the outlier of the elevation data in the process of restoring the elevation data disturbed by external factors. Therefore, the suspected interval starting points in each fluctuation interval are preliminarily screened out according to whether the elevation outlier of each suspected interval starting point is greater than the elevation outlier of the suspected interval starting point on its left.

It should be further explained that, when the road surface to be tested is tested, it may contain pebbles and leaves, etc., so that the elevation data affected by pebbles and leaves may be the suspected interval starting point, so the suspected interval starting point is screened out for the second time. Since the elevation value of the elevation data affected by pebbles and leaves is much smaller than the elevation value of the elevation data disturbed by external factors, the elevation outlier of the elevation data affected by pebbles and leaves is much smaller than the elevation outlier of the elevation data disturbed by external factors, so according to the elevation outlier of each suspected interval starting point, the suspected interval starting point in each fluctuation interval is screened out for the second time, and the final interval starting point in each data sequence is obtained, and each data sequence is divided into several fluctuation intervals.

Specifically, in In a data sequence, if the The elevation outlier of the first elevation data is greater than that of the The elevation outlier of the elevation data is The first The elevation data is recorded as The suspected interval starting point in the data sequence. The suspected interval starting point whose elevation outlier degree in the data sequence is less than or equal to the elevation outlier degree of the previous suspected region starting point is recorded as the non-suspected interval starting point. In the data sequence, The elevation outlier of the starting point of the suspected interval is greater than The height outlier of the starting point of the interval, The elevation outlier of the starting point of the suspected interval is less than The height outlier of the starting point of the suspected interval, The elevation outlier of the starting point of the suspected interval is less than The height outlier of the starting point of the suspected interval; The first The starting point of the suspected interval The starting point of the suspected interval is The starting point of a non-suspected interval in the data sequence. Remove the non-suspected interval starting points from the suspected interval starting points in the data sequence, and record the other suspected interval starting points as The possible starting point of the interval within the data sequence.

Furthermore, according to The height outlier of the possible interval starting point in the data sequence is The possible interval starting points in the data sequence are arranged in ascending order to obtain the The possible interval sequence of data sequences. Calculate the The possible interval sequence of a data sequence The absolute value of the difference in elevation outlier between the starting point of the first possible interval and the starting point of the next interval is recorded as The possible interval sequence of a data sequence difference. The minimum value of the height outlier of the two possible interval starting points corresponding to the maximum difference in the possible interval sequence of the data sequence is recorded as The starting point threshold of the data sequence. The height outlier degree in the data series is greater than The possible interval starting point of the starting point threshold of the data sequence, The first and last elevation data in a data sequence are recorded as The final interval starting point in the data sequence. The first The starting point of the final interval is The elevation data within the starting point of the final interval and the The final interval starting point is The first The elements within the fluctuation range. The data series is divided into several fluctuation intervals.

At this point, each data series is divided into several fluctuation intervals.

It should be further explained that the elevation data caused by the shaking of the vehicle due to external interference factors takes a long time to recover to normal elevation data, and during the recovery process, the elevation data recovers to normal elevation data after multiple up and down fluctuations with gradually decreasing fluctuation amplitudes. That is, within the fluctuation interval where the elevation data affected by external interference factors are located, the difference in elevation outlier between each elevation data affected by external interference factors and the elevation data around it affected by external interference factors is small; and the value of the elevation data of the vehicle affected by external interference factors during the recovery process fluctuates around the interval mean. Therefore, according to the value and elevation outlier of each elevation data in each fluctuation interval and the elevation data on its right side, the fluctuation kurtosis parameter of each elevation data in each fluctuation interval is calculated.

It should be further explained that when the vehicle is disturbed by external factors, the vehicle body continues to shake and the amplitude of the shaking gradually decreases, while when the vehicle is affected by unqualified road quality, the vehicle continues to shake. This makes the fluctuation kurtosis parameter of each elevation data in the fluctuation interval where the elevation data disturbed by external factors is located smaller and the difference in the fluctuation kurtosis parameters of the elevation data is smaller. Therefore, according to the fluctuation kurtosis parameter of each elevation data in each fluctuation interval, the elevation fluctuation interference degree of each fluctuation interval is calculated, and then the elevation fluctuation interference degree of each elevation data is obtained.

Furthermore, any fluctuation interval in any data sequence is recorded as the target fluctuation interval, and the specific calculation formula for obtaining the fluctuation kurtosis parameter of each elevation data in the target fluctuation interval is as follows:

In the formula, Indicates the target fluctuation range. The fluctuation kurtosis parameter of the elevation data, Indicates the target fluctuation range. The value of the elevation data, Indicates the target fluctuation range. The value of the elevation data, Represents the mean of all elevation data within the target fluctuation range. Indicates the target fluctuation range. The elevation outlier of the elevation data, Indicates the target fluctuation range. The elevation outlier of the elevation data, represents the absolute value function, Represents the first adjustment factor, used to prevent , this embodiment makes 1, and can be set to other values in other implementations.

It should be noted that The smaller the value is, the closer the target fluctuation range is. The more the elevation data of the vehicle affected by external interference factors fluctuates around the mean value of the interval during the recovery process, the more consistent the elevation data is with the characteristics of the vehicle affected by external interference factors during the recovery process, that is, the first The greater the possibility that the elevation data is affected by external interference factors; The smaller the value is, the closer the target fluctuation range is. The more the elevation data is in line with the characteristics of the smaller difference in elevation outlier between the elevation data affected by external interference factors and the elevation data around it affected by external interference factors, that is, the first elevation data within the target fluctuation range is The greater the possibility that the elevation data is affected by external interference factors.

Furthermore, the specific calculation formula for obtaining the elevation fluctuation interference degree of the target fluctuation range is as follows:

In the formula, Indicates the elevation fluctuation interference degree of the target fluctuation range, Indicates the number of elevation data contained in the target fluctuation range. Indicates the target fluctuation range. The fluctuation kurtosis parameter of the elevation data, It represents the mean value of the fluctuation kurtosis parameter of all elevation data within the target fluctuation range. is an exponential function with a natural constant as the base. Model to present inverse proportional relationship and normalization, As the input of the model, the implementer can set the inverse proportional function and normalization function according to the actual situation.

It should be noted that The smaller the value is, the more the elevation data in the target fluctuation range conforms to the characteristics that the fluctuation kurtosis parameter of each elevation data in the fluctuation range where the elevation data is disturbed by external factors is small and the difference in the fluctuation kurtosis parameters of the elevation data is small, that is, the elevation data in the target fluctuation range is more likely to be affected by external interference factors.

Furthermore, the elevation fluctuation interference degree of the target fluctuation interval is recorded as the elevation fluctuation interference degree of each elevation data within the target fluctuation interval.

At this point, the elevation fluctuation interference degree of all elevation data is obtained.

Step S004: According to the value of each elevation data, the elevation fluctuation interference, the elevation outlier and the coordinates of the corresponding data points, the abnormal distance between each elevation data and other elevation data is obtained, and then the abnormal local factor of each elevation data is obtained; according to the local abnormal factor of each elevation data, the abnormal data is obtained, and the road surface to be detected is detected.

Specifically, the The data point corresponding to the elevation data is The square of the Euclidean distance between the data points corresponding to the first elevation data is recorded as The elevation data and The first distance of each elevation data, and the calculation formula for calculating the abnormal distance between each elevation data and other elevation data:

In the formula, Indicates The elevation data and The abnormal distance of the elevation data, Indicates The elevation data and The mean of the elevation outliers of the elevation data, Indicates The elevation fluctuation interference of the elevation data is Indicates The elevation fluctuation interference of the elevation data is Indicates The elevation data and The first distance of the elevation data, Indicates The value of the elevation data, Indicates The value of the elevation data.

It should be noted that since the elevation data disturbed by external factors and the elevation data affected by unqualified road quality have a large difference in elevation fluctuation interference, and the elevation data disturbed by external factors and the elevation data affected by unqualified road quality have a large elevation outlier, As The weight of amplifies the difference in fluctuation interference characteristics between the elevation data disturbed by external factors and the elevation data affected by unqualified road quality; since the elevation outlier of normal elevation data is small, As The weight of the elevation data is used to amplify the difference between the elevation data disturbed by external factors and the normal elevation data.

Furthermore, based on the abnormal distance between the elevation data, the local abnormal factors of all elevation data in the two-dimensional coordinate system are calculated by the LOF algorithm. The parameter k of the LOF algorithm is set to 3. , Indicates the number of data points contained in each row in the two-dimensional coordinate system.

At this point, the local anomaly factor of each elevation data is obtained.

Furthermore, the abnormal factor threshold is preset , the local anomaly factor is greater than the anomaly factor threshold The elevation data of is recorded as the disturbed elevation data. The abnormal factor threshold value preset in this embodiment is , which is described by taking this as an example, and other implementations may be set to other values. The disturbed elevation data is the elevation data disturbed by external factors.

Furthermore, after removing the abnormal elevation data in each sequence, the interpolation method is used to complete the data again. According to the completed data, the international roughness index of the road surface to be detected is calculated, and the compaction intelligent detection of the road surface to be detected is realized according to the international roughness index of the road surface to be detected. Among them, the difference method, the calculation of the international roughness index of a road surface according to the elevation data of the road surface, and the realization of the compaction detection of the road surface to be detected according to the international roughness index of the road surface to be detected are all existing well-known technologies, and will not be repeated in this embodiment.

At this point, this embodiment is completed.

The present invention also provides an intelligent monitoring device for roadbed compaction quality, which includes: a data acquisition module, a data analysis module and a pavement detection module; wherein the data acquisition module and the data analysis module obtain abnormal pavement elevation data by calling a computer program to implement the steps of an intelligent monitoring method for roadbed compaction quality, and the pavement detection module obtains the international flatness index of the road surface to be detected based on other elevation data after removing the abnormal pavement elevation data.

Another embodiment of the present invention provides an intelligent monitoring system for roadbed compaction quality, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the above method steps S001 to S004 are implemented.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A method for intelligent monitoring of roadbed compaction quality, characterized in that the method comprises the following steps: Acquire the elevation data of each acquisition position on the road surface to be detected, construct a two-dimensional coordinate system, obtain the elevation data of each data point in the two-dimensional coordinate system, and then obtain a plurality of data sequences; each data point in the two-dimensional coordinate system corresponds to a acquisition position on the road surface to be detected; According to the numerical difference between each elevation data and the adjacent elevation data in each data sequence, the road surface smoothness index of each elevation data in each data sequence is obtained; according to the numerical values of all elevation data in each data sequence and the road surface smoothness index, the elevation outlier of each elevation data is obtained; According to the distribution of the elevation outliers of the elevation data in each data sequence, each data sequence is divided into several fluctuation intervals; according to the values of the elevation data in each fluctuation interval and the difference between the elevation outliers of the adjacent elevation data, the fluctuation kurtosis parameter of each elevation data in each fluctuation interval is obtained; according to the fluctuation kurtosis parameters and their distribution of all the elevation data in each fluctuation interval, the elevation fluctuation interference of each elevation data is obtained; According to the value of each elevation data, the elevation fluctuation interference, the elevation outlier and the coordinates of the corresponding data points, the abnormal distance between each elevation data and other elevation data is obtained, and then the abnormal local factor of each elevation data is obtained; according to the local abnormal factor of each elevation data, the abnormal data is obtained, and the road surface to be inspected is inspected. 2. A method for intelligent monitoring of roadbed compaction quality according to claim 1, characterized in that the obtaining of a plurality of data sequences comprises the following specific methods: In the two-dimensional coordinate system The elevation data corresponding to all data points in the column is used as the Elements in a data sequence; According to the vertical coordinate of the data point corresponding to the elevation data, Arrange the elevation data in the data sequence in ascending order and get the A data sequence. 3. The intelligent monitoring method for roadbed compaction quality according to claim 1 is characterized in that the road surface smoothness index of each elevation data in each data sequence is obtained according to the numerical difference between each elevation data in each data sequence and the adjacent elevation data, including the specific method of: The first In the data sequence The elevation data minus the The difference of the elevation data is taken as the In the data sequence The left slope of the elevation data; Get the In the data sequence The specific calculation formula for the road surface smoothness index of elevation data is as follows: In the formula, Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The left slope of the elevation data, Indicates In the data sequence The left slope of the elevation data, represents the absolute value function, is an exponential function with a natural constant as its base. 4. The intelligent monitoring method for roadbed compaction quality according to claim 1 is characterized in that the elevation outlier of each elevation data is obtained according to the values of all elevation data in each data sequence and the road surface flatness index, including the specific method of: In the formula, Indicates In the data sequence The elevation outlier of the elevation data, Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The value of the elevation data, Represents the number of data points contained in each row in the two-dimensional coordinate system. Represents the number of data points contained in each column in the two-dimensional coordinate system. Indicates In the data sequence The road surface smoothness index of the elevation data, Indicates In the data sequence The value of the elevation data, represents the absolute value function, Represents the softmax normalization function. 5. The method for intelligent monitoring of roadbed compaction quality according to claim 1 is characterized in that each data sequence is divided into a number of fluctuation intervals according to the distribution of elevation outliers of elevation data in each data sequence, including the following specific methods: In the In a data sequence, if the The elevation outlier of the first elevation data is greater than that of the The elevation outlier of the elevation data is The first The elevation data is recorded as The suspected interval starting point in the data sequence; The first The suspected interval starting point whose elevation outlier degree in a data sequence is less than or equal to the elevation outlier degree of the previous suspected region starting point is recorded as the non-suspected interval starting point; From Remove the non-suspected interval starting points from the suspected interval starting points in the data sequence, and record the other suspected interval starting points as Possible interval starting points within a data sequence; According to The height outlier of the possible interval starting point in the data sequence is The possible interval starting points in the data sequence are arranged in ascending order to obtain the The possible interval sequence of a data sequence; Calculate the The possible interval sequence of a data sequence The absolute value of the difference in elevation outlier between the starting point of the first possible interval and the starting point of the next interval is recorded as The possible interval sequence of a data sequence differences; The first The minimum value of the height outlier of the two possible interval starting points corresponding to the maximum difference in the possible interval sequence of the data sequence is recorded as The starting point threshold of a data sequence; The first The height outlier degree in the data series is greater than The possible interval starting point of the starting point threshold of the data sequence, The first and last elevation data in a data sequence are recorded as The final interval starting point in the data sequence; The first The starting point of the final interval is The elevation data within the starting point of the final interval and the The final interval starting point is The first elements within the fluctuation range; The data series is divided into several fluctuation intervals. 6. A method for intelligent monitoring of roadbed compaction quality according to claim 1, characterized in that the fluctuation kurtosis parameter of each elevation data in each fluctuation interval is obtained according to the value of the elevation data in each fluctuation interval and the difference between the elevation outliers of adjacent elevation data, including the specific method of: Any fluctuation interval in any data sequence is recorded as the target fluctuation interval, and the specific calculation formula for obtaining the fluctuation kurtosis parameter of each elevation data in the target fluctuation interval is as follows: In the formula, Indicates the target fluctuation range. The fluctuation kurtosis parameter of the elevation data, Indicates the target fluctuation range. The value of the elevation data, Indicates the target fluctuation range. The value of the elevation data, Represents the mean of all elevation data within the target fluctuation range. Indicates the target fluctuation range. The elevation outlier of the elevation data, Indicates the target fluctuation range. The elevation outlier of the elevation data, represents the absolute value function, Represents the first adjustment coefficient. 7. A roadbed compaction quality intelligent monitoring method according to claim 6, characterized in that the elevation fluctuation interference degree of each elevation data is obtained according to the fluctuation kurtosis parameter and its distribution of all elevation data in each fluctuation interval, including the specific method of: In the formula, Indicates the elevation fluctuation interference degree of the target fluctuation range, Indicates the number of elevation data contained in the target fluctuation range. Indicates the target fluctuation range. The fluctuation kurtosis parameter of the elevation data, It represents the mean value of the fluctuation kurtosis parameter of all elevation data within the target fluctuation range. is an exponential function with a natural constant as base; The elevation fluctuation interference degree of the target fluctuation interval is recorded as the elevation fluctuation interference degree of each elevation data within the target fluctuation interval. 8. The intelligent monitoring method for roadbed compaction quality according to claim 1 is characterized in that the abnormal distance between each elevation data and other elevation data is obtained according to the value of each elevation data, the elevation fluctuation interference degree, the elevation outlier degree and the coordinates of the corresponding data point, including the specific method of: The first The data point corresponding to the elevation data is The square of the Euclidean distance between the data points corresponding to the first elevation data is recorded as The elevation data and The first distance of the elevation data; The calculation formula for calculating the abnormal distance between each elevation data and other elevation data is as follows: In the formula, Indicates The elevation data and The abnormal distance of the elevation data, Indicates The elevation data and The mean of the elevation outliers of the elevation data, Indicates The elevation fluctuation interference of the elevation data is Indicates The elevation fluctuation interference of elevation data, Indicates The elevation data and The first distance of the elevation data, Indicates The value of the elevation data, Indicates The value of the elevation data. 9. An intelligent monitoring device for roadbed compaction quality, characterized in that the device comprises: A data acquisition module, a data analysis module and a pavement detection module; wherein the data acquisition module and the data analysis module obtain abnormal pavement elevation data by calling a computer program to implement the steps of a roadbed compaction quality intelligent monitoring method as described in any one of claims 1 to 8, and the pavement detection module obtains the international roughness index of the pavement to be detected based on other elevation data after removing the abnormal pavement elevation data. 10. A roadbed compaction quality intelligent monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that when the processor executes the computer program, the steps of a roadbed compaction quality intelligent monitoring method as described in any one of claims 1-8 are implemented.