CN117726324B - Road traffic construction inspection method and system based on data identification - Google Patents
Road traffic construction inspection method and system based on data identification Download PDFInfo
- Publication number
- CN117726324B CN117726324B CN202410172923.9A CN202410172923A CN117726324B CN 117726324 B CN117726324 B CN 117726324B CN 202410172923 A CN202410172923 A CN 202410172923A CN 117726324 B CN117726324 B CN 117726324B
- Authority
- CN
- China
- Prior art keywords
- maintenance
- data
- time
- road
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000010276 construction Methods 0.000 title claims abstract description 38
- 238000007689 inspection Methods 0.000 title claims abstract description 28
- 238000012423 maintenance Methods 0.000 claims description 306
- 238000001556 precipitation Methods 0.000 claims description 54
- 238000013528 artificial neural network Methods 0.000 claims description 48
- 238000004364 calculation method Methods 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 31
- 230000008859 change Effects 0.000 claims description 21
- 210000002569 neuron Anatomy 0.000 claims description 21
- 238000002360 preparation method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 5
- 230000006378 damage Effects 0.000 description 22
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a highway traffic construction inspection method and system based on data identification, which belong to the field of data processing systems specially used for management.
Description
Technical Field
The invention belongs to the field of data processing systems specially used for management, and particularly relates to a highway traffic construction inspection method and system based on data identification.
Background
With the large-scale development of national capital construction, the number of roads and traffic volume are greatly increased, the driving density and the vehicle load are larger and larger, the safety performance of the roads is more and more important to people, corresponding construction inspection is carried out on road traffic, the prior art cannot carry out data analysis on the damage condition of the roads when carrying out road maintenance early warning, and further cannot accurately estimate the time of the roads needing to be maintained, so that the time difference exists between the road maintenance and the road damage, the synchronization of the road maintenance and the road damage cannot be realized, and the problems exist in the prior art;
For example, in chinese patent application publication No. CN112836572a, a highway traffic construction inspection method and system are disclosed, where the entire inspection system identifies road surface information to automatically obtain construction position, predicts the construction position to predict the construction information, and performs gradient processing through multitask learning to calibrate the prediction result; therefore, for huge workload in the road construction inspection process, a large amount of manpower and material resources are saved, and the required construction information can be obtained after the data acquired by the cameras at all positions are acquired, identified, processed, predicted and learned;
The problems proposed in the background art exist in the above patents: in the prior art, when road maintenance early warning is carried out, data analysis cannot be carried out on the damage condition of a road, further accurate prediction cannot be carried out on the time of the road to be maintained, so that the time difference exists between the road maintenance and the road damage, and the synchronization of the road maintenance and the road damage cannot be realized.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a road traffic construction inspection method and system based on data identification, road data, vehicle transportation data, temperature data and precipitation data in a road transportation process are acquired in real time through a road data acquisition module, a time threshold is set according to maintenance preparation time, a maintenance value of a real-time road is calculated in a road maintenance value calculation model constructed based on road data input in the road transportation process, a maintenance value, vehicle transportation data, temperature data and precipitation data input in a set time period are constructed based on maintenance value change quantity, vehicle transportation data, temperature data and precipitation data in a historical time period, a neural network prediction model of the maintenance value change quantity in the historical time period is output, the maintenance value, predicted vehicle transportation data, predicted temperature data and predicted precipitation data in the future time period are acquired, the acquired maintenance value change quantity after the set time period is input into the neural network model, the acquired maintenance value change quantity is added with the maintenance value of the real-time road, the time maintenance value reaches the set maintenance threshold is estimated, the time is set as the maintenance time, the acquired maintenance value is compared with the estimated time, the time is less than the estimated time, the road is damaged when the road maintenance time is damaged, and the road is accurately compared with the road maintenance time threshold is damaged when the road maintenance time is not estimated, and the road damage is reduced.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a highway traffic construction inspection method based on data identification comprises the following specific steps:
S1, road data, vehicle transportation data, temperature data and precipitation data in the road transportation process are obtained in real time through a road data acquisition module, and a time threshold is set according to maintenance preparation time;
S2, calculating a maintenance value of a real-time road in a road maintenance value calculation model constructed based on road data input in the road transportation process;
S3, constructing a neural network prediction model which is input as the maintenance value, the vehicle transportation data, the temperature data and the precipitation data of the set time period based on the maintenance value variation of the historical set time period, and outputting the neural network prediction model as the maintenance value variation of the historical set time period;
S4, acquiring a maintenance value, predicted vehicle transportation data, predicted temperature data and predicted precipitation data of a future set time period, importing the maintenance value variation after the set time period into a constructed neural network model, adding the acquired maintenance value variation and a maintenance value of a real-time road to obtain a future time maintenance value, and predicting the time when the future time maintenance value reaches a set maintenance threshold value to be set as maintenance time;
S5, comparing the obtained maintenance time with a time threshold, and carrying out road maintenance alarm when the maintenance time is smaller than or equal to the time threshold and not carrying out road maintenance alarm when the maintenance time is larger than the time threshold.
Specifically, the step S1 includes the following specific steps:
s11, acquiring road image data through a road data acquisition module, importing the road image data into image processing software to output pixel value data of each pixel point of a road image, acquiring vehicle weight data of road running through a vehicle transportation acquisition module, and storing the vehicle weight data in a first storage module;
S12, acquiring environmental temperature data and precipitation data of a road in the road transportation process through a weather data acquisition module, and storing the environmental temperature data and precipitation data in a second storage module;
S13, acquiring the preparation time of the historical maintenance process, and setting the average value of the preparation time in the historical maintenance process as a time threshold.
Specifically, the S2 includes the following specific contents:
S21, acquiring pixel value data of each pixel point of the obtained real-time road image, and simultaneously extracting the pixel value data of each pixel point of the road image of the normal road surface;
s22, substituting the extracted pixel value data of each pixel point of the real-time road image and the pixel value data of each pixel point of the road image of the normal road surface into a maintenance value calculation formula to calculate the maintenance value of the road, wherein the maintenance value calculation formula of the road is as follows:
Where n is the number of pixels in the road image,/> Pixel value of ith pixel point of real-time road image,/>For judging the pixel value of the ith pixel point corresponding to the road image of the normal road surface,/>The distance between the ith pixel point of the real-time road image and the road center line is the distance between the ith pixel point of the real-time road image and the road center line;
specifically, the step S3 includes the following specific steps:
S31, acquiring maintenance value variation, vehicle transportation data, temperature data and precipitation data in a set historical time period, constructing a neural network prediction model which is input as the maintenance value, the vehicle transportation data, the temperature data and the precipitation data in the set time period and outputting the maintenance value variation in the set time period, wherein the vehicle transportation data is vehicle transportation tonnage data;
S32, dividing the extracted maintenance value variation, vehicle transportation data, temperature data and precipitation data in the historical set time period into a 70% parameter training set and a 30% parameter test set; inputting 70% of parameter training sets into a neural network prediction model for training to obtain an initial neural network prediction model; testing the initial neural network prediction model by using 30% of parameter test sets, and outputting the initial neural network prediction model meeting the highest maintenance value variation accuracy as a neural network prediction model, wherein an output strategy formula in the neural network prediction model is as follows: wherein/> Output of p-term neuron for z+1 layer,/>For the connection weight of the z-layer neuron j and the z+1-layer p term neuron,/>Representing the input of layer z neuron j,/>Bias representing the linear relationship of layer z neuron j to layer z+1 p neurons,/>, andRepresenting a Sigmoid activation function, m is the number of z-layer neurons.
Specifically, the step S4 includes the following specific steps:
s41, acquiring an average value of vehicle transportation tonnage data in a previous set time period, setting the average value as predicted vehicle transportation data, and acquiring maintenance values, predicted vehicle transportation data, predicted temperature data and predicted precipitation data at the starting moment of a future set time period, wherein the predicted temperature data and the predicted precipitation data in the future set time period are acquired through weather forecast;
s42, importing the acquired maintenance value, the predicted vehicle transportation data, the predicted temperature data and the predicted precipitation data at the starting time of the future set time period into a constructed neural network prediction model to output the maintenance value variation after the future set time period, and adding the output maintenance value variation after the future set time period and the maintenance value of the real-time road to obtain a future time maintenance value;
s43, substituting the maintenance value variation, the real-time road maintenance value and the set maintenance threshold value into a maintenance time calculation formula to calculate the maintenance time, wherein the maintenance time calculation formula is as follows: the minimum value of T meeting the maintenance time calculation formula is obtained to be the maintenance time, wherein X is the maintenance value of the real-time road, T is time,/> For the change in maintenance value after t future set time periods, dt is the time integral,/>For the set maintenance threshold, the maintenance threshold is obtained by finding out the road to be maintained from 5000 sets of historical road data by 100 experts, obtaining the maintenance value of the road to be maintained, and then averaging the maintenance values of the road to be maintained.
Specifically, the specific steps of S5 are as follows:
s51, extracting the calculated maintenance time, and comparing the obtained maintenance time with a time threshold;
and S52, carrying out road maintenance alarm when the maintenance time is less than or equal to the time threshold value, and not carrying out road maintenance alarm when the maintenance time is greater than the time threshold value.
The road traffic construction inspection system based on data identification is realized based on the road traffic construction inspection method based on data identification, and comprises a data acquisition module, a road maintenance value calculation module, a neural network prediction model construction module, a maintenance time calculation module, a time comparison module, a maintenance alarm module and a control module, wherein the data acquisition module is used for acquiring road data, vehicle transportation data, temperature data and precipitation data of a road transportation process in real time through the road data acquisition module, setting a time threshold according to maintenance preparation time, the road maintenance value calculation module is used for calculating a maintenance value of a real-time road in a road maintenance value calculation model constructed based on road data input of the road transportation process, and the neural network prediction model construction module is used for constructing a neural network prediction model which is input as a maintenance value, vehicle transportation data, temperature data and precipitation data of a set time period based on the maintenance value change amount of the historical set time period and outputting the maintenance value change amount of the historical set time period.
Specifically, the maintenance time calculation module is used for obtaining maintenance values, predicted vehicle transportation data, predicted temperature data and predicted precipitation data of a future set time period, importing the maintenance value variation after the set time period into a constructed neural network model, adding the obtained maintenance value variation and the maintenance value of a real-time road to obtain a future time maintenance value, predicting the time when the future time maintenance value reaches a set maintenance threshold value, setting the time as maintenance time, the time comparison module is used for comparing the obtained maintenance time with a time threshold value, and the maintenance alarm module is used for carrying out road maintenance alarm when the maintenance time is smaller than or equal to the time threshold value.
Specifically, the control module is used for controlling the operation of the data acquisition module, the road maintenance value calculation module, the neural network prediction model construction module, the maintenance time calculation module, the time comparison module and the maintenance alarm module.
An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
The processor executes the highway traffic construction inspection method based on data identification by calling the computer program stored in the memory.
A computer readable storage medium storing instructions that when executed on a computer cause the computer to perform a method of highway traffic inspection based on data identification as described above.
Compared with the prior art, the invention has the beneficial effects that:
The road data acquisition module acquires road data, vehicle transportation data, temperature data and precipitation data in real time in a road maintenance value calculation model constructed based on road data input in the road transportation process, calculates a real-time road maintenance value in the road maintenance value calculation model according to maintenance preparation time set time thresholds, constructs a maintenance value, vehicle transportation data, temperature data and precipitation data input in the set time periods based on maintenance value change amounts in the historical set time periods, vehicle temperature data and precipitation data, outputs a neural network prediction model for the maintenance value change amounts in the historical set time periods, acquires the maintenance value in the future set time periods, predicts the vehicle transportation data, predicts the temperature data and predicts the precipitation data, acquires the maintenance value change amounts after the set time periods in the neural network model constructed, adds the acquired maintenance value change amounts and the maintenance value of the real-time road to obtain a future time maintenance value, predicts the time when the future time maintenance value reaches the set maintenance threshold, sets the obtained maintenance time and time threshold as the maintenance time, carries out maintenance alarm when the maintenance time is smaller than or equal to the time threshold, carries out maintenance alarm when the maintenance time is not longer than the maintenance time threshold, carries out the road damage alarm condition on the road and the road damage condition when the road maintenance time is not longer than the maintenance threshold, and the road damage condition is accurately analyzed, and the road damage is reduced.
Drawings
FIG. 1 is a schematic flow chart of a highway traffic construction inspection method based on data identification;
Fig. 2 is a schematic diagram of an overall framework of a highway traffic construction inspection system based on data identification.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1, an embodiment of the present invention is provided: a highway traffic construction inspection method based on data identification comprises the following specific steps:
S1, road data, vehicle transportation data, temperature data and precipitation data in the road transportation process are obtained in real time through a road data acquisition module, and a time threshold is set according to maintenance preparation time;
S2, calculating a maintenance value of a real-time road in a road maintenance value calculation model constructed based on road data input in the road transportation process;
S3, constructing a neural network prediction model which is input as the maintenance value, the vehicle transportation data, the temperature data and the precipitation data of the set time period based on the maintenance value variation of the historical set time period, and outputting the neural network prediction model as the maintenance value variation of the historical set time period;
S4, acquiring a maintenance value, predicted vehicle transportation data, predicted temperature data and predicted precipitation data of a future set time period, importing the maintenance value variation after the set time period into a constructed neural network model, adding the acquired maintenance value variation and a maintenance value of a real-time road to obtain a future time maintenance value, and predicting the time when the future time maintenance value reaches a set maintenance threshold value to be set as maintenance time;
S5, comparing the obtained maintenance time with a time threshold, and carrying out road maintenance alarm when the maintenance time is less than or equal to the time threshold and not carrying out road maintenance alarm when the maintenance time is greater than the time threshold;
it should be noted that, S1 includes the following specific steps:
s11, acquiring road image data through a road data acquisition module, importing the road image data into image processing software to output pixel value data of each pixel point of a road image, acquiring vehicle weight data of road running through a vehicle transportation acquisition module, and storing the vehicle weight data in a first storage module;
The following is a simple C language program framework for implementing step S11:
#include<stdio.h>
#include<opencv2/opencv.hpp>
Defining a structure for storing pixel values and vehicle weight data
typedef struct {
int pixel_value;
float vehicle_weight;
} PixelData;
int main() {
And (1) collecting road image data through a road data collecting module
Cv:: mat road_image = cv:: imread ("road_image. Jpg");// assume we read the road image from the file
if (road_image.empty()) {
Printf ("unable to load image \n");
return -1;
}
Input road image data into image processing software to output pixel value data of each pixel point of road image
int width = roadimage.cols;
int height = road_image.rows;
PixelData *pixel_data = (PixelData *)malloc(width * height * sizeof(PixelData));
for (int y = 0; y<height; y++) {
for (int x = 0; x<width; x++) {
cv::Vec3b pixel = road_image.atcv::Vec3by, x);
Let us assume that we only care about the blue value of a pixel
pixel_data[y * width + x].pixel_value = pixel[0];
}
}
And/3, collecting vehicle weight data of road running through a vehicle transportation collection module
However, that// is merely exemplary, and that vehicle weight data may be obtained by other means as may be required in practice
for (int i = 0; i<width * height; i++) {
Pixel_data [ i ]. Vehicle_weight= (float) RAND ()/rand_max 1000.0;// randomizing a vehicle weight value
}
Is/4 stored in the first storage module
FILE *file = fopen("pixel_data.bin", "wb");
if (!file) {
Printf ("unable to open file\n");
return -1;
}
write(pixel_data, sizeof(PixelData), width * height, file);
fclose(file);
free(pixel_data);
return 0;
}
S12, acquiring environmental temperature data and precipitation data of a road in the road transportation process through a weather data acquisition module, and storing the environmental temperature data and precipitation data in a second storage module;
S13, acquiring preparation time of a historical maintenance process, and setting an average value of the preparation time in the historical maintenance process as a time threshold;
Road damage refers to damage or destruction of a road during use due to various reasons, and the following are some common road damage factors:
1. Traffic load: the passage of a vehicle can create a load on the road. Excessive heavy vehicles or frequent traffic can exacerbate road damage. Heavy trucks and large vehicles are more damaging to the road;
2. weather factors: the weather conditions have a great influence on the abrasion of the road; for example, rain water can penetrate into the road surface to cause the road surface to become slippery, accumulated water or frozen water can cause the road surface to become uneven, and high temperature can also cause the road surface to expand and deform;
the above is only some common road damage factors, and in fact other factors may have an influence on the service life and quality of the road, so periodic inspection, maintenance and appropriate repair work are very important to keep the road safe and reliable;
here, S2 includes the following specific contents:
S21, acquiring pixel value data of each pixel point of the obtained real-time road image, and simultaneously extracting the pixel value data of each pixel point of the road image of the normal road surface;
s22, substituting the extracted pixel value data of each pixel point of the real-time road image and the pixel value data of each pixel point of the road image of the normal road surface into a maintenance value calculation formula to calculate the maintenance value of the road, wherein the maintenance value calculation formula of the road is as follows: Where n is the number of pixels in the road image,/> Pixel value of ith pixel point of real-time road image,/>For judging the pixel value of the ith pixel point corresponding to the road image of the normal road surface,/>The distance between the ith pixel point of the real-time road image and the road center line is the distance between the ith pixel point of the real-time road image and the road center line;
it should be noted that, S3 includes the following specific steps:
S31, acquiring maintenance value variation, vehicle transportation data, temperature data and precipitation data in a set historical time period, constructing a neural network prediction model which is input as the maintenance value, the vehicle transportation data, the temperature data and the precipitation data in the set time period and outputting the maintenance value variation in the set time period, wherein the vehicle transportation data is vehicle transportation tonnage data;
S32, dividing the extracted maintenance value variation, vehicle transportation data, temperature data and precipitation data in the historical set time period into a 70% parameter training set and a 30% parameter test set; inputting 70% of parameter training sets into a neural network prediction model for training to obtain an initial neural network prediction model; testing the initial neural network prediction model by using 30% of parameter test sets, and outputting the initial neural network prediction model meeting the highest maintenance value variation accuracy as a neural network prediction model, wherein an output strategy formula in the neural network prediction model is as follows: Wherein/> Output of p-term neuron for z+1 layer,/>For the connection weight of the z-layer neuron j and the z+1-layer p term neuron,/>Representing the input of layer z neuron j,/>Bias representing the linear relationship of layer z neuron j to layer z+1 p neurons,/>, andRepresenting a Sigmoid activation function, wherein m is the number of z-layer neurons, and in the optimal initial neural network prediction model meeting the accuracy of the preset maintenance value variation, the accuracy of the preset maintenance value variation is the proportion of the maintenance value output by the neural network and the actual calculated maintenance value phase difference value to the actual calculated maintenance value, namely the prediction accuracy, and the optimal meaning is the highest, namely the initial neural network prediction model meeting the highest prediction accuracy;
It should be noted that, S4 includes the following specific steps:
s41, acquiring an average value of vehicle transportation tonnage data in a previous set time period, setting the average value as predicted vehicle transportation data, and acquiring maintenance values, predicted vehicle transportation data, predicted temperature data and predicted precipitation data at the starting moment of a future set time period, wherein the predicted temperature data and the predicted precipitation data in the future set time period are acquired through weather forecast;
s42, importing the acquired maintenance value, the predicted vehicle transportation data, the predicted temperature data and the predicted precipitation data at the starting time of the future set time period into a constructed neural network prediction model to output the maintenance value variation after the future set time period, and adding the output maintenance value variation after the future set time period and the maintenance value of the real-time road to obtain a future time maintenance value;
s43, substituting the maintenance value variation, the real-time road maintenance value and the set maintenance threshold value into a maintenance time calculation formula to calculate the maintenance time, wherein the maintenance time calculation formula is as follows: the minimum value of T meeting the maintenance time calculation formula is obtained to be the maintenance time, wherein X is the maintenance value of the real-time road, T is the time, For the change in maintenance value after t future set time periods, dt is the time integral,/>For setting the maintenance threshold, finding out the road to be maintained from 5000 groups of historical road data by 100 experts, solving the maintenance value of the road to be maintained, and then averaging the maintenance value of the road to be maintained to obtain the set maintenance threshold;
the specific steps of S5 are as follows:
s51, extracting the calculated maintenance time, and comparing the obtained maintenance time with a time threshold;
S52, road maintenance alarm is carried out when the maintenance time is less than or equal to the time threshold value, and road maintenance alarm is not carried out when the maintenance time is greater than the time threshold value;
It should be noted that the advantages of this embodiment compared with the prior art are: the road data, the vehicle transportation data, the temperature data and the precipitation data in the road transportation process are obtained in real time through the road data collecting module, the time threshold is set according to maintenance preparation time, the maintenance value of the real-time road is calculated in the road maintenance value calculation model constructed based on the road data input in the road transportation process, the maintenance value, the vehicle transportation data, the temperature data and the precipitation data in the set time are constructed based on the maintenance value change amount in the historical set time, the vehicle transportation data, the temperature data and the precipitation data, the neural network prediction model of the maintenance value change amount in the historical set time is output, the maintenance value, the predicted vehicle transportation data, the predicted temperature data and the predicted precipitation data in the future set time are obtained, the maintenance value change amount after the set time is obtained by introducing the constructed neural network model, the obtained maintenance value change amount and the maintenance value of the real-time road are added to obtain the future time maintenance value, the time when the obtained maintenance value reaches the set maintenance threshold is set as the maintenance time, the obtained maintenance time is compared with the time threshold, the maintenance time is carried out when the maintenance time is smaller than or equal to the time threshold, the maintenance time is carried out, the road damage is not carried out when the maintenance time is larger than the maintenance time threshold, the road damage is accurately estimated, the road damage is reduced, and the road damage is accurately caused, and the road damage is prevented.
Example 2
As shown in fig. 2, a highway traffic construction inspection system based on data identification is implemented based on the above-mentioned highway traffic construction inspection method based on data identification, which includes a data acquisition module, a road maintenance value calculation module, a neural network prediction model construction module, a maintenance time calculation module, a time comparison module, a maintenance alarm module and a control module, wherein the data acquisition module is used for acquiring road data, vehicle transportation data, temperature data and precipitation data of a highway transportation process in real time through the road data acquisition module, setting a time threshold according to maintenance preparation time, the road maintenance value calculation module is used for calculating a maintenance value of a real-time road in a road maintenance value calculation model constructed based on road data input of the highway transportation process, and the neural network prediction model construction module is used for constructing a neural network prediction model input as a maintenance value, vehicle transportation data, temperature data and precipitation data of a set time period based on a maintenance value change amount of a history set time period and outputting the maintenance value change amount of the history set time period; the maintenance time calculation module is used for acquiring maintenance values, predicted vehicle transportation data, predicted temperature data and predicted precipitation data of a future set time period, importing the maintenance value variation after the set time period into a constructed neural network model, adding the acquired maintenance value variation and the maintenance value of a real-time road to obtain a future time maintenance value, predicting the time when the future time maintenance value reaches a set maintenance threshold value, setting the time as maintenance time, and the time comparison module is used for comparing the acquired maintenance time with the time threshold value, and the maintenance alarm module is used for carrying out road maintenance alarm when the maintenance time is smaller than or equal to the time threshold value; the control module is used for controlling the operation of the data acquisition module, the road maintenance value calculation module, the neural network prediction model construction module, the maintenance time calculation module, the time comparison module and the maintenance alarm module.
Example 3
The present embodiment provides an electronic device including: a processor and a memory, wherein the memory stores a computer program for the processor to call;
The processor executes the road traffic construction inspection method based on data identification by calling the computer program stored in the memory.
The electronic device may have a relatively large difference due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, where at least one computer program is stored in the memories, and the computer program is loaded and executed by the processors to implement a highway traffic construction inspection method based on data identification provided by the above method embodiments. The electronic device can also include other components for implementing the functions of the device, for example, the electronic device can also have wired or wireless network interfaces, input-output interfaces, and the like, for inputting and outputting data. The present embodiment is not described herein.
Example 4
The present embodiment proposes a computer-readable storage medium having stored thereon an erasable computer program;
the computer program, when run on the computer device, causes the computer device to perform a highway traffic construction inspection method based on data identification as described above.
For example, the computer readable storage medium can be Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), compact disk Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), magnetic tape, floppy disk, optical data storage device, and the like.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by way of wired or/and wireless networks from one website site, computer, server, or data center to another. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. Usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tape), optical media (e.g., DVD), or semiconductor media. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the partitioning of units is merely one way of partitioning, and there may be additional ways of partitioning in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (4)
1. The highway traffic construction inspection method based on data identification is characterized by comprising the following specific steps of:
S1, road data, vehicle transportation data, temperature data and precipitation data in the road transportation process are obtained in real time through a road data acquisition module, and a time threshold is set according to maintenance preparation time;
S2, calculating a maintenance value of a real-time road in a road maintenance value calculation model constructed based on road data input in the road transportation process;
S3, constructing a neural network prediction model which is input as the maintenance value, the vehicle transportation data, the temperature data and the precipitation data of the set time period based on the maintenance value variation of the historical set time period, and outputting the neural network prediction model as the maintenance value variation of the historical set time period;
S4, acquiring a maintenance value, predicted vehicle transportation data, predicted temperature data and predicted precipitation data of a future set time period, importing the maintenance value variation after the set time period into a constructed neural network model, adding the acquired maintenance value variation and a maintenance value of a real-time road to obtain a future time maintenance value, and predicting the time when the future time maintenance value reaches a set maintenance threshold value to be set as maintenance time;
S5, comparing the obtained maintenance time with a time threshold, and carrying out road maintenance alarm when the maintenance time is less than or equal to the time threshold and not carrying out road maintenance alarm when the maintenance time is greater than the time threshold; the S1 comprises the following specific steps:
s11, acquiring road image data through a road data acquisition module, importing the road image data into image processing software to output pixel value data of each pixel point of a road image, acquiring vehicle weight data of road running through a vehicle transportation acquisition module, and storing the vehicle weight data in a first storage module;
S12, acquiring environmental temperature data and precipitation data of a road in the road transportation process through a weather data acquisition module, and storing the environmental temperature data and precipitation data in a second storage module;
s13, acquiring preparation time of a historical maintenance process, and setting an average value of the preparation time in the historical maintenance process as a time threshold; the S2 comprises the following specific contents:
S21, acquiring pixel value data of each pixel point of the obtained real-time road image, and simultaneously extracting the pixel value data of each pixel point of the road image of the normal road surface;
s22, substituting the extracted pixel value data of each pixel point of the real-time road image and the pixel value data of each pixel point of the road image of the normal road surface into a maintenance value calculation formula to calculate the maintenance value of the road, wherein the maintenance value calculation formula of the road is as follows: Where n is the number of pixels in the road image,/> Pixel value of ith pixel point of real-time road image,/>For judging the pixel value of the ith pixel point corresponding to the road image of the normal road surface,/>The distance between the ith pixel point of the real-time road image and the road center line is the distance between the ith pixel point of the real-time road image and the road center line; the step S3 comprises the following specific steps:
S31, obtaining maintenance value variation, vehicle transportation data, temperature data and precipitation data in a set historical time period, constructing maintenance values, vehicle transportation data, temperature data and precipitation data which are input into the set time period, and outputting a neural network prediction model of the maintenance value variation in the set time period, wherein the vehicle transportation data are vehicle transportation tonnage data;
S32, dividing the extracted maintenance value variation, vehicle transportation data, temperature data and precipitation data in the historical set time period into a 70% parameter training set and a 30% parameter test set; inputting 70% of parameter training sets into a neural network prediction model for training to obtain an initial neural network prediction model; testing the initial neural network prediction model by using 30% of parameter test sets, and outputting the initial neural network prediction model meeting the highest maintenance value variation accuracy as a neural network prediction model, wherein an output strategy formula in the neural network prediction model is as follows: output of p-term neuron for z+1 layer,/> For the connection weight of the z-layer neuron j and the z+1-layer p term neuron,/>Table input of layer z neuron j,/>Bias representing the linear relationship of layer z neuron j to layer z+1 p neurons,/>, andRepresenting a Sigmoid activation function, wherein m is the number of z-layer neurons; the step S4 comprises the following specific steps:
S41, acquiring an average value of vehicle transportation tonnage data in a previous set time period, setting the average value as predicted vehicle transportation data, and acquiring maintenance values, predicted vehicle transportation data, predicted temperature data and predicted precipitation data at the starting moment of a future set time period, wherein the predicted temperature data and the predicted precipitation data in the future set time period are acquired through weather forecast;
s42, importing the acquired maintenance value, the predicted vehicle transportation data, the predicted temperature data and the predicted precipitation data at the starting time of the future set time period into a constructed neural network prediction model to output the maintenance value variation after the future set time period, and adding the output maintenance value variation after the future set time period and the maintenance value of the real-time road to obtain a future time maintenance value;
s43, substituting the maintenance value variation, the real-time road maintenance value and the set maintenance threshold value into a maintenance time calculation formula to calculate the maintenance time, wherein the maintenance time calculation formula is as follows: the minimum value of T meeting the maintenance time calculation formula is obtained to be the maintenance time, wherein X is the maintenance value of the real-time road, T is time,/> For the change in maintenance value after t future set time periods, dt is the time integral,/>Is the set maintenance threshold.
2. A highway traffic construction inspection system based on data identification, which is realized based on the highway traffic construction inspection method based on data identification according to claim 1, and is characterized by comprising a data acquisition module, a road maintenance value calculation module, a neural network prediction model construction module, a maintenance time calculation module, a time comparison module, a maintenance alarm module and a control module, wherein the data acquisition module is used for acquiring road data, vehicle transportation data, temperature data and precipitation data of a highway transportation process in real time through the road data acquisition module, setting a time threshold according to maintenance preparation time, the road maintenance value calculation module is used for calculating a maintenance value of a real-time road in a road maintenance value calculation model constructed based on road data input of the highway transportation process, and the neural network prediction model construction module is used for constructing a neural network prediction model which is input as a maintenance value of a set time period, vehicle transportation data, temperature data and precipitation data based on a maintenance value change of a history set time period and outputting the maintenance value change of the history set time period; the maintenance time calculation module is used for obtaining maintenance values, predicted vehicle transportation data, predicted temperature data and predicted precipitation data of a future set time period, importing the obtained maintenance value variation after the set time period into the constructed neural network model, adding the obtained maintenance value variation and the maintenance value of a real-time road to obtain a future time maintenance value, predicting the time of the future time maintenance value reaching a set maintenance threshold value, setting the time as the maintenance time, the time comparison module is used for comparing the obtained maintenance time with the time threshold value, the maintenance alarm module is used for carrying out road maintenance alarm when the maintenance time is smaller than or equal to the time threshold value, and the control module is used for controlling the operation of the data acquisition module, the road maintenance value calculation module, the neural network prediction model construction module, the maintenance time calculation module, the time comparison module and the maintenance alarm module.
3. An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
The method is characterized in that the processor executes a highway traffic construction inspection method based on data identification as claimed in claim 1 by calling a computer program stored in the memory.
4. A computer readable storage medium having stored thereon instructions which, when executed on a computer, cause the computer to perform a data recognition based highway traffic inspection method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410172923.9A CN117726324B (en) | 2024-02-07 | 2024-02-07 | Road traffic construction inspection method and system based on data identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410172923.9A CN117726324B (en) | 2024-02-07 | 2024-02-07 | Road traffic construction inspection method and system based on data identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117726324A CN117726324A (en) | 2024-03-19 |
| CN117726324B true CN117726324B (en) | 2024-04-30 |
Family
ID=90211004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410172923.9A Active CN117726324B (en) | 2024-02-07 | 2024-02-07 | Road traffic construction inspection method and system based on data identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117726324B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9365217B2 (en) * | 2013-06-03 | 2016-06-14 | Booz Allen Hamilton Inc. | Mobile pothole detection system and method |
| CN109902571A (en) * | 2019-01-23 | 2019-06-18 | 中交信息技术国家工程实验室有限公司 | A kind of maintenance process of highway planting engineering and system based on unmanned plane |
| CN110837933A (en) * | 2019-11-11 | 2020-02-25 | 重庆远通电子技术开发有限公司 | Leakage identification method, device, equipment and storage medium based on neural network |
| CN111553902A (en) * | 2020-04-28 | 2020-08-18 | 周欢 | Highway road surface safety monitoring system based on big data |
| CN112836572A (en) * | 2020-12-20 | 2021-05-25 | 刘星亮 | Highway traffic construction inspection method and system |
| CN112884174A (en) * | 2021-02-05 | 2021-06-01 | 上海市市政工程管理咨询有限公司 | Daily maintenance information management method and system for road |
| CN114444737A (en) * | 2022-02-18 | 2022-05-06 | 招商局重庆交通科研设计院有限公司 | Intelligent pavement maintenance planning method based on transfer learning |
| KR102423218B1 (en) * | 2021-07-16 | 2022-07-20 | 한국건설기술연구원 | System and method for simultaneously detecting road damage and moving obstacles using deep neural network, and a recording medium recording a computer readable program for executing the method. |
| CN114912635A (en) * | 2022-04-28 | 2022-08-16 | 广州铁路职业技术学院（广州铁路机械学校） | Highway maintenance decision-making method and system, storage medium and electronic equipment |
| CN115267143A (en) * | 2022-09-28 | 2022-11-01 | 江苏筑升土木工程科技有限公司 | Road cavity defect detection system and detection method |
| DE102022120968A1 (en) * | 2021-12-14 | 2023-06-15 | GM Global Technology Operations LLC | NETWORKED VEHICLE-BASED DETERMINATION OF ROAD SURFACE QUALITY |
| KR20230100787A (en) * | 2021-12-28 | 2023-07-06 | (주) 경성테크놀러지 | Active road integrated management system using artificial intelligence for road maintenance |
| CN116739376A (en) * | 2023-06-12 | 2023-09-12 | 中铁二院工程集团有限责任公司 | Highway pavement preventive maintenance decision method based on data mining |
| CN117078235A (en) * | 2023-10-17 | 2023-11-17 | 深圳市城市交通规划设计研究中心股份有限公司 | Road network maintenance method, electronic equipment and storage medium for comprehensive evaluation |
| CN117372979A (en) * | 2023-09-15 | 2024-01-09 | 重庆赛力斯新能源汽车设计院有限公司 | Road inspection method, device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3035328C (en) * | 2017-03-31 | 2021-07-13 | Hitachi Construction Machinery Co., Ltd. | Road surface management system and road surface management method |
-
2024
- 2024-02-07 CN CN202410172923.9A patent/CN117726324B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9365217B2 (en) * | 2013-06-03 | 2016-06-14 | Booz Allen Hamilton Inc. | Mobile pothole detection system and method |
| CN109902571A (en) * | 2019-01-23 | 2019-06-18 | 中交信息技术国家工程实验室有限公司 | A kind of maintenance process of highway planting engineering and system based on unmanned plane |
| CN110837933A (en) * | 2019-11-11 | 2020-02-25 | 重庆远通电子技术开发有限公司 | Leakage identification method, device, equipment and storage medium based on neural network |
| CN111553902A (en) * | 2020-04-28 | 2020-08-18 | 周欢 | Highway road surface safety monitoring system based on big data |
| CN112836572A (en) * | 2020-12-20 | 2021-05-25 | 刘星亮 | Highway traffic construction inspection method and system |
| CN112884174A (en) * | 2021-02-05 | 2021-06-01 | 上海市市政工程管理咨询有限公司 | Daily maintenance information management method and system for road |
| KR102423218B1 (en) * | 2021-07-16 | 2022-07-20 | 한국건설기술연구원 | System and method for simultaneously detecting road damage and moving obstacles using deep neural network, and a recording medium recording a computer readable program for executing the method. |
| DE102022120968A1 (en) * | 2021-12-14 | 2023-06-15 | GM Global Technology Operations LLC | NETWORKED VEHICLE-BASED DETERMINATION OF ROAD SURFACE QUALITY |
| KR20230100787A (en) * | 2021-12-28 | 2023-07-06 | (주) 경성테크놀러지 | Active road integrated management system using artificial intelligence for road maintenance |
| CN114444737A (en) * | 2022-02-18 | 2022-05-06 | 招商局重庆交通科研设计院有限公司 | Intelligent pavement maintenance planning method based on transfer learning |
| CN114912635A (en) * | 2022-04-28 | 2022-08-16 | 广州铁路职业技术学院（广州铁路机械学校） | Highway maintenance decision-making method and system, storage medium and electronic equipment |
| CN115267143A (en) * | 2022-09-28 | 2022-11-01 | 江苏筑升土木工程科技有限公司 | Road cavity defect detection system and detection method |
| CN116739376A (en) * | 2023-06-12 | 2023-09-12 | 中铁二院工程集团有限责任公司 | Highway pavement preventive maintenance decision method based on data mining |
| CN117372979A (en) * | 2023-09-15 | 2024-01-09 | 重庆赛力斯新能源汽车设计院有限公司 | Road inspection method, device, electronic equipment and storage medium |
| CN117078235A (en) * | 2023-10-17 | 2023-11-17 | 深圳市城市交通规划设计研究中心股份有限公司 | Road network maintenance method, electronic equipment and storage medium for comprehensive evaluation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117726324A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2017401053B2 (en) | Method and apparatus for monitoring formation of ice on wind turbine blade | |
| CN113221905B (en) | Semantic segmentation unsupervised domain adaptation method, device and system based on uniform clustering and storage medium | |
| US7743005B2 (en) | Diagnosis of abnormal operation modes of a machine utilizing self organizing map | |
| US7464063B2 (en) | Information processor, state judging unit and diagnostic unit, information processing method, state judging method and diagnosing method | |
| CN114332749B (en) | Sand production monitoring method of sand production ship based on deep learning | |
| CN112347571A (en) | Rolling bearing residual life prediction method considering model and data uncertainty | |
| CN112542049A (en) | Comprehensive management and control platform for intelligent traffic | |
| CN110703743A (en) | Equipment failure prediction and detection system and method | |
| CN113379099A (en) | Machine learning and copula model-based highway traffic flow self-adaptive prediction method | |
| CN117726324B (en) | Road traffic construction inspection method and system based on data identification | |
| CN117711185B (en) | Multi-source data-based early warning and monitoring system and method for highway construction | |
| CN114863170A (en) | Deep learning-based new energy vehicle battery spontaneous combustion early warning method and device | |
| CN113918433A (en) | Adaptive intelligent network equipment performance index abnormity detection device and method | |
| CN113963314A (en) | Rainfall monitoring method and device, computer equipment and storage medium | |
| CN116881783B (en) | Road damage detection method, device, computer equipment and storage medium | |
| CN113221352A (en) | Complex equipment health management method and system based on digital twins | |
| CN112434600A (en) | Unmanned aerial vehicle inspection method and system | |
| CN112418460A (en) | Fault diagnosis method and fault diagnosis device for engineering vehicle | |
| Li et al. | Spilled load detection based on lightweight YOLOv4 trained with easily accessible synthetic dataset | |
| CN116805409A (en) | Method for identifying road surface state and evaluating flatness by using driving video | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| CN115660513A (en) | Monitoring method and system based on aqueduct deformation of hydraulic engineering | |
| Yang et al. | Forecasting model for urban traffic flow with BP neural network based on genetic algorithm | |
| CN113743654A (en) | Automatic wharf gate traffic flow early warning method | |
| CN114826951B (en) | Service automatic degradation method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |