CN117764303A - Road inspection data analysis system and method based on artificial intelligence - Google Patents
Road inspection data analysis system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117764303A CN117764303A CN202311533033.8A CN202311533033A CN117764303A CN 117764303 A CN117764303 A CN 117764303A CN 202311533033 A CN202311533033 A CN 202311533033A CN 117764303 A CN117764303 A CN 117764303A
- Authority
- CN
- China
- Prior art keywords
- road
- inspection
- route
- routes
- inspected
- 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.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 261
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 238000007405 data analysis Methods 0.000 title claims abstract description 16
- 201000010099 disease Diseases 0.000 claims abstract description 40
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 40
- 238000007726 management method Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims description 42
- 238000012216 screening Methods 0.000 claims description 34
- 238000010276 construction Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 230000003203 everyday effect Effects 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of road inspection, in particular to a road inspection data analysis system and method based on artificial intelligence, comprising the following steps: the road inspection system comprises a road information acquisition module, a database, an inspection sequence planning module, an inspection time management module and a road inspection module, wherein the road information acquisition module is used for acquiring route information required to be inspected and road traffic history information forming each route, all acquired data are transmitted to the database, all received data are stored in the database, the inspection sequence planning module is used for analyzing the road inspection emergency degree of different routes to be inspected, the road inspection is screened out, the road inspection is preferentially carried out, the inspection time management module is used for managing the time of the road inspection by utilizing the inspection vehicle according to the screened route, the road inspection is carried out on the corresponding route according to the management time through the road inspection module, the road inspection is reasonably carried out when resources are limited, the probability of disease position omission is reduced, and the road inspection quality is improved.
Description
Technical Field
The invention relates to the technical field of road inspection, in particular to a road inspection data analysis system and method based on artificial intelligence.
Background
Along with the rapid promotion of urban development, the construction and maintenance work of road infrastructure become increasingly important, so as to promote the digitization level of maintenance business, promote intelligent maintenance, adopt the inspection vehicle to replace the inspection work of road surface diseases in the running process by purely manual inspection, and utilize the artificial intelligence technology to carry out intelligent identification on the road surface diseases, so that the efficiency of road inspection and the accuracy of disease judgment can be effectively improved;
however, under the conditions that a large number of roads need to be inspected and the resources of the inspected vehicles are limited, the urgency of inspection maintenance of the inspection routes is different, the prior art does not carry out data analysis on the inspection route information, generally adopts random sequence to carry out road inspection, fails to reasonably allocate and screen necessary routes to carry out priority inspection and timely carry out road maintenance, and cannot reduce the overall road risk degree on the premise of limited resources; secondly, because the inspection vehicle shoots images and carries out disease identification in the driving process, the integrity of the shot images is very important, if the inspection vehicle has too much traffic, the distance between the inspection vehicle and a nearby vehicle is possibly small, and each image shooting has a time interval, the image shooting is possibly missed in the driving process, so that the complete road image on the inspection route cannot be shot, the probability of missing the disease position is high, the inspection vehicle cannot be arranged to carry out inspection work in a reasonable time period, and the probability of missing the disease position cannot be reduced in the prior art.
Therefore, there is a need for an artificial intelligence based road inspection data analysis system and method to solve the above problems.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based road inspection data analysis system and an artificial intelligence-based road inspection data analysis method, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an artificial intelligence based road inspection data analysis system, the system comprising: the system comprises a road information acquisition module, a database, a patrol order planning module, a patrol time management module and a road patrol module;
the output end of the road information acquisition module is connected with the input end of the database, the output end of the database is connected with the input ends of the inspection sequence planning module and the inspection time management module, the output end of the inspection sequence planning module is connected with the input end of the inspection time management module, and the output end of the inspection time management module is connected with the input end of the road inspection module;
the road information acquisition module is used for acquiring route information required to be inspected and road traffic history information forming each route, and transmitting all acquired data to the database;
the database is used for storing all received data;
the inspection sequence planning module is used for analyzing the road inspection emergency degree of different routes to be inspected, and screening out the routes to carry out road inspection preferentially;
the inspection time management module is used for managing the time of road inspection according to the screened route by using the inspection vehicle;
the road inspection module is used for performing road inspection on the corresponding route according to the management time.
Further, the road information acquisition module comprises a routing inspection route information acquisition unit, a vehicle information acquisition unit and a road construction information acquisition unit;
the output ends of the inspection route information acquisition unit, the vehicle information acquisition unit and the road construction information acquisition unit are connected with the input end of the database;
the routing inspection route information acquisition unit is used for acquiring route information to be inspected of the inspection vehicle, and comprises the number of routes to be inspected, route navigation information to be inspected and duration information expected to be needed by the inspection vehicle to inspect the corresponding routes;
the vehicle information acquisition unit is used for acquiring the past traffic flow information on each road of a route to be patrolled and examined, and comprises traffic flow information on the roads in different time periods every day and total number information of vehicles running on the roads, wherein each route to be patrolled and examined consists of a plurality of roads;
the road surface construction information acquisition unit is used for acquiring interval duration information of the current time of the built traffic time interval of the road surface forming the route to be inspected.
Further, the inspection sequence planning module comprises an emergency degree analysis unit and a priority route screening unit;
the input end of the emergency degree analysis unit is connected with the output end of the database, and the output end of the emergency degree analysis unit is connected with the input end of the priority route screening unit;
the emergency degree analysis unit is used for adjusting out total number information of vehicles travelling on each road of n routes to be inspected and interval duration information of the current time of the built-up traffic time interval of the road pavement corresponding to the routes to be inspected, analyzing the road inspection emergency degree of the n routes to be inspected, forming training samples of the road inspection emergency degree, the total number of vehicles and the interval duration data of the n routes to be inspected, establishing an emergency degree analysis model, substituting the route information of the rest routes to be inspected except the n routes to be inspected into the emergency degree analysis model, and analyzing the road inspection emergency degree of the rest routes to be inspected;
the priority route screening unit is used for comparing the road inspection emergency degree of all routes to be inspected and screening out the routes to be inspected, which need to be inspected with priority.
Further, the inspection time management module comprises a screening route analysis unit and an inspection time setting unit;
the input end of the screening route analysis unit is connected with the output ends of the priority route screening unit and the database; the output end of the screening route analysis unit is connected with the input end of the inspection time setting unit;
the screening route analysis unit is used for calling the traffic flow information of the screened route to be inspected, which needs to be inspected by the road preferentially, in different time periods every day, dividing m time periods by taking the time required by the inspection vehicle inspection to finish the corresponding route as unit time, and counting the traffic flow of the road in different time periods;
the inspection time setting unit is used for comparing the traffic flow on roads in different time periods, and arranging the inspection vehicle to carry out road inspection in the time period with the minimum traffic flow.
Further, the road inspection module comprises a road image shooting unit, a disease identification unit and an identification data transmission unit;
the input end of the road image shooting unit is connected with the output end of the inspection time setting unit, the output end of the road image shooting unit is connected with the input end of the disease identification unit, and the output end of the disease identification unit is connected with the input end of the identification data transmission unit;
the road image shooting unit is used for the inspection vehicle to run along the route to be inspected for road inspection preferentially according to navigation information in a scheduled time period and shooting road images;
the disease identification unit is used for identifying the disease of the road by utilizing a CNN network deep learning algorithm and obtaining a disease identification result;
the identification data transmission unit is used for transmitting the road disease identification result to the inspection terminal.
An artificial intelligence-based road inspection data analysis method comprises the following steps:
s1: collecting route information required to be inspected and road traffic history information forming each route;
s2: analyzing the road inspection emergency degree of different routes to be inspected;
s3: screening a route to carry out road inspection preferentially;
s4: managing the time for carrying out road inspection according to the screened route by utilizing the inspection vehicle;
s5: and carrying out road inspection on the corresponding route according to the management time.
Further, in step s1: the number of the routes to be inspected is c, the navigation information of the routes to be inspected and the time length information expected to be needed by the inspection vehicle to inspect the corresponding routes c are collected, the total number of vehicles running on each road of the routes c and the traffic flow information of the roads in different time periods every day are collected, and the time length information of the current time interval of the built traffic time interval of the road surfaces of the roads forming the routes c is collected.
Further, in step s2: and calling out n pieces of route information to be patrolled and examined from the c routes: the total number of vehicles running on each road of random one route in the n routes is acquired to be K= { K 1 ，K 2 ，...，K f Wherein f represents the number of roads constituting the corresponding route, and the interval duration set of the current time of the built-up traffic time interval of the road surface of the obtained f roads is t= { t 1 ，t 2 ，...，t f According to the formula }Road inspection for calculating random routeDegree of urgency Q i The road inspection emergency degree set for obtaining n routes is Q= { Q 1 ，Q 2 ，...，Q i ，...，Q n The total number of vehicles which are driven on each road of n routes and the interval duration of the current time of the built-up traffic time interval of the road surfaces of the n routes are called, and the average value set of the total number of vehicles which are driven on all the roads of each route in the n routes is k= { k 1 ，k 2 ，…，k n The average interval duration set of the current time of the built-up traffic time interval of the road pavement constituting each route of the n routes is u= { U 1 ，U 2 ，…，U n }, where k n Representing the average value of the total number of vehicles running on all roads of the nth route, U n The average interval duration of the current time of the built-up traffic time interval of all road surfaces representing the nth route is obtained by dividing the sum of the total number of vehicles which all roads of the corresponding route travel by the number of roads, the average interval duration is obtained by dividing the sum of the interval durations of the current time of the built-up traffic time interval of all road surfaces constituting the corresponding route by the number of roads, and a training sample data set { (k) is generated 1 ，U 1 ，Q 1 ），（k 2 ，U 2 ，Q 2 ），…，（k n ，U n ，Q n ) Fitting the training sample data, and establishing an emergency degree analysis model as follows: />Wherein x and y represent independent variables in the emergency degree analysis model, Z represents a model dependent variable, +.>、/>And->Representing fitting coefficients, solving for +.>、/>And->：
；
；
；
Wherein k is i Representing the average value of the total number of vehicles running on all roads of the ith route, U i The average interval duration of the current time of the built-up traffic intervals of all road surfaces of the ith route is represented, the route information of c-n routes to be patrolled except for n routes to be patrolled and examined is obtained from the average value of the total number of vehicles which travel on all roads of the rest routes and the average interval duration of the current time of the built-up traffic intervals of all road surfaces of the rest routes, the average value of the total number of vehicles which travel on all roads of a random route in the rest c-n routes is obtained, the average interval duration of the current time of the built-up traffic intervals of all road surfaces of the random route is T, and the x= L, y =T is obtained, so that the emergency degree of road patrol of the random route in the rest c-n routes is as follows:substituting the average value of the total number of vehicles and the average interval duration into an emergency degree analysis model to obtain the road inspection emergency degree of the remaining c-n routes to be inspected;
the method comprises the steps of analyzing route history information to be inspected through big data, firstly, retrieving part of routes, analyzing the road inspection emergency degree of the part of routes according to the number of vehicles which travel on the roads of the retrieved part of routes and the road construction traffic time of the roads forming the complete route, wherein the more vehicles travel, the more serious road surface diseases on the roads with diseases are, the longer the road construction traffic time is, the more road aging degree is judged, the road diseases are more likely to appear, after the retrieved road inspection emergency degree of the part of routes is obtained, the related data of the part of routes are formed into a training sample, an emergency degree analysis model is built, the related data of the rest routes are substituted into the model, the road inspection emergency degree of all routes can be obtained together, one-to-one analysis is not needed for each route, the workload of analyzing the inspection data of each route is reduced, and the obtaining efficiency of the road inspection emergency degree is improved.
Further, in step s3: combining to obtain a road inspection emergency degree set of Q= { Q for all the routes to be inspected 1 ，Q 2 ，…，Q c The emergency degree of road inspection is compared, c routes to be inspected are arranged in an order from the emergency degree to the small and then are divided into b groups, wherein the emergency degree of all routes to be inspected in the former group is greater than that of the latter group, and an average emergency degree set of each route to be inspected in the b groups is D= { D in a random grouping result 1 ，D 2 ，…，D b According to the formula }Calculating an emergency degree discrete coefficient G of a route to be patrolled and examined in a random grouping result, wherein D v Representing the average emergency degree of the v-th group route to be inspected in a random grouping result, calculating the emergency degree discrete coefficient of the route to be inspected in different grouping results in the same mode, screening out one grouping result with the highest discrete coefficient, and screening out the route to be inspected in the first group from the screened grouping result to carry out road inspection preferentially;
after the road inspection emergency degree of all routes is obtained through analysis, the routes to be inspected are grouped according to the emergency degree, the emergency degree discrete coefficients of the routes to be inspected in different grouping results are analyzed, the larger the discrete coefficients are, the closer the road inspection emergency degree of the routes to be inspected in each group in the grouping results is, the grouping result with the highest discrete coefficient is selected, the first group of routes to be inspected is screened out, the road inspection is carried out preferentially, the road inspection emergency degree of the first group of routes to be inspected in all routes is generally higher, the road driving safety is lower, the road inspection is required to be carried out preferentially, the routes are screened out in a grouping mode, the rationality of the screening result is improved, the road inspection is arranged to be carried out preferentially when the inspection vehicle, namely the road inspection resource is insufficient, the road inspection is favorable for reasonably carrying out, the road inspection is further carried out timely, the route with high demand, namely the route with higher emergency degree is preferentially maintained, and the overall road risk is reduced.
Further, in step s4: the predicted time length required by a random route selected by the inspection vehicle after inspection is called as H, the time of day is divided into m time periods by taking H as a unit time, the interval time length from the starting time to the ending time of each time period is H, and the total traffic flow set on the random road forming the corresponding route is called as V= { V in the random time period of w days in the past 1 ，V 2 ，…，V w According to }, according toObtaining the average traffic flow on a random road in a random time period, and obtaining the average traffic flow set on all roads forming the corresponding route in the random time period as F= { F 1 ，F 2 ，…，F e ，…，F a Obtaining the sum of the average traffic flows of all roads constituting the corresponding route in a random time period as J u ，/>The average traffic flow sum of all roads constituting the corresponding route in m time periods is calculated to be J= { J by the same method 1 ，J 2 ，…，J u ，…，J m Comparing the average traffic flow sum, and setting the time period with the minimum average traffic flow sum as the patrol vehicle to carry out corresponding routeAnd (5) a time period of road inspection.
Further, in step s5: the inspection vehicle runs and shoots a road image according to the route correspondingly screened by the navigation information in a set time period, a CNN network deep learning algorithm is utilized to identify the road diseases and acquire disease identification results, and the road disease identification results are transmitted to the inspection terminal;
the CNN network deep learning algorithm refers to a neural network deep learning algorithm, and road disease types comprise pit grooves, transverse cracks, longitudinal cracks, network cracks, road subsidence and the like on the road, and the artificial intelligence technology is utilized to carry out road inspection and identify road diseases, so that the accuracy of the identification result is improved, the maintenance of disease positions on the road in different modes by related personnel according to the accurate identification result is facilitated, and the road safety after the maintenance is improved;
after a route needing to be preferentially inspected on the road is selected, an optimal time period is selected to arrange the inspection vehicle to inspect the road, the time of day is divided into a plurality of time periods, the estimated required time for the inspection vehicle to complete the road inspection work of the corresponding route is taken as unit time to be divided, the inspection vehicle can encounter fewer vehicles when inspecting in the set optimal time period so as to smoothly complete the inspection, if the distance between the inspection vehicle and the front vehicle or the front vehicle is too small, the inspection vehicle can not shoot a complete road image in the driving process, the time period with the minimum traffic flow is selected as the optimal time period, the inspection vehicle is arranged to inspect the road in the set time period, the shooting omission probability caused by the fact that the distance between the inspection vehicle and the front vehicle or the front vehicle is small due to the excessive traffic flow in the inspection process is reduced, and the road inspection quality is improved.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the historical information of the route to be inspected is analyzed through big data, a part of route is firstly extracted, the road inspection emergency degree of the part of route is analyzed according to the number of vehicles which pass through on the road of the extracted part of route and the time for constructing the whole road, after the road inspection emergency degree of the extracted part of route is obtained, the related data of the part of route is formed into a training sample and an emergency degree analysis model is established, the related data of the rest of route is substituted into the model, the road inspection emergency degree of all routes can be obtained together, one-to-one analysis is not needed for each route, the workload for analyzing the inspection data of each route is reduced, and the obtaining efficiency of the road inspection emergency degree is improved;
after the road inspection emergency degree of all routes is obtained through analysis, the routes to be inspected are grouped according to the emergency degree, emergency degree discrete coefficients of the routes to be inspected in different grouping results are analyzed, the grouping result with the highest discrete coefficient is selected, the first group of routes to be inspected are screened out to conduct road inspection preferentially, the routes are screened out in a grouping mode, the rationality of the screening result is improved, when inspection vehicles, namely, the roads are insufficient in inspection resources, the roads are arranged to conduct preferential inspection, reasonable road inspection by utilizing limited resources is facilitated, the routes with high demands, namely, the routes with high emergency degree are maintained preferentially in time, and the overall road risk degree is reduced;
after a route needing to be preferentially inspected on the road is selected, an optimal time period is selected to arrange the inspection vehicle to inspect the road, the time of day is divided into a plurality of time periods, the estimated required time for the inspection vehicle to finish the road inspection work of the corresponding route is taken as unit time to be divided, the inspection vehicle can meet fewer vehicles when inspecting in the set optimal time period so as to smoothly finish inspection, the time period with the minimum traffic flow is selected as the optimal time period, the inspection vehicle is arranged to inspect the road in the set time period, the shooting probability caused by the fact that the distance between the inspection vehicle and a front vehicle or the distance between the inspection vehicle and a side front vehicle is reduced due to excessive traffic flow in the inspection process is reduced, the probability of disease position omission is reduced, and the road inspection quality is improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of an artificial intelligence based road inspection data analysis system of the present invention;
FIG. 2 is a flow chart of a method for analyzing road inspection data based on artificial intelligence.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention is further described below with reference to fig. 1-2 and the specific embodiments.
Embodiment one:
as shown in fig. 1, the present embodiment provides a road inspection data analysis system based on artificial intelligence, the system includes: the road information acquisition module is used for acquiring route information required to be inspected and road traffic history information forming each route, all acquired data are transmitted to the database, the database is used for storing all received data, the inspection sequence planning module is used for analyzing road inspection emergency degrees of different routes to be inspected, the screened routes are subjected to road inspection preferentially, the inspection time management module is used for managing the time of road inspection according to the screened routes by using the inspection vehicle, and the road inspection module is used for carrying out road inspection on the corresponding routes according to the management time.
The road information acquisition module comprises a routing inspection route information acquisition unit, a vehicle information acquisition unit and a road construction information acquisition unit, wherein the routing inspection route information acquisition unit is used for acquiring route information to be inspected of the routing inspection vehicle, the routing inspection route information comprises the number of routes to be inspected, route navigation information to be inspected and time length information expected to be required by the corresponding route of inspection vehicle inspection, the vehicle information acquisition unit is used for acquiring past traffic flow information on each road of the routes to be inspected, the traffic flow information comprises traffic flow information on different time periods every day on the roads and total number of vehicles travelling on the roads, each route to be inspected consists of a plurality of roads, and the road construction information acquisition unit is used for acquiring time interval time length information of the current time of the built traffic space of the road pavement forming the routes to be inspected.
The inspection sequence planning module comprises an emergency degree analysis unit and a priority route screening unit, wherein the emergency degree analysis unit is used for adjusting and taking out total number information of vehicles which travel on each road of n routes to be inspected and interval duration information of the current time of the built-up traffic time interval of the road pavement corresponding to the routes to be inspected, analyzing the road inspection emergency degree of the n routes to be inspected, forming training samples by the road inspection emergency degree of the n routes to be inspected, the total number of vehicles and the interval duration data, establishing an emergency degree analysis model, substituting the information of the routes to be inspected except the n routes to be inspected into the emergency degree analysis model, analyzing the road inspection emergency degree of the routes to be inspected, and the priority route screening unit is used for comparing the road inspection emergency degree of all the routes to be inspected and screening out the routes to be inspected which need to be inspected with priority.
The inspection time management module comprises a screening route analysis unit and an inspection time setting unit, wherein the screening route analysis unit is used for calling the traffic flow information of the screened roads needing to be inspected on the roads with priority in different time periods every day, dividing m time periods by taking the expected time length required by the inspection vehicle to finish the inspection of the corresponding routes as unit time, counting the traffic flows on the roads in different time periods, and the inspection time setting unit is used for comparing the traffic flows on the roads in different time periods and setting the time period with the minimum traffic flow to arrange the inspection vehicle to carry out the road inspection.
The road inspection module comprises a road image shooting unit, a disease identification unit and an identification data transmission unit, wherein the road image shooting unit is used for inspecting vehicles to travel along a route to be inspected and shooting road images according to navigation information to carry out road inspection preferentially as required in a scheduled time period, the disease identification unit is used for carrying out disease identification on roads by using a CNN network deep learning algorithm and obtaining a disease identification result, and the identification data transmission unit is used for transmitting the road disease identification result to an inspection terminal.
Embodiment two:
as shown in fig. 2, the present embodiment provides an artificial intelligence-based road inspection data analysis method, which is implemented based on the data analysis system in the embodiment, and specifically includes the following steps:
s1: collecting route information required to be inspected and road traffic history information forming each route, collecting the number of routes to be inspected as c, collecting the navigation information of the routes to be inspected and the duration information expected to be required by the inspection vehicle to inspect the corresponding c routes, collecting the total number of vehicles running on each road of the c routes and the traffic information of the roads in different time periods every day, and collecting the interval duration information of the current time of the built traffic time interval of the road surfaces forming the c routes;
s2: analyzing the road inspection emergency degree of different routes to be inspected, and calling n pieces of route information to be inspected from c routes: the total number of vehicles running on each road of random one route in the n routes is acquired to be K= { K 1 ，K 2 ，...，K f Wherein f represents the number of roads constituting the corresponding route, and the interval duration set of the current time of the built-up traffic time interval of the road surface of the obtained f roads is t= { t 1 ，t 2 ，...，t f According to the formula }Calculating road inspection emergency degree Q of random route i The road inspection emergency degree set for obtaining n routes is Q= { Q 1 ，Q 2 ，...，Q i ，...，Q n The total number of vehicles which are driven on each road of n routes and the interval duration of the current time of the built-up traffic time interval of the road surfaces of the n routes are called, and the average value set of the total number of vehicles which are driven on all the roads of each route in the n routes is k= { k 1 ，k 2 ，…，k n The average interval duration set of the current time of the built-up traffic time interval of the road pavement constituting each route of the n routes is u= { U 1 ，U 2 ，…，U n Generating a training sample dataset as { (k) 1 ，U 1 ，Q 1 ），（k 2 ，U 2 ，Q 2 ），…，（k n ，U n ，Q n ) Fitting the training sample data, and establishing an emergency degree analysis model as follows: />Wherein x and y represent independent variables in the emergency degree analysis model, Z represents a model dependent variable, +.>、/>And->Representing the fitting coefficients according to the formula ∈ ->、And->Separately solve for、/>And->Wherein k is i Representing the average value of the total number of vehicles running on all roads of the ith route, U i Representing the average interval duration of the current time of the built-up traffic time interval of all road surfaces of the ith route, and obtaining the average value of the total number of vehicles running on all the roads of the rest route and all the road surfaces of the rest route from the rest of the c-n route information to be patrolled except for the n routes to be patrolledThe average interval duration of the current time of the built-up traffic interval is obtained, the average value of the total number of vehicles which travel on all roads of a random one of the remaining c-n routes is L, the average interval duration of the current time of the built-up traffic interval on all road surfaces of the random one of the routes is T, and x= L, y =T is given, so that the emergency degree of road inspection of the random one of the remaining c-n routes is obtained: />Substituting the average value of the total number of vehicles and the average interval duration into an emergency degree analysis model to obtain the road inspection emergency degree of the remaining c-n routes to be inspected;
for example: on solving to obtain、/>And->The final emergency degree analysis model is obtained as follows:the average value of the total number of vehicles running on all roads of one random route in the rest routes is L=200, the average interval duration of the current time of the built traffic time interval of all road surfaces of one random route is T=4, and the unit is: for each year, let x=l=200, y=t=4, the road inspection urgency to obtain the corresponding route is:；
s3: screening routes to carry out road inspection preferentially, and combining to obtain a road inspection emergency degree set of all routes to be inspected, wherein the road inspection emergency degree set is Q= { Q 1 ，Q 2 ，…，Q c Comparing the emergency degree of road inspection, arranging c routes to be inspected according to the order of the emergency degree from big to small, and dividing the routes into b groups, wherein the emergency degree of all routes to be inspected in the former group is greater than that of the latter group, and acquiring the following routesIn the machine-one grouping result, the average emergency degree set of each group of routes to be patrolled and examined in group b is D= { D 1 ，D 2 ，…，D b According to the formula }Calculating an emergency degree discrete coefficient G of a route to be patrolled and examined in a random grouping result, wherein D v Representing the average emergency degree of the v-th group route to be inspected in a random grouping result, calculating the emergency degree discrete coefficient of the route to be inspected in different grouping results in the same mode, screening out one grouping result with the highest discrete coefficient, and screening out the route to be inspected in the first group from the screened grouping result to carry out road inspection preferentially;
s4: managing the time of road inspection according to the screened route by using the inspection vehicle, and s5: according to the management time, road inspection is carried out on the corresponding route, the expected required time length of a random route selected after inspection of the inspection vehicle is called as H, one-day time is divided into m time periods by taking H as a unit time, the interval time length from the starting time to the ending time of each time period is called as H, and the total traffic flow set on the random route forming the corresponding route is called as V= { V in the previous random time period of w days 1 ，V 2 ，…，V w According to }, according toObtaining the average traffic flow on a random road in a random time period, and obtaining the average traffic flow set on all roads forming the corresponding route in the random time period as F= { F 1 ，F 2 ，…，F e ，…，F a Obtaining the sum of the average traffic flows of all roads constituting the corresponding route in a random time period as J u ，/>The average traffic flow sum of all roads constituting the corresponding route in m time periods is calculated to be J= { J by the same method 1 ，J 2 ，…，J u ，…，J m And comparing the average vehicle flow sum, setting a time period with the minimum average vehicle flow sum as a time period for the inspection vehicle to inspect the road on the corresponding route, driving the inspection vehicle in the set time period according to the route correspondingly screened by the navigation information, shooting a road image, identifying the road by using a CNN network deep learning algorithm, acquiring a disease identification result, and transmitting the road disease identification result to the inspection terminal.
Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides a road inspection data analysis system based on artificial intelligence which characterized in that: the system comprises: the system comprises a road information acquisition module, a database, a patrol order planning module, a patrol time management module and a road patrol module;
the output end of the road information acquisition module is connected with the input end of the database, the output end of the database is connected with the input ends of the inspection sequence planning module and the inspection time management module, the output end of the inspection sequence planning module is connected with the input end of the inspection time management module, and the output end of the inspection time management module is connected with the input end of the road inspection module;
the road information acquisition module is used for acquiring route information required to be inspected and road traffic history information forming each route, and transmitting all acquired data to the database;
the database is used for storing all received data;
the inspection sequence planning module is used for analyzing the road inspection emergency degree of different routes to be inspected, and screening out the routes to carry out road inspection preferentially;
the inspection time management module is used for managing the time of road inspection according to the screened route by using the inspection vehicle;
the road inspection module is used for performing road inspection on the corresponding route according to the management time.
2. The system for analyzing road inspection data based on artificial intelligence according to claim 1, wherein: the road information acquisition module comprises a routing inspection route information acquisition unit, a vehicle information acquisition unit and a road construction information acquisition unit;
the output ends of the inspection route information acquisition unit, the vehicle information acquisition unit and the road construction information acquisition unit are connected with the input end of the database;
the routing inspection route information acquisition unit is used for acquiring route information to be inspected of the inspection vehicle, and comprises the number of routes to be inspected, route navigation information to be inspected and duration information expected to be needed by the inspection vehicle to inspect the corresponding routes;
the vehicle information acquisition unit is used for acquiring the past traffic flow information on each road of a route to be patrolled and examined, and comprises traffic flow information on the roads in different time periods every day and total number information of vehicles running on the roads, wherein each route to be patrolled and examined consists of a plurality of roads;
the road surface construction information acquisition unit is used for acquiring interval duration information of the current time of the built traffic time interval of the road surface forming the route to be inspected.
3. The system for analyzing road inspection data based on artificial intelligence according to claim 1, wherein: the inspection sequence planning module comprises an emergency degree analysis unit and a priority route screening unit;
the input end of the emergency degree analysis unit is connected with the output end of the database, and the output end of the emergency degree analysis unit is connected with the input end of the priority route screening unit;
the emergency degree analysis unit is used for adjusting out total number information of vehicles travelling on each road of n routes to be inspected and interval duration information of the current time of the built-up traffic time interval of the road pavement corresponding to the routes to be inspected, analyzing the road inspection emergency degree of the n routes to be inspected, forming training samples of the road inspection emergency degree, the total number of vehicles and the interval duration data of the n routes to be inspected, establishing an emergency degree analysis model, substituting the route information of the rest routes to be inspected except the n routes to be inspected into the emergency degree analysis model, and analyzing the road inspection emergency degree of the rest routes to be inspected;
the priority route screening unit is used for comparing the road inspection emergency degree of all routes to be inspected and screening out the routes to be inspected, which need to be inspected with priority.
4. A system for analyzing road inspection data based on artificial intelligence according to claim 3, wherein: the inspection time management module comprises a screening route analysis unit and an inspection time setting unit;
the input end of the screening route analysis unit is connected with the output ends of the priority route screening unit and the database; the output end of the screening route analysis unit is connected with the input end of the inspection time setting unit;
the screening route analysis unit is used for calling the traffic flow information of the screened route to be inspected, which needs to be inspected by the road preferentially, in different time periods every day, dividing m time periods by taking the time required by the inspection vehicle inspection to finish the corresponding route as unit time, and counting the traffic flow of the road in different time periods;
the inspection time setting unit is used for comparing the traffic flow on roads in different time periods, and arranging the inspection vehicle to carry out road inspection in the time period with the minimum traffic flow.
5. The system for analyzing road inspection data based on artificial intelligence according to claim 4, wherein: the road inspection module comprises a road image shooting unit, a disease identification unit and an identification data transmission unit;
the input end of the road image shooting unit is connected with the output end of the inspection time setting unit, the output end of the road image shooting unit is connected with the input end of the disease identification unit, and the output end of the disease identification unit is connected with the input end of the identification data transmission unit;
the road image shooting unit is used for the inspection vehicle to run along the route to be inspected for road inspection preferentially according to navigation information in a scheduled time period and shooting road images;
the disease identification unit is used for identifying the disease of the road by utilizing a CNN network deep learning algorithm and obtaining a disease identification result;
the identification data transmission unit is used for transmitting the road disease identification result to the inspection terminal.
6. The road inspection data analysis method based on artificial intelligence is characterized by comprising the following steps of: the method comprises the following steps:
s1: collecting route information required to be inspected and road traffic history information forming each route;
s2: analyzing the road inspection emergency degree of different routes to be inspected;
s3: screening a route to carry out road inspection preferentially;
s4: managing the time for carrying out road inspection according to the screened route by utilizing the inspection vehicle;
s5: and carrying out road inspection on the corresponding route according to the management time.
7. The method for analyzing road inspection data based on artificial intelligence according to claim 6, wherein the method comprises the following steps: in step s1: the number of the routes to be inspected is c, the navigation information of the routes to be inspected and the time length information expected to be needed by the inspection vehicle to inspect the corresponding routes c are collected, the total number of vehicles running on each road of the routes c and the traffic flow information of the roads in different time periods every day are collected, and the time length information of the current time interval of the built traffic time interval of the road surfaces of the roads forming the routes c is collected.
8. The method for analyzing road inspection data based on artificial intelligence according to claim 7, wherein the method comprises the following steps: in step s2: and calling out n pieces of route information to be patrolled and examined from the c routes: the total number of vehicles running on each road of random one route in the n routes is acquired to be K= { K 1 ，K 2 ，...，K f Wherein f represents the number of roads constituting the corresponding route, and the interval duration set of the current time of the built-up traffic time interval of the road surface of the obtained f roads is t= { t 1 ，t 2 ，...，t f According to the formula }Calculating road inspection emergency degree Q of random route i The road inspection emergency degree set for obtaining n routes is Q= { Q 1 ，Q 2 ，...，Q i ，...，Q n The total number of vehicles which are driven on each road of n routes and the interval duration of the current time of the built-up traffic time interval of the road surfaces of the n routes are called, and the average value set of the total number of vehicles which are driven on all the roads of each route in the n routes is k= { k 1 ，k 2 ，…，k n The average interval duration set of the current time of the built-up traffic time interval of the road pavement constituting each route of the n routes is u= { U 1 ，U 2 ，…，U n Generating a training sample dataset as { (k) 1 ，U 1 ，Q 1 ），（k 2 ，U 2 ，Q 2 ），…，（k n ，U n ，Q n ) Fitting the training sample data, and establishing an emergency degree analysis model as follows: />Wherein x and y represent independent variables in the emergency degree analysis model, Z represents a model dependent variable, +.>、/>And->Representing fitting coefficients, solving for +.>、/>And->：
；
；
；
Wherein k is i Representing the average value of the total number of vehicles running on all roads of the ith route, U i Representing the average interval duration of the current time of the built-up traffic interval of all road surfaces of the ith route, obtaining the total number average of vehicles running on all roads of the rest route and the average interval duration of the current time of the built-up traffic interval of all road surfaces of the rest route from the rest route information of c-n routes to be patrolled except n routes to be patrolled, obtaining the total number average of vehicles running on all roads of a random one route in the rest c-n routes to be L, and obtaining the average of the current time of the built-up traffic interval of all road surfaces of the random one routeThe average interval duration is T, let x= L, y =T, get the road inspection emergency degree of a random route in the remaining c-n routes as follows:and substituting the average value of the total number of the vehicles and the average interval duration into an emergency degree analysis model to obtain the road inspection emergency degree of the remaining c-n routes to be inspected.
9. The method for analyzing road inspection data based on artificial intelligence according to claim 8, wherein the method comprises the following steps: in step s3: combining to obtain a road inspection emergency degree set of Q= { Q for all the routes to be inspected 1 ，Q 2 ，…，Q c Comparing the emergency degree of road inspection, arranging c routes to be inspected according to the order of the emergency degree from big to small, dividing the routes into b groups, and obtaining an average emergency degree set of each route to be inspected in the b groups as D= { D in a random grouping result 1 ，D 2 ，…，D b According to the formula }Calculating an emergency degree discrete coefficient G of a route to be patrolled and examined in a random grouping result, wherein D v The average emergency degree of the v-th group route to be inspected in the random one grouping result is represented, emergency degree discrete coefficients of routes to be inspected in different grouping results are obtained through calculation in the same mode, one grouping result with the highest discrete coefficient is screened out, and the route to be inspected in the first group is screened out from the screened grouping results to carry out road inspection preferentially.
10. The method for analyzing road inspection data based on artificial intelligence according to claim 9, wherein the method comprises the following steps: in steps s4-s 5: the predicted time length required by a random route selected after finishing inspection of the inspection vehicle is H, m time periods are divided from one day time by taking H as a unit time, the interval time length from the starting time to the ending time of each time period is H, and the random route is selected in the past for w daysIn the time period, the total number of traffic flows on a random one road constituting the corresponding route is set to be v= { V 1 ，V 2 ，…，V w According to }, according toObtaining the average traffic flow on a random road in a random time period, and obtaining the average traffic flow set on all roads forming the corresponding route in the random time period as F= { F 1 ，F 2 ，…，F e ，…，F a Obtaining the sum of the average traffic flows of all roads constituting the corresponding route in a random time period as J u ，/>The average traffic flow sum of all roads constituting the corresponding route in m time periods is calculated to be J= { J by the same method 1 ，J 2 ，…，J u ，…，J m And comparing the average vehicle flow sum, setting a time period with the minimum average vehicle flow sum as a time period for the inspection vehicle to inspect the road on the corresponding route, driving the inspection vehicle in the set time period according to the route correspondingly screened by the navigation information, shooting a road image, identifying the road by using a CNN network deep learning algorithm, acquiring a disease identification result, and transmitting the road disease identification result to the inspection terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311533033.8A CN117764303B (en) | 2023-11-17 | 2023-11-17 | Road inspection data analysis system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311533033.8A CN117764303B (en) | 2023-11-17 | 2023-11-17 | Road inspection data analysis system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117764303A true CN117764303A (en) | 2024-03-26 |
| CN117764303B CN117764303B (en) | 2024-06-21 |
Family
ID=90312824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311533033.8A Active CN117764303B (en) | 2023-11-17 | 2023-11-17 | Road inspection data analysis system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117764303B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260217A (en) * | 2020-01-16 | 2020-06-09 | 赵志平 | Highway daily maintenance information management system |
| CN112507919A (en) * | 2020-12-16 | 2021-03-16 | 南京渐起网络科技有限公司 | Highway comprehensive management visual cloud computing platform based on big data analysis |
| WO2021057213A1 (en) * | 2019-09-23 | 2021-04-01 | 上海意略明数字科技股份有限公司 | Big data acquisition and analysis system based on intelligent image recognition, and application method |
| CN112820109A (en) * | 2021-01-15 | 2021-05-18 | 林安齐 | Road inspection safety early warning method and system |
| CN113485376A (en) * | 2021-08-16 | 2021-10-08 | 厦门中卡科技股份有限公司 | Unmanned inspection vehicle with self-adaptive cruise and path planning functions |
| CN113706737A (en) * | 2021-10-27 | 2021-11-26 | 北京主线科技有限公司 | Road surface inspection system and method based on automatic driving vehicle |
| CN113724503A (en) * | 2021-08-31 | 2021-11-30 | 山东交通学院 | Automatic highway state inspection system and method based on cloud platform |
| CN114266892A (en) * | 2021-12-20 | 2022-04-01 | 江苏燕宁工程科技集团有限公司 | Pavement disease identification method and system for multi-source data deep learning |
| CN114333313A (en) * | 2021-12-29 | 2022-04-12 | 金陵科技学院 | Intelligent inspection method based on highway monitoring |
| CN114363316A (en) * | 2022-01-28 | 2022-04-15 | 交通运输部路网监测与应急处置中心 | Intelligent networking monitoring and supervision system for cross-regional road infrastructure |
| CN115577810A (en) * | 2022-10-18 | 2023-01-06 | 微纵联合网络科技(武汉)有限公司 | Traffic road operation and maintenance intelligent management system based on image recognition technology |
| CN115936356A (en) * | 2022-11-30 | 2023-04-07 | 金陵科技学院 | Traffic maintenance planning method based on Internet of things technology |
| KR20230079606A (en) * | 2021-11-29 | 2023-06-07 | 연세대학교 산학협력단 | Deep Learning-based Road Condition Monitoring System and Method |
| CN117014472A (en) * | 2023-09-04 | 2023-11-07 | 中国长江电力股份有限公司 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
-
2023
- 2023-11-17 CN CN202311533033.8A patent/CN117764303B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021057213A1 (en) * | 2019-09-23 | 2021-04-01 | 上海意略明数字科技股份有限公司 | Big data acquisition and analysis system based on intelligent image recognition, and application method |
| CN111260217A (en) * | 2020-01-16 | 2020-06-09 | 赵志平 | Highway daily maintenance information management system |
| CN112507919A (en) * | 2020-12-16 | 2021-03-16 | 南京渐起网络科技有限公司 | Highway comprehensive management visual cloud computing platform based on big data analysis |
| CN112820109A (en) * | 2021-01-15 | 2021-05-18 | 林安齐 | Road inspection safety early warning method and system |
| CN113485376A (en) * | 2021-08-16 | 2021-10-08 | 厦门中卡科技股份有限公司 | Unmanned inspection vehicle with self-adaptive cruise and path planning functions |
| CN113724503A (en) * | 2021-08-31 | 2021-11-30 | 山东交通学院 | Automatic highway state inspection system and method based on cloud platform |
| CN113706737A (en) * | 2021-10-27 | 2021-11-26 | 北京主线科技有限公司 | Road surface inspection system and method based on automatic driving vehicle |
| KR20230079606A (en) * | 2021-11-29 | 2023-06-07 | 연세대학교 산학협력단 | Deep Learning-based Road Condition Monitoring System and Method |
| CN114266892A (en) * | 2021-12-20 | 2022-04-01 | 江苏燕宁工程科技集团有限公司 | Pavement disease identification method and system for multi-source data deep learning |
| CN114333313A (en) * | 2021-12-29 | 2022-04-12 | 金陵科技学院 | Intelligent inspection method based on highway monitoring |
| CN114363316A (en) * | 2022-01-28 | 2022-04-15 | 交通运输部路网监测与应急处置中心 | Intelligent networking monitoring and supervision system for cross-regional road infrastructure |
| CN115577810A (en) * | 2022-10-18 | 2023-01-06 | 微纵联合网络科技(武汉)有限公司 | Traffic road operation and maintenance intelligent management system based on image recognition technology |
| CN115936356A (en) * | 2022-11-30 | 2023-04-07 | 金陵科技学院 | Traffic maintenance planning method based on Internet of things technology |
| CN117014472A (en) * | 2023-09-04 | 2023-11-07 | 中国长江电力股份有限公司 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
Non-Patent Citations (4)
| Title |
|---|
| 于中华;: "浅谈移动巡查技术在高速公路营运管理上的应用", 通讯世界, no. 14, 25 July 2017 (2017-07-25), pages 263 - 264 * |
| 何桂平，李宇峙: "公路改建和养护的优先性规划", 国外公路, no. 06, 19 December 1996 (1996-12-19), pages 6 * |
| 吕宁宁;潘娜娜;董慧;: "建立数学模型解决"巡检线路排班"问题", 河北北方学院学报(自然科学版), vol. 36, no. 03, 28 March 2020 (2020-03-28), pages 35 - 43 * |
| 陆春桃;: "巡检线路排班优化模型研究――以某厂26个站点为例", 企业科技与发展, no. 11, 10 November 2017 (2017-11-10), pages 35 - 38 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117764303B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106228808B (en) | City expressway travel time prediction method based on Floating Car space-time grid data | |
| CN110362557B (en) | Missing path repairing method based on machine learning and license plate recognition data | |
| CN112800913A (en) | Pavement damage data space-time analysis method based on multi-source feature fusion | |
| CN104318324A (en) | Taxi GPS (Global Positioning System) record based airport bus station and path planning method | |
| CN114049765A (en) | Urban road network traffic flow OD estimation method based on automatic vehicle number plate identification data | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN108648445A (en) | Dynamic traffic Tendency Prediction method based on traffic big data | |
| CN114463972A (en) | Road section interval traffic analysis and prediction method based on ETC portal communication data | |
| CN115662122B (en) | Maintenance system and method for road inspection, disease identification and inspection and examination based on GPS | |
| CN113269347B (en) | College express network node flow prediction method based on random forest | |
| CN116631186B (en) | Expressway traffic accident risk assessment method and system based on dangerous driving event data | |
| CN116824861B (en) | Method and system for scheduling sharing bicycle based on multidimensional data of urban brain platform | |
| CN112215416B (en) | Intelligent planning inspection route system and method | |
| CN117437789B (en) | Intelligent park system based on multidimensional linkage command scheduling of city information model | |
| CN116052435B (en) | Urban road congestion influence range definition and road influence calculation method | |
| CN110636134A (en) | Urban road damage monitoring and maintaining method and system | |
| CN115995149A (en) | Multi-source data-based parking supply and demand characteristic dynamic evaluation method and system | |
| CN110287995B (en) | Multi-feature learning network model method for grading all-day overhead traffic jam conditions | |
| US20230386327A1 (en) | Methods and internet of things systems for managing traffic road cleaning in smart city | |
| CN114647684A (en) | Traffic prediction method and device based on stacking algorithm and related equipment | |
| CN110659774B (en) | Big data method driven parking demand prediction method | |
| CN116258290A (en) | Wisdom trip system based on big data | |
| CN117575349A (en) | Urban data model-based traffic influence evaluation method and system | |
| CN116884223B (en) | Smart city traffic guiding system | |
| CN117764303B (en) | Road inspection data analysis system and method based on artificial intelligence |
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 |