CN113128789A - Urban road surface collapse prevention method and system based on probability prediction and storage medium - Google Patents
Urban road surface collapse prevention method and system based on probability prediction and storage medium Download PDFInfo
- Publication number
- CN113128789A CN113128789A CN202110539246.6A CN202110539246A CN113128789A CN 113128789 A CN113128789 A CN 113128789A CN 202110539246 A CN202110539246 A CN 202110539246A CN 113128789 A CN113128789 A CN 113128789A
- Authority
- CN
- China
- Prior art keywords
- road
- road surface
- probability
- collapse
- ind
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000002265 prevention Effects 0.000 title claims description 18
- 238000003860 storage Methods 0.000 title claims description 9
- 238000010276 construction Methods 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 230000009467 reduction Effects 0.000 claims abstract description 11
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 9
- 238000009933 burial Methods 0.000 claims description 6
- 238000001556 precipitation Methods 0.000 claims description 6
- 230000008439 repair process Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 239000000758 substrate Substances 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- CNIIGCLFLJGOGP-UHFFFAOYSA-N 2-(1-naphthalenylmethyl)-4,5-dihydro-1H-imidazole Chemical compound C=1C=CC2=CC=CC=C2C=1CC1=NCCN1 CNIIGCLFLJGOGP-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
A method for preventing urban road surface collapse based on probability prediction comprises the following steps of 1, constructing a road surface collapse related index system, and performing dimension reduction treatment on the road surface collapse related index system by adopting a principal component analysis method; 2. the method comprises the steps of (1) realizing classification of samples of different road sections by adopting an unsupervised clustering method, and providing a classification method with adjustable parameters based on density and distance to classify known road surface collapse accidents; 3. defining the occurrence probability of the general road surface collapse of one class, and proposing the membership degree of each acquisition road section sample point in the class to the road surface collapse probability of the class based on the maximum similarity estimation; 4. and calculating and re-classifying categories according to the similarity of the geological conditions and the road construction quality, and constructing a machine learning prediction model for each category of road section sample points to realize the prediction of the road surface collapse probability of the same category of road sections under different road operation conditions.
Description
Technical Field
The invention relates to the technical field of road collapse prediction, in particular to a method and a system for preventing urban road surface collapse based on probability prediction and a storage medium.
Background
In recent years, the occurrence frequency of road surface collapse accidents is gradually increased, and the accidents are sudden, so that great hidden dangers are brought to the life and property safety of people and the social public transportation safety. The prediction of the road surface collapse probability is helpful for people to actively make the prevention work of the emergency, and has very important practical significance. Currently, research in this regard is very rare. The urban road surface collapse prevention method based on probability prediction can predict the collapse probability of the road surface through a machine learning method, and further reduce the collapse probability of the road surface to a safe range through regulating and controlling the running condition of the road, so that the advance prevention work of the road surface collapse is realized, and the risk of the road surface collapse is reduced.
Disclosure of Invention
The invention aims to provide a method, a system and a storage medium for preventing urban road surface collapse based on probability prediction.
The invention is realized by the technical scheme, and the method comprises the following specific steps:
1) constructing a pavement index information set, wherein the pavement index set comprises road construction quality information, geological condition information, external environment information and running road condition information;
2) processing and clustering the index data of the road index information set, and dividing n road section samples into Q categories;
3) collecting a pavement index information data set in historical pavement collapse accidents, constructing a classification sample space, and classifying the pavement index information set in the historical pavement collapse accidents in the classification sample space according to the Q categories by adopting a distance and density-based method;
4) calculating the road surface collapse probability of each category and the probability membership degree of each sample point;
5) respectively constructing a machine learning prediction model for predicting the road surface collapse probability aiming at each category;
6) collecting a road index information set of a road section to be evaluated, determining the road type j (j is 1,2,.. multidot.A) of the target road section by adopting a distance and density-based method in the step 3) according to geological conditions and road construction quality, setting probability membership, and adopting a machine learning prediction model LM obtained in the step 6)jPredicting the road surface collapse probability of the road section;
7) and setting a safety probability threshold value of the road surface collapse, taking the road running road condition as a regulation object, and obtaining the running road condition range lower than the set safety probability threshold value through an intelligent optimization algorithm.
Further, the specific contents of the road construction quality information, the geological condition information, the external environment information and the operation road condition information in the step 1) are as follows:
1-1) the road construction quality information includes:
road repair rate
SrFor road repair area, SaIs the total area of the road;
road condition index
Representing the weight of the ith road damage type, wherein the road damage type is mainly divided into a crack type, a deformation type and other types; omega represents the severity of road damage, the value range is 0 to 1, and the larger the value is, the more serious the damage is; σ is the damage density;
road surface strength index
a0,a1Is a constant;
structural strength index of pavement
ld,lsRespectively represent the pavement design deflection, the actual measurement represents the deflection, the unit: millimeter;
road age ind — 5;
1-2) the geological condition information comprises:
the value range of the geological stability ind _6 is 0 to 1;
bearing capacity ind _7 ═ f of foundationk+εbγ(b-3)+εdγ0(d-0.5)，fkRepresenting the standard value of the bearing capacity (kN/m) of the soft soil layer at the bottom surface of the cushion layer2)，εb,εdThe bearing capacity correction coefficients respectively represent the width and the burial depth of the foundation, b represents the width (m) of the foundation, d represents the burial depth (m) of the foundation, and gamma represents the bottom gravity (kN/m) of the foundation3)，γ0Average background Severe on the substrate (kN/m)3)；
1-3) the external environment information comprises:
a monthly average precipitation ind _8, a monthly precipitation maximum variance ind _9, a monthly average air temperature ind _10, a monthly air temperature maximum variance ind _11, a monthly average humidity ind _12 and a monthly humidity maximum variance ind _ 13;
1-4) the traffic information includes:
the average pedestrian flow rate ind _14, the average vehicle flow rate ind _15 and the daily bearing load ind _ 16;
further, the concrete steps of processing and clustering the index data of the road index information set in the step 2) are as follows:
2-1) normalizing data ori _ data of the road index information set [ ind _1, ind _2, ·, ind _16], and performing dimensionality reduction by a principal component analysis method:
and 2-2) carrying out unsupervised clustering analysis on the reconstructed data by adopting a K-means algorithm, and dividing n road section samples into Q categories.
Further, the step 2-1) of performing the dimensionality reduction by the principal component analysis method comprises the following specific steps:
2-1-1) calculating a correlation coefficient matrix corr16×16；
2-1-2) calculating characteristic value lambda of correlation coefficient matrixi(i ═ 1, 2.., 16) and a feature vector ηi(i＝1,2,...,16)；
2-1-3) arranging the characteristic values in the order from big to small, and calculating the top t(t 1, 2.., 16) feature values correspond to the accumulated contribution degree of the principal component
2-1-4) when cumtWhen the sum is just equal to or greater than 0.95, the eigenvectors corresponding to the first t principal components are taken to form a transformation matrix tran ═ η1,η2,...,ηt]Wherein etat＝[e1,e2,...,e16]T，data＝ori_data×tran＝[ind_1,ind_2,...,ind_t]Namely the reconstructed data after the dimension reduction; the t-th principal component data is ind _ t ═ a1t,a2t,...,ant]T，antThe nth sample data representing the t-th principal component.
Further, the step 2-2) of performing unsupervised cluster analysis on the reconstructed data by using a K-means algorithm comprises the following specific steps:
2-2-1) setting the number Q of the clustering target categories and a minimum threshold value, and randomly selecting Q sample points from the data set data as category cluster centers;
2-2-2) assigning each sample point to the cluster center of the closest class;
2-2-3) calculating the average value of all samples of each cluster, taking the average value as a new cluster center, and calculating the distance between the centroid of each cluster before and after updating;
2-2-4) if the distance between the centers of the front and rear clusters is greater than or equal to a set threshold, returning to the step 2-2-2); and if the distance between the centers of the front and rear clusters is smaller than a set threshold value, stopping the calculation and obtaining a clustering result.
Further, the specific steps of clustering the pavement index information sets in the historical pavement collapse accidents in the classification sample space by Q categories by adopting a distance and density-based method in the step 3) are as follows:
3-1) collecting road surface index information data event _ data in historical road surface collapse accidentss×16Reconstructing all road surface collapse accident index information through a conversion matrix tran to obtain e _ data ═ event _ data × tran [ [ y ═ y1,y2,...,yi,...,yt]Wherein y isi＝[y1i,y2i,...,ysi]TS represents the total number of samples of the road surface collapse accident;
3-2) constructing a t-dimensional coordinate system by using the t indexes, and constructing a classification sample point space;
3-3) calculating cluster center coordinates of each cluster of the sample point space, wherein the cluster center coordinates of the kth (k is 1,2,.., Q)) cluster are as follows:
wherein ind _ ikjData representing the ith index of the jth sample in the kth class cluster, and m represents the total number of sample points of the kth class cluster;
3-4) calculating the distance from each road surface collapse sample point to the centers of various clusters in the historical road surface collapse accidents, wherein the h (h is 1,2, s) th road surface collapse sample point is (y)h1,yh2,...,yhi,...,yht) Then the sample point goes to the cluster CenterkThe distance of (d) can be written as:
the distance from the h (h ═ 1, 2.., s) th road surface collapse sample point to the centers of all the cluster types is Dh＝[dh1,dh2,...,dhk,...,dhQ]；
Counting the number of sample points in each cluster in the radius r by taking the h (h is 1,2,.. s) th pavement collapse sample point as the center of a circle, and counting the num number of the k type sample pointskIf the number of the h-th pavement collapse sample point is not less than the number of the adjacent various sample points within the radius rh＝[numh1,numh2,...numhk,...,numhQ]；
The effective value of the radius r is not more than the maximum value of the linear distance between the h (h is 1, 2.., s) th road surface collapse sample point and each sampling road section sample point, and is not less than the minimum value of the linear distance;
based on the principle that the number of samples in a certain category is the largest when the center of the cluster is the nearest and within a set radius, the Num is obtainedhAnd DhThe normalization results in Num _ guihAnd D _ guihThe attribution degree is calculated according to the following formula:
Attributionh＝α×Num_guih-β×D_guih＝[ath1,ath2,...,athi,...,athQ]
wherein, α, β ∈ [0,1] is a weight coefficient, and α + β ═ 1 is satisfied, and a specific weight value needs to be determined according to actual data distribution; the more concentrated the data cluster distribution and the larger the class interval, the larger the beta value; if the data cluster distribution is more dispersed and the class interval is smaller, the alpha value is larger;
selection of AttributionhMaximum mean value athxAnd the subscript x is the category serial number of the h-th road surface collapse sample point.
Further, the concrete steps of calculating the road surface collapse probability of each category and the probability membership degree of each sample point in the step 4) are as follows:
4-1) note that P is present in the kth (k ═ 1,2kThe total number of road surface collapse accidents is Nk，εkFor a proportionality constant less than 1, the general probability of collapse for the class of road segments is:
if PkIf not equal to 0, then take Pk0.01, i.e. the probability of collapse for any road segment, guarantees probkIs not 0;
4-2) calculating the similarity between each non-collapse accident sample point and each collapse accident sample point in the kth category, and obtaining a similarity matrix as follows:
in matrix bijRepresenting the similarity of the ith collapse accident sample point and the jth non-collapse accident sample point, wherein m represents the total number of the non-collapse accident sample points in the kth category;
4-3) pairs sim _ matrixkIs maximized to obtain mu _ kmax＝[bmax1,bmax2,...,bmaxj,bmaxm]，bmaxjThe probability of occurrence of the jth uncollapsed accident sample point in the kth class is represented as probkDegree of membership.
Further, the specific steps of constructing the machine learning prediction model for predicting the road surface collapse probability in the step 5) are as follows:
5-1) calculating the similarity of all sample points according to geological conditions and road construction quality, namely index ind _1 to ind _7 information, and if the sample points with the similarity higher than 0.9 are classified into one type, the sample points are classified into A types, and the total number of the ith (i is 1,2i；
5-2) countingi(i ═ 1, 2., a) ≥ Set _ N1, directly taking index information ind _8 to ind _16 and probability membership of the sample points as input, taking corresponding road surface collapse probability as output, and constructing a machine learning model LM for predicting the i-th road surface collapse probabilityi；
5-3) if counti(i＝1,2,...,A)<Set _ N1 and counti(i ═ 1, 2., a) ≥ Set _ N2, the data Set size can be enlarged by a data enhancement method, the index information ind _8 to ind _16 and the probability membership degree of the expanded sample points are used as input, the corresponding road surface collapse probability is used as output, and a machine learning model LM of predicting the i-th road surface collapse probability is constructedi；
5-4) counti(i＝1,2,...,A)<Set _ N2, the sample data is too little to model, and is considered as noise data.
Further, an urban road surface collapse prevention system based on probability prediction comprises:
the road surface index information set construction module is used for constructing a road surface index information set;
the clustering module is used for processing and clustering index data of the road index information set and dividing n road section samples into Q categories;
the historical data processing module is used for collecting a pavement index information data set in historical pavement collapse accidents and classifying the pavement index information data set according to the Q categories;
the class collapse probability calculation module is used for calculating the road surface collapse probability of each class and the probability membership degree of each sample point;
the prediction model learning module is used for calculating the road surface collapse probability of each category and the probability membership degree of each sample point;
the target prediction module is used for collecting a road index information set of a road section to be evaluated and predicting the road surface collapse probability of the road section;
and the collapse prevention module is used for setting the running road condition range of the safety probability threshold.
Further, the storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the urban road surface collapse prevention method.
Due to the adoption of the technical scheme, the invention has the following advantages:
1. constructing a road surface collapse related index system, and performing dimension reduction treatment on the road surface collapse related index system by adopting a principal component analysis method;
2. the method comprises the steps of (1) realizing classification of samples of different road sections by adopting an unsupervised clustering method, and providing a classification method with adjustable parameters based on density and distance to classify known road surface collapse accidents;
3. defining the occurrence probability of the general road surface collapse of one class, and proposing the membership degree of each acquisition road section sample point in the class to the road surface collapse probability of the class based on the maximum similarity estimation;
4. calculating and re-classifying categories according to the similarity of geological conditions and road construction quality, constructing a machine learning prediction model for each category of road section sample point, and realizing the prediction of the road surface collapse probability of the same category of road sections under different road operation conditions;
5. and setting the collapse probability of the safe road surface, and solving the running state of the safe road through an intelligent optimization algorithm to realize the prevention of the road surface collapse accident.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof.
Drawings
The drawings of the present invention are described below.
FIG. 1 is a schematic flow diagram of the present invention;
fig. 2 is a schematic diagram of a classification process of road surface collapse accidents.
Detailed Description
The invention is further illustrated by the following figures and examples.
The first embodiment is as follows: assume the collected sample data set is as shown in the following table (each index unit is uniform):
table one: collected road section sample set
Table two: sample set for road surface collapse accident
The method comprises the following steps: unsupervised cluster analysis of the sample set:
1) principal component analysis was performed on the sample set of table one by the matlab platform, and the first 10 principal components (cumulative contribution 96.87%) were extracted as shown in the following table:
2) adopting a K-means tool box in matlab to perform non-monitoring clustering on the sample set, and assuming that the clustering category is 4, obtaining the following clustering result:
step two: classifying the known road surface collapse accidents by using a classification method based on distance and density:
1) the four types of clustering center coordinates obtained by adopting a K-means tool box in the matlab platform are as follows:
center1＝(3.48 0.63 -0.25 -0.41 -0.72 0.17 -0.09 0.14 -0.26 -0.25)
center2＝(0.46 -1.24 -0.27 0.36 0.39 -0.49 -0.03 0.04 0.17 0.13)
center3＝(-0.85 0.10 1.62 -0.67 0.13 0.56 0.02 -0.65 0.19 0.05)
center4＝(-2.30 1.36 -0.78 0.29 -0.22 0.16 0.08 0.39 -0.23 -0.08)
2) the main component data obtained by reducing the dimensions of each road surface collapse accident sample point are as follows:
3) the distance between each road surface collapse accident sample point and the centers of various clusters is as follows:
| center1 | center2 | center3 | center4 | |
| B1 | 51.88 | 19.78 | 21.11 | 10.39 |
| B2 | 18.78 | 22.64 | 11.44 | 20.18 |
| B3 | 19.00 | 5.31 | 26.04 | 23.56 |
| B4 | 23.72 | 7.38 | 20.69 | 27.30 |
| B5 | 6.54 | 33.91 | 34.73 | 49.21 |
| B6 | 37.94 | 19.30 | 8.02 | 23.90 |
| B7 | 43.64 | 27.25 | 21.39 | 4.77 |
| B8 | 32.48 | 6.76 | 10.18 | 14.76 |
| B9 | 11.67 | 4.05 | 12.58 | 24.01 |
4) calculating a distance matrix of each road surface collapse accident sample point from each acquisition road section sample point as follows, wherein one column of the matrix B _ Dis represents a straight line distance of one collapse accident sample point from 24 sampling road section sample points:
solving the maximum value and the minimum value of each row of the matrix, namely the effective value range of the initial radius r of the corresponding collapse accident sample point, namely when r is smaller than the minimum value of the row, no other sampling road section sample points exist in the radius r, and when r is larger than the maximum value of the row, all sampling road section sample points are contained in the radius r;
for the collapse accident sample point B1, as can be seen from the first column of the matrix B _ Dis, 2.78< r ≦ 16.26, and assuming that r is 12, the number of samples in each category is shown in the following table three within the range of the coordinate B1 after dimension reduction as the center of circle and the radius of 12:
| categories | 1 | 2 | 3 | 4 |
| Number of | 0 | 3 | 2 | 3 |
Then there is D1＝B_Dis(1，:)＝[51.88 19.78 21.11 10.39]，Num1＝[0 3 2 3]；
5) Will D1，N1After normalization, there are:
D_gui1＝[1 0.23 0.26 0]，Num_gui1＝[0 1 0.67 1]；
assuming that α is 0.6 and β is 0.4, there are:
Attribution1＝α×Num_gui1-β×D_gui1＝[-0.4 0.51 0.3 0.6]
apparently Attribution1The fourth element is the largest, so the collapse accident sample point B1 is classified into the fourth category.
As shown in fig. 1, the present invention mainly comprises seven parts: constructing a road surface collapse index system, carrying out unsupervised cluster analysis on a sample set, classifying known road surface collapse accidents by a classification method based on distance and density, calculating the collapse probability of each class of road surfaces and the probability membership of each sample point, establishing a road surface collapse probability prediction model, predicting the road surface collapse probability of the sample point of the target road section, and regulating and controlling the road operation condition of the sample point of the target road section by an intelligent optimization algorithm;
the first part is to construct a road index information set, where the road index set includes road construction quality information, geological condition information, external environment information, and operating road condition information, and as shown in table one in the first embodiment, the method specifically includes the following steps:
1) the road construction quality information comprises:
road repair rate
SrFor road repair area, SaIs the total area of the road;
road condition index
Representing the weight of the ith road damage type, wherein the road damage type is mainly divided into a crack type, a deformation type and other types; omega represents the severity of road damage, the value range is 0 to 1, and the larger the value is, the more serious the damage is; σ is the damage density;
road surface strength index
a0,a1Is a constant;
structural strength index of pavement
ld,lsRespectively represent the pavement design deflection, the actual measurement represents the deflection, the unit: millimeter;
road age ind — 5;
2) the geological condition information comprises:
the value range of the geological stability ind _6 is 0 to 1;
bearing capacity ind _7 ═ f of foundationk+εbγ(b-3)+εdγ0(d-0.5)，fkRepresenting the standard value of the bearing capacity (kN/m) of the soft soil layer at the bottom surface of the cushion layer2)，εb,εdThe bearing capacity correction coefficients respectively represent the width and the burial depth of the foundation, b represents the width (m) of the foundation, d represents the burial depth (m) of the foundation, and gamma represents the bottom gravity (kN/m) of the foundation3)，γ0Average background Severe on the substrate (kN/m)3)；
3) The external environment information comprises:
daily average precipitation ind _8, daily precipitation variance ind _9, daily average air temperature ind _10, daily air temperature variance ind _11, daily average humidity ind _12, and daily humidity variance ind _ 13;
4) the information of the operating road condition comprises:
the average pedestrian flow rate ind _14, the average vehicle flow rate ind _15 and the daily bearing load ind _ 16;
the second part is to cluster the index data of the road index information set, and divide the n-24 road segment samples into Q-4 categories, as shown in step 1) in the first embodiment, the specific steps are as follows:
1) normalizing data ori _ data of the road surface index information set [ ind _1, ind _2, as, ind _16], and performing dimensionality reduction by a principal component analysis method:
s1, calculating a correlation coefficient matrix corr16×16；
S2, calculating the characteristic value lambda of the correlation coefficient matrixi(i ═ 1, 2.., 16) and a feature vector ηi(i＝1,2,...,16)；
S3, arranging the eigenvalues in descending order, and calculating the accumulated contribution degrees of the first t (t is 1,2, 16) eigenvalues corresponding to the principal component
S4 when cumtWhen the sum is just equal to or greater than 0.95, the characteristic vectors corresponding to the first t-10 principal components are taken to form a conversion matrix tran-eta1,η2,...,ηt]，ηt＝[e1,e2,...,e16]TThe data ori _ data × tran main _ agned is reconstruction data after dimensionality reduction; wherein main _ aggregated [ ind _1, ind _ 2. ], ind _ t [ ]]If the t-th main component data is ind _ t ═ a1t,a2t,...,ant]T，antAn nth sample data representing the t-th principal component;
2) as shown in step one in the embodiment 2), performing unsupervised clustering analysis on the reconstructed data by using a K-means algorithm, and dividing n-24 road segment samples into Q-4 categories:
s1: setting the number Q of the clustering target categories and a minimum threshold value, and randomly selecting Q sample points from the data set data as category cluster centers;
s2: distributing each sample point to the center of the cluster with the closest distance;
s3: calculating the average value of all samples of each cluster, taking the average value as a new cluster center, and calculating the distance between the centroid of each cluster before and after updating;
s4: if the distance between the centers of the front and rear clusters is larger than or equal to the set threshold value, repeating the steps S2-S3; if the distance between the centers of the front and rear clusters is smaller than a set threshold value, stopping calculation to obtain a clustering result;
in the third part, as shown in fig. 2, a road surface index information data set in historical road surface collapse accidents is collected, and a classification sample space is constructed, as shown in the second step in the embodiment, a distance and density-based method is adopted to classify the road surface index information set in the historical road surface collapse accidents in the classification sample space, and the specific steps are as follows:
1) collecting pavement index information data event _ data in historical pavement collapse accidentss×16(see table two in the first embodiment), all the road surface collapse accident index information is reconstructed by the conversion matrix tran to obtain e _ data ═ event _ data × tran ═ main _ Bgred [ -y1,y2,...,yi,...,yt]Wherein y isi＝[y1i,y2i,...,ysi]TAnd s is 9, representing the total number of samples of the road surface collapse accident;
2) constructing a t-dimensional coordinate system by using t as 10 indexes, and constructing a classification sample point space;
3) calculating cluster center coordinates of each cluster in the sample point space, wherein the cluster center coordinates of a kth (k is 1, 2.
Wherein ind _ ikjData representing the ith index of the jth sample in the kth class cluster, and m represents the total number of sample points of the kth class cluster;
the coordinates of the centers of four clusters in the first embodiment are shown in the step 1) in the second embodiment;
4) calculating the distance from each road surface collapse sample point to the centers of various clusters in historical road surface collapse accidents, wherein the h (h is 1,2, s) th road surface collapse sample point is (y)h1,yh2,...,yhi,...,yht) Then the sample point goes to the cluster CenterkThe distance of (d) can be written as:
the distance from the h (h ═ 1, 2.., s) th road surface collapse sample point to the centers of all the cluster types is Dh＝[dh1,dh2,...,dhk,...,dhQ]As shown in step 2) of example one;
5) as shown in step 4) in the first embodiment, a radius r is taken, and how many sample points exist in each cluster within the radius r by taking the h (h is 1,2,.., s) th road surface collapse sample point as a center of a circle is counted, and num is counted as the number of the k-th type sample pointskIf the number of the h-th pavement collapse sample point is not less than the number of the adjacent various sample points within the radius rh＝[numh1,numh2,...numhk,...,numhQ]；
The effective value of the radius r is not more than the maximum value of the linear distance between the h (h is 1, 2.., s) th road surface collapse sample point and each sampling road section sample point, and is not less than the minimum value of the linear distance;
6) as shown in step 5) in the first embodiment, Num is determined based on the principle that the number of samples in a certain category closest to the center of the cluster is the largest within a set radiushAnd DhThe normalization results in Num _ guihAnd D _ guihThe attribution degree is calculated according to the following formula:
Attributionh＝α×Num_guih-β×D_guih＝[ath1,ath2,...,athi,...,athQ]
selection of AttributionhMaximum mean value athxThe subscript x is the category serial number of the h-th pavement collapse sample point;
wherein, α, β ∈ [0,1] is a weight coefficient, and α + β ═ 1 is satisfied, and a specific weight value needs to be determined according to actual data distribution; the more concentrated the data cluster distribution and the larger the class interval, the larger the beta value; if the data cluster distribution is more dispersed and the class interval is smaller, the alpha value is larger;
and the fourth step of calculating the road surface collapse probability of each category and the probability membership degree of each sample point, which comprises the following steps:
1) note that P exists in the kth (k ═ 1, 2.., Q) categorykThe total number of road surface collapse accidents is Nk，εkFor a proportionality constant less than 1, the general probability of collapse for the class of road segments is:
if PkIf not equal to 0, then take Pk0.01, i.e. the probability of collapse for any road segment, guarantees probkIs not 0;
2) calculating the similarity (the value range is 0 to 1) between each non-collapse accident sample point and each collapse accident sample point in the kth category to obtain a similarity matrix as follows:
in matrix bijRepresenting the similarity of the ith collapse accident sample point and the jth non-collapse accident sample point, wherein m represents the total number of the non-collapse accident sample points in the kth category;
3) for sim _ matrixkIs maximized to obtain mu _ kmax＝[bmax1,bmax2,...,bmaxj,bmaxm]，bmaxjThe probability of occurrence of the jth uncollapsed accident sample point in the kth class is represented as probkDegree of membership of;
and a fifth step of respectively constructing a machine learning prediction model for predicting the road surface collapse probability aiming at each category, wherein the specific steps are as follows:
1) calculating the similarity of all sample points according to geological conditions and road construction quality, namely index ind _ 1-ind _7 information, classifying the sample points with the similarity higher than 0.9 into one class, and then classifying the class points into A classes, wherein the total number of the i (i is 1,2i；
2) If counti(i ═ 1, 2., a) ≥ Set _ N1, directly taking index information ind _8 to ind _16 and probability membership of the sample points as input, taking corresponding road surface collapse probability as output, and constructing a machine learning model LM for predicting the i-th road surface collapse probabilityi；
3) If counti(i＝1,2,...,A)<Set _ N1 and counti(i ═ 1, 2., a) ≥ Set _ N2, the data Set size can be enlarged by a data enhancement method, the index information ind _8 to ind _16 and the probability membership degree of the expanded sample points are used as input, the corresponding road surface collapse probability is used as output, and a machine learning model LM of predicting the i-th road surface collapse probability is constructedi；
4) If counti(i＝1,2,...,A)<Set _ N2, if the sample data is too little, modeling analysis cannot be performed, and the sample data can be regarded as noise data;
the sixth part is used for collecting a road index information set of a road section to be evaluated, determining the road type j (j is 1,2,.. multidot.A) of the target road section by adopting a distance and density-based method in the step 3) according to geological conditions and road construction quality, namely index ind _1 to ind _7 information, setting probability membership, and adopting a machine learning prediction model LM obtained in the step 6)jPredicting the road surface collapse probability of the road section;
and a seventh part, setting a safety probability threshold value of the road surface collapse, taking the road running road condition as a regulation object, and obtaining the running road condition range lower than the set safety probability threshold value through an intelligent optimization algorithm.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A method for preventing urban road surface collapse based on probability prediction is characterized by comprising the following specific steps:
1) constructing a pavement index information set, wherein the pavement index set comprises road construction quality information, geological condition information, external environment information and running road condition information;
2) processing and clustering the index data of the road index information set, and dividing n road section samples into Q categories;
3) collecting a pavement index information data set in historical pavement collapse accidents, constructing a classification sample space, collecting pavement index information in the historical pavement collapse accidents in the classification sample space by adopting a distance and density-based method, and classifying according to the Q categories;
4) calculating the road surface collapse probability of each category and the probability membership degree of each sample point;
5) respectively constructing a machine learning prediction model for predicting the road surface collapse probability aiming at each category;
6) collecting a road index information set of a road section to be evaluated, determining the road type j (j is 1,2,.. multidot.A) of the target road section by adopting a distance and density-based method in the step 3) according to geological conditions and road construction quality, setting probability membership, and adopting a machine learning prediction model LM obtained in the step 6)jPredicting the road surface collapse probability of the road section;
7) and setting a safety probability threshold value of the road surface collapse, taking the road running road condition as a regulation object, and obtaining the running road condition range lower than the set safety probability threshold value through an intelligent optimization algorithm.
2. The urban road surface collapse prevention method based on probability prediction as claimed in claim 1, wherein the specific contents of the road construction quality information, the geological condition information, the external environment information and the operating road condition information in step 1) are as follows:
1-1) the road construction quality information includes:
road repair rate
SrFor road repair area, SaIs the total area of the road;
road condition index
pi(i ═ 1,2,3) represents the weight of the ith road damage type, and the road damage types are mainly divided into cracks, deformations and other types; omega represents the severity of road damage, the value range is 0 to 1, and the larger the value is, the more serious the damage is; σ is the damage density;
road surface strength index
a0,a1Is a constant;
structural strength index of pavement
ld,lsRespectively represent the pavement design deflection, the actual measurement represents the deflection, the unit: millimeter;
road age ind — 5;
1-2) the geological condition information comprises:
the geological stability ind _6 ranges from 0 to 1, and the larger the value is, the higher the stability is;
bearing capacity ind _7 ═ f of foundationk+εbγ(b-3)+εdγ0(d-0.5)，fkRepresenting the standard value of the bearing capacity (kN/m) of the soft soil layer at the bottom surface of the cushion layer2)，εb,εdThe bearing capacity correction coefficients respectively represent the width and the burial depth of the foundation, b represents the width (m) of the foundation, d represents the burial depth (m) of the foundation, and gamma represents the bottom gravity (kN/m) of the foundation3)，γ0Average background Severe on the substrate (kN/m)3)；
1-3) the external environment information comprises:
a monthly average precipitation ind _8, a monthly precipitation maximum variance ind _9, a monthly average air temperature ind _10, a monthly air temperature maximum variance ind _11, a monthly average humidity ind _12 and a monthly humidity maximum variance ind _ 13;
1-4) the traffic information includes:
the average pedestrian flow rate ind _14, the average vehicle flow rate ind _15 and the daily bearing load ind _ 16;
3. the urban road surface collapse prevention method based on probability prediction according to claim 2, wherein the specific steps of processing and clustering the index data of the road surface index information set in step 2) are as follows:
2-1) normalizing data ori _ data of the road index information set [ ind _1, ind _2, ·, ind _16], and performing dimensionality reduction by a principal component analysis method:
and 2-2) carrying out unsupervised clustering analysis on the reconstructed data by adopting a K-means algorithm, and dividing n road section samples into Q categories.
4. The urban road surface collapse prevention method based on probability prediction according to claim 3, wherein the specific steps of performing dimension reduction through a principal component analysis method in the step 2-1) are as follows:
2-1-1) calculating a correlation coefficient matrix corr16×16；
2-1-2) calculating characteristic value lambda of correlation coefficient matrixi(i ═ 1, 2.., 16) and a feature vector ηi(i＝1,2,...,16)；
2-1-3) arranging the characteristic values in descending order, and calculating the cumulative contribution degrees of the first t (t is 1,2, 16) characteristic values corresponding to the principal components
2-1-4) when cumtWhen the sum is just equal to or greater than 0.95, the eigenvectors corresponding to the first t principal components are taken to form a transformation matrix tran ═ η1,η2,...,ηt]Wherein etat＝[e1,e2,...,e16]T，data＝ori_data×tran＝[ind_1,ind_2,...,ind_t]Namely the reconstructed data after the dimension reduction; the t-th principal component data is ind _ t ═ a1t,a2t,...,ant]T，antThe nth sample data representing the t-th principal component.
5. The urban road surface collapse prevention method based on probability prediction as claimed in claim 4, wherein the specific steps of adopting K-means algorithm to carry out unsupervised cluster analysis on the reconstructed data in step 2-2) are as follows:
2-2-1) setting the number Q of the clustering target categories and a minimum threshold value, and randomly selecting Q sample points from the data set data as category cluster centers;
2-2-2) assigning each sample point to the cluster center of the closest class;
2-2-3) calculating the average value of all samples of each cluster, taking the average value as a new cluster center, and calculating the distance between the centroid of each cluster before and after updating;
2-2-4) if the distance between the centers of the front and rear clusters is greater than or equal to a set threshold, returning to the step 2-2-2); and if the distance between the centers of the front and rear clusters is smaller than a set threshold value, stopping the calculation and obtaining a clustering result.
6. The urban road surface collapse prevention method based on probability prediction according to claim 5, wherein the concrete steps of clustering the road surface index information sets in historical road surface collapse accidents in Q categories in the classification sample space by adopting a distance and density based method in the step 3) are as follows:
3-1) collecting road surface index information data event _ data in historical road surface collapse accidentss×16Reconstructing all road surface collapse accident index information through a conversion matrix tran to obtain e _ data ═ event _ data × tran [ [ y ═ y1,y2,...,yi,...,yt]Wherein y isi＝[y1i,y2i,...,ysi]TS represents the total number of samples of the road surface collapse accident;
3-2) constructing a t-dimensional coordinate system by using the t indexes, and constructing a classification sample point space;
3-3) calculating cluster center coordinates of each cluster of the sample point space, wherein the cluster center coordinates of the kth (k is 1,2,.., Q)) cluster are as follows:
wherein ind _ ikjRepresents the jth sample in the kth class clusterData of i indexes, wherein m represents the total number of sample points of the kth class cluster;
3-4) calculating the distance from each road surface collapse sample point to the centers of various clusters in the historical road surface collapse accidents, wherein the h (h is 1,2, s) th road surface collapse sample point is (y)h1,yh2,...,yhi,...,yht) Then the sample point goes to the cluster CenterkThe distance of (d) can be written as:
the distance from the h (h ═ 1, 2.., s) th road surface collapse sample point to the centers of all the cluster types is Dh＝[dh1,dh2,...,dhk,...,dhQ]；
Counting the number of sample points in each cluster in the radius r by taking the h (h is 1,2,.. s) th pavement collapse sample point as the center of a circle, and counting the num number of the k type sample pointskIf the number of the h-th pavement collapse sample point is not less than the number of the adjacent various sample points within the radius rh＝[numh1,numh2,...numhk,...,numhQ]；
The effective value of the radius r is not more than the maximum value of the linear distance between the h (h is 1, 2.., s) th road surface collapse sample point and each sampling road section sample point, and is not less than the minimum value of the linear distance;
based on the principle that the number of samples in a certain category is the largest when the center of the cluster is the nearest and within a set radius, the Num is obtainedhAnd DhThe normalization results in Num _ guihAnd D _ guihThe attribution degree is calculated according to the following formula:
Attributionh＝α×Num_guih-β×D_guih＝[ath1,ath2,...,athi,...,athQ]
wherein, α, β ∈ [0,1] is a weight coefficient, and α + β ═ 1 is satisfied, and a specific weight value needs to be determined according to actual data distribution; the more concentrated the data cluster distribution and the larger the class interval, the larger the beta value; if the data cluster distribution is more dispersed and the class interval is smaller, the alpha value is larger;
selection of AttributionhMaximum mean value athxAnd the subscript x is the category serial number of the h-th road surface collapse sample point.
7. The urban road surface collapse prevention method based on probability prediction according to claim 6, wherein the specific steps of calculating the road surface collapse probability of each category and the probability membership degree of each sample point in step 4) are as follows:
4-1) note that P is present in the kth (k ═ 1,2kThe total number of road surface collapse accidents is Nk，εkFor a proportionality constant less than 1, the general probability of collapse for the class of road segments is:
if PkIf not equal to 0, then take Pk0.01, i.e. the probability of collapse for any road segment, guarantees probkIs not 0;
4-2) calculating the similarity between each non-collapse accident sample point and each collapse accident sample point in the kth category, and obtaining a similarity matrix as follows:
in matrix bijRepresenting the similarity of the ith collapse accident sample point and the jth non-collapse accident sample point, wherein m represents the total number of the non-collapse accident sample points in the kth category;
4-3) pairs sim _ matrixkIs maximized to obtain mu _ kmax＝[bmax1,bmax2,...,bmaxj,bmaxm]，bmaxjThe probability of occurrence of the jth uncollapsed accident sample point in the kth class is represented as probkDegree of membership.
8. The urban road surface collapse prevention method based on probability prediction as claimed in claim 7, wherein the specific steps of constructing the machine learning prediction model for predicting the road surface collapse probability in step 5) are as follows:
5-1) calculating the similarity of all sample points according to geological conditions and road construction quality, namely index ind _1 to ind _7 information, and if the sample points with the similarity higher than 0.9 are classified into one type, the sample points are classified into A types, and the total number of the ith (i is 1,2i；
5-2) countingi(i ═ 1, 2., a) ≥ Set _ N1, directly taking index information ind _8 to ind _16 and probability membership of the sample points as input, taking corresponding road surface collapse probability as output, and constructing a machine learning model LM for predicting the i-th road surface collapse probabilityi；
5-3) if counti(i＝1,2,...,A)<Set _ N1 and counti(i ═ 1, 2., a) ≥ Set _ N2, the data Set size can be enlarged by a data enhancement method, the index information ind _8 to ind _16 and the probability membership degree of the expanded sample points are used as input, the corresponding road surface collapse probability is used as output, and a machine learning model LM of predicting the i-th road surface collapse probability is constructedi；
5-4) counti(i＝1,2,...,A)<Set _ N2, the sample data is too little to model, and is considered as noise data.
9. An urban road surface collapse prevention system based on probability prediction, characterized in that the system comprises:
the road surface index information set construction module is used for constructing a road surface index information set;
the clustering module is used for processing and clustering index data of the road index information set and dividing n road section samples into Q categories;
the historical data processing module is used for collecting a pavement index information data set in historical pavement collapse accidents and classifying the pavement index information data set according to the Q categories;
the class collapse probability calculation module is used for calculating the road surface collapse probability of each class and the probability membership degree of each sample point;
the prediction model learning module is used for calculating the road surface collapse probability of each category and the probability membership degree of each sample point;
the target prediction module is used for collecting a road index information set of a road section to be evaluated and predicting the road surface collapse probability of the road section;
and the collapse prevention module is used for setting the running road condition range of the safety probability threshold.
10. A storage medium storing instructions adapted to be loaded by a processor to perform the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110539246.6A CN113128789B (en) | 2021-05-18 | 2021-05-18 | Urban pavement collapse prevention method, system and storage medium based on probability prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110539246.6A CN113128789B (en) | 2021-05-18 | 2021-05-18 | Urban pavement collapse prevention method, system and storage medium based on probability prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113128789A true CN113128789A (en) | 2021-07-16 |
| CN113128789B CN113128789B (en) | 2023-08-08 |
Family
ID=76782143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110539246.6A Active CN113128789B (en) | 2021-05-18 | 2021-05-18 | Urban pavement collapse prevention method, system and storage medium based on probability prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128789B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114937359A (en) * | 2022-05-20 | 2022-08-23 | 四川大学 | Method, system, terminal and medium for positioning and analyzing cascade fault of traffic infrastructure |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102731022A (en) * | 2012-06-27 | 2012-10-17 | 哈尔滨工业大学 | Asphalt road surface freezing damage resistance protection material and preparation method thereof |
| CN106830767A (en) * | 2017-02-17 | 2017-06-13 | 武汉理工大学 | A kind of bituminous paving check crack punishment regeneration sealing material and preparation method thereof |
| CN110232414A (en) * | 2019-06-11 | 2019-09-13 | 西北工业大学 | Density peaks clustering algorithm based on k nearest neighbor and shared nearest neighbor |
| CN111598148A (en) * | 2020-04-29 | 2020-08-28 | 中国电子科技集团公司第二十八研究所 | Capacity evaluation method and device based on historical capacity similarity characteristics |
-
2021
- 2021-05-18 CN CN202110539246.6A patent/CN113128789B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102731022A (en) * | 2012-06-27 | 2012-10-17 | 哈尔滨工业大学 | Asphalt road surface freezing damage resistance protection material and preparation method thereof |
| CN106830767A (en) * | 2017-02-17 | 2017-06-13 | 武汉理工大学 | A kind of bituminous paving check crack punishment regeneration sealing material and preparation method thereof |
| CN110232414A (en) * | 2019-06-11 | 2019-09-13 | 西北工业大学 | Density peaks clustering algorithm based on k nearest neighbor and shared nearest neighbor |
| CN111598148A (en) * | 2020-04-29 | 2020-08-28 | 中国电子科技集团公司第二十八研究所 | Capacity evaluation method and device based on historical capacity similarity characteristics |
Non-Patent Citations (2)
| Title |
|---|
| 付建村;孟宪秋;庄传仪;王仁坤;: "系统聚类方法在路面寿命周期费用分析中的应用", 中外公路, no. 02, pages 99 - 103 * |
| 施彦;凌天清;崔立龙;葛豪;陈巧巧;: "沥青路面预防性养护评价标准及决策优化研究", 公路交通科技, no. 10, pages 25 - 34 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114937359A (en) * | 2022-05-20 | 2022-08-23 | 四川大学 | Method, system, terminal and medium for positioning and analyzing cascade fault of traffic infrastructure |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113128789B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108550077A (en) | A kind of individual credit risk appraisal procedure and assessment system towards extensive non-equilibrium collage-credit data | |
| CN108428024B (en) | Emergency resource allocation decision optimization method for irregular emergency under uncertain information | |
| CN103020582A (en) | Method for computer to identify vehicle type by video image | |
| CN107025468A (en) | Highway congestion recognition methods based on PCA GA SVM algorithms | |
| Bamakan et al. | A novel feature selection method based on an integrated data envelopment analysis and entropy model | |
| CN110363230A (en) | Stacking integrated sewage handling failure diagnostic method based on weighting base classifier | |
| CN116109458A (en) | Reservoir flood discharge gate scheduling method, system, storage medium and computing equipment | |
| CN113128789A (en) | Urban road surface collapse prevention method and system based on probability prediction and storage medium | |
| CN114861719A (en) | High-speed train bearing fault diagnosis method based on ensemble learning | |
| Wang et al. | The detection of network intrusion based on improved adaboost algorithm | |
| CN109842614B (en) | Network intrusion detection method based on data mining | |
| Zhang et al. | A fuzzy weighted c-means classification method for traffic flow state division | |
| CN110619422A (en) | Intelligent station passenger flow condition prediction method and system | |
| KR101085066B1 (en) | An Associative Classification Method for detecting useful knowledge from huge multi-attributes dataset | |
| CN111222570B (en) | Ensemble learning classification method based on difference privacy | |
| CN115049136A (en) | Transformer load prediction method | |
| Ba-Karait et al. | Handwritten digits recognition using particle swarm optimization | |
| CN110097126B (en) | Method for checking important personnel and house missing registration based on DBSCAN clustering algorithm | |
| CN113723660A (en) | Specific behavior type prediction method and system based on DNN-LSTM fusion model | |
| Benyao et al. | Elevator Traffic Pattern Recognition Based on Density Peak Clustering | |
| CN117556339B (en) | Network illegal behavior risk and risk level assessment method | |
| CN117829370B (en) | Traffic accident severity prediction method, system and computer equipment | |
| CN117056795A (en) | Dermatitis classification method based on deep T-S persistence rule optimization | |
| WO2022083047A1 (en) | Method and apparatus for obtaining cell classification model, and computer readable storage medium | |
| Pota et al. | Insights into interpretability of neuro-fuzzy systems |
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 |