CN112241808A - Road surface technical condition prediction method, device, electronic equipment and storage medium - Google Patents
Road surface technical condition prediction method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112241808A CN112241808A CN202011041591.9A CN202011041591A CN112241808A CN 112241808 A CN112241808 A CN 112241808A CN 202011041591 A CN202011041591 A CN 202011041591A CN 112241808 A CN112241808 A CN 112241808A
- Authority
- CN
- China
- Prior art keywords
- road surface
- data
- technical condition
- sample
- prediction
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000012423 maintenance Methods 0.000 claims abstract description 92
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 59
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 11
- 238000001514 detection method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000010426 asphalt Substances 0.000 description 2
- 239000004568 cement Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000009191 jumping Effects 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
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
Abstract
The embodiment of the invention provides a method and a device for predicting a technical condition of a road surface, electronic equipment and a storage medium, wherein the method comprises the steps of acquiring road surface technical grade data, road surface type data and road surface maintenance data related to the technical condition of the road surface; inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition; and determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface. The input data of the embodiment of the invention comprises pavement maintenance data, so that the intervention of maintenance factors is considered by the prediction model; meanwhile, the prediction model is trained based on a machine learning algorithm, and parameters of the prediction model can be automatically corrected and optimized, so that the prediction efficiency and the prediction precision are greatly improved, and the prediction score output by the prediction model can more accurately reflect the technical condition of the road surface.
Description
Technical Field
The present invention relates to the technical field of pavement performance prediction, and in particular, to a method and an apparatus for predicting a pavement technical condition, an electronic device, and a storage medium.
Background
The road surface performance is gradually reduced along with the time lapse after the vehicle is communicated, however, the highway in China is mostly a semi-rigid road surface, the fatigue life of the road surface is short, and the maintenance time and the maintenance strategy are accurately mastered, so that the maintenance work has more economic and social benefits. Scholars at home and abroad begin to comprehensively evaluate and explore decay laws of pavement service performance in order to help highway management departments to optimally allocate maintenance budgets and determine the optimal maintenance strategy, but the targeted pavement performance prediction modeling research is still insufficient. The performance prediction modeling of the prior road surface technical condition is based on a grey theory, the adoption of machine learning is lacked, and the problem of the change of the road surface performance under the condition of maintenance intervention is not considered.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present invention provide a method and an apparatus for predicting a road surface technical condition, an electronic device, and a storage medium.
In a first aspect, an embodiment of the present invention provides a road surface technical condition prediction method, including:
acquiring pavement technical grade data, pavement type data and pavement maintenance data related to pavement technical conditions;
inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition;
determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface;
the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
Further, still include:
preprocessing the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition;
the preprocessing comprises the steps of utilizing a neural network to carry out abnormal value restoration on road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions to obtain a reliable data set corresponding to the road surface technical grade data, the road surface type data and the road surface maintenance data;
and carrying out normalization processing on the reliable data set.
Further, the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by using, as input data, road surface technical grade sample data, road surface type sample data, and road surface maintenance sample data of a sample road surface, which are related to a road surface technical condition, and by using, as output data, a prediction score corresponding to the road surface technical condition of the sample road surface, and specifically includes:
acquiring pavement technical grade sample data, pavement type sample data and pavement maintenance sample data of a sample pavement, which are related to the pavement technical condition;
dividing pavement technical grade sample data, pavement type sample data and pavement maintenance sample data of the sample pavement, which are related to the pavement technical condition, into an initial training data set and a test data set according to a preset proportion to serve as sample input data, training a pavement technical condition prediction model by adopting a strategy of non-overlapping change updating of the initial training data set and the test data set according to a first relation model, and determining the pavement technical condition prediction model by adopting a prediction score corresponding to the pavement technical condition of the sample pavement as output data until the prediction score corresponding to the pavement technical condition of the sample pavement meets a preset training end condition;
wherein the first relationship model comprises:
wherein the content of the first and second substances,
representing a training sample xiTraining error of，Ω(fk) Regular terms representing the kth tree, K representing the total number of trees, fkA (k) th tree is shown,
representing a training sample xiPredicted result of (1), xiRepresents training samples, Obj (θ) represents a loss function, n represents the total number of training samples, i represents the ith sample, y representsiRepresenting a training sample xiThe true value of (d).
Further, the normalizing the reliable data set specifically includes:
according to a second relation model, carrying out normalization processing on the reliable data set;
wherein the second relational model comprises:
wherein x is*Representing the processed value, x representing the value to be processed, min being the minimum value of the value to be processed, and max being the maximum value of the value to be processed.
Further, still include:
according to the third correlation model, estimating the prediction effect of the road surface technical condition prediction model by adopting a complex correlation coefficient, a root mean square error and an average absolute value error;
wherein the third relationship model comprises:
wherein R is2Denotes the complex correlation coefficient, RMSE denotes the root mean square error, MAE denotes the mean absolute error, i denotes the ith sample, fiDenotes the predicted value of the i-th sample, yiThe true value of the ith sample is represented,
represents the average of all real values and N represents the total number of samples.
Further, still include:
the road surface technical condition prediction result is a road surface technical condition prediction result of a PQI index;
according to a fourth relational model, calculating a road surface technical condition prediction result of the PQI index;
the fourth relational model includes:
PQI＝ωPCIPCI+ωRQIRQI+ωRDIRDI+ωPBIPBI+ωPWIPWI+ωSRISRI
wherein PQI represents the road surface service performance condition, PCI represents the road surface damage condition, and omegaPCIDenotes the weight of PCI in PQI, RQI denotes the road surface running quality index, omegaRQIRepresents the weight of RQI in PQI, and RDI represents the road rut depth index, omegaRDIRepresents the weight of RDI in PQI, PBI represents the road jump index, omegaPBIRepresents the weight of PBI in PQI, PWI represents the road wear index, ωPWIRepresents the weight of PWI in PQI, SRI represents the road skid resistance index, omegaSRIRepresents the weight of SRI in PQI.
In a second aspect, an embodiment of the present invention provides a road surface technical condition prediction apparatus, including:
the acquisition module is used for acquiring road surface technical grade data, road surface type data and road surface maintenance data related to the road surface technical condition;
the prediction module is used for inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition;
the determining module is used for determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface;
the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
Further, the apparatus further comprises:
the data preprocessing module is used for preprocessing the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition;
the preprocessing comprises the steps of utilizing a neural network to carry out abnormal value restoration on road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions to obtain a reliable data set corresponding to the road surface technical grade data, the road surface type data and the road surface maintenance data;
and carrying out normalization processing on the reliable data set.
In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the road surface technical condition prediction method according to the first aspect when executing the program.
In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the road surface technical condition prediction method according to the first aspect.
As can be seen from the foregoing technical solutions, the method, the apparatus, the electronic device, and the storage medium for predicting a technical condition of a road surface according to the embodiments of the present invention obtain technical grade data, type data, and maintenance data of the road surface, which are related to the technical condition of the road surface; inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition; determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface; the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data. The input data of the embodiment of the invention comprises pavement maintenance data, so that the intervention of maintenance factors is considered by the prediction model; meanwhile, the prediction model is trained based on a machine learning algorithm, and parameters of the prediction model can be automatically corrected and optimized, so that the prediction efficiency and the prediction precision are greatly improved, and the prediction score output by the prediction model can more accurately reflect the technical condition of the road surface.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a road surface technical condition prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a prediction technique route according to another embodiment of the present invention;
FIG. 3 is a diagram illustrating predicted results using PQI as an example according to another embodiment of the present invention;
FIG. 4 is a diagram illustrating predicted results using PQI as an example according to another embodiment of the present invention;
fig. 5 is a schematic diagram of a prediction result of the region a by taking PQI as an example according to another embodiment of the present invention;
fig. 6 is a schematic diagram illustrating a B region prediction result according to another embodiment of the present invention, taking PQI as an example;
fig. 7 is a schematic diagram of a prediction result of a C region using PQI as an example according to another embodiment of the present invention;
fig. 8 is a diagram illustrating a D region prediction result according to another embodiment of the present invention, taking PQI as an example;
fig. 9 is a schematic diagram of the prediction result of the E region using PQI as an example according to another embodiment of the present invention;
FIG. 10 is a schematic diagram of road surface performance PQI prediction performance of five major economic zones according to another embodiment of the present invention;
fig. 11 is a schematic structural diagram of a road surface technical condition prediction apparatus according to an embodiment of the present invention;
fig. 12 is a schematic physical structure diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. The method for detecting train collision according to the present invention will be explained and illustrated in detail by specific embodiments.
Fig. 1 is a schematic flow chart of a road surface technical condition prediction method according to an embodiment of the present invention; as shown in fig. 1, the method includes:
step 101: road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions are acquired.
In this step, road surface technical grade data, road surface type data, and road surface maintenance data relating to the technical condition of the road surface are acquired through actual measurement and history data. If the target area is M province, wherein the road technical grade data refers to the road grades of the M province road in the area, such as a first-level road, a second-level road, a third-level road and a fourth-level road, which are divided according to the technical grade standard; the pavement type data refers to which pavement type the pavement of the M province in the area belongs to, such as a cement pavement and an asphalt pavement; the road surface maintenance data refers to maintenance times and maintenance levels of the road surfaces of the M provinces in the area, wherein the maintenance levels are set to give scores according to the time from the maintenance year to the year to be predicted (namely the score of the maintenance level is the last maintenance year in the data-the detection initial year), and the calculation of the maintenance levels needs to be specifically analyzed according to the actual situation of the obtained original data. For example, if the acquired detection data starts from 2012, and the road segment is maintained in 2013 and 2015, respectively, the number of maintenance times is 2, and the years to be measured are unified into one year in the same batch of data, for example, 2015, and the maintenance level is 3 (2015-2012); if the road section is maintained in 2018, the highest maintenance level is 6 when data of 2019 are predicted (2018 and 2012).
In this step, it should be noted that, the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition obtain an original data set, and a part of data in this original data set is literal data, and the literal data needs to be digitally converted (i.e. quantized), for example, the conversion method is as shown in table 1:
TABLE 1 index conversion Table
Step 102: inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition; the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
In this step, a data set consisting of road surface technical grade data, road surface type data and road surface maintenance data may be input to a pre-trained road surface technical prediction model, where the data set includes quantized data and data that is not required to be quantized in an original data set, and the data may be directly input to the prediction model.
In this step, it is to be noted that, for the road technical condition prediction model trained in advance, the training model is updated by using a training set and a test set without overlapping change and is verified one by a multi-parameter collocation scheme, the road technical condition prediction model is adjusted and optimized according to an optimal precision solution to obtain a prediction model with high prediction precision, the road technical condition prediction model trained in advance is used for predicting the road technical condition, a prediction score corresponding to the road technical condition in the target area is used as output data, a new tree is added by fixing a learned part to compensate for error improvement precision, the trend of the road technical condition changing along with time is well restored, a road technical condition prediction result is obtained, and the prediction result has high accuracy.
Step 103: and determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface.
In this step, the technical condition of the road surface can be determined according to the prediction score corresponding to the technical condition of the road surface, that is, the performance of the road surface can be obtained according to the technical condition of the road surface, so that the change rule of the service performance of the road surface can be comprehensively evaluated and explored.
In this embodiment, it should be noted that, if a user wants to predict the road surface technical condition of a certain road segment, the data set related to the road surface technical condition of the corresponding road segment may be collected; if the user wants to predict the road surface technical condition of a certain area, the road surface technical condition prediction result of the corresponding area can be obtained by collecting the data sets of all road sections in the corresponding area, wherein the data sets are related to the road surface technical condition, and each road section label is predicted.
In this embodiment, referring to fig. 2, for example, the method includes collecting road surface data of the national province of the highway of the main line of the sichuan province, including data acquisition and collection of the cic road condition detection vehicle data and maintenance history data, establishing a detection and maintenance data set, preprocessing the detection and maintenance data set, generally including data restoration, feature screening and data normalization, inputting processed reliable data into a trained machine learning model, where the machine learning model is calibrated and optimized through one or more of an XGBoost algorithm, a random forest algorithm, a LightGBM algorithm, and network search cross validation, and the machine learning model predicts and outputs a technical condition index decay prediction result of the sichuan province road surface according to the input data.
Therefore, the road surface technical condition prediction method provided by the embodiment of the invention obtains the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition; inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition; according to the prediction value corresponding to the technical road condition, the technical road condition is determined, and because the input data comprises road maintenance data, the prediction model considers the intervention of maintenance factors; meanwhile, the prediction model is trained based on a machine learning algorithm, and parameters of the prediction model can be automatically corrected and optimized (especially suitable for network-level data), so that the prediction efficiency and the prediction precision are greatly improved, and the prediction score output by the prediction model can more accurately reflect the technical condition of the road surface; and further, the method provides reference for a highway maintenance department, assists the maintenance department to accurately master maintenance opportunities, and makes a more targeted maintenance strategy, so that the maintenance work has more economic and social benefits.
On the basis of the above embodiment, in this embodiment, the method further includes:
preprocessing the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition;
the preprocessing comprises the steps of utilizing a neural network to carry out abnormal value restoration on road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions to obtain a reliable data set corresponding to the road surface technical grade data, the road surface type data and the road surface maintenance data;
and carrying out normalization processing on the reliable data set.
In this embodiment, it should be noted that the preprocessing is performed on the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition, and the preprocessing includes cleaning the data, repairing abnormal values of the data by using a neural network, and finally performing a normalization processing operation on the data to obtain a reliable data set.
In this embodiment, it should be noted that the neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm. The calculation process of the BP neural network consists of a forward calculation process and a backward calculation process. And in the forward propagation process, the input mode is processed layer by layer from the input layer through the hidden unit layer and is transferred to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output can not be obtained at the output layer, the reverse propagation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal.
In this embodiment, for example, referring to fig. 3, it can be seen from fig. 3 that the value of PQI suddenly decays from 97.6 to 43.8, which does not conform to the normal decay rule of the road surface, and is presumed to be an abnormal value, and the abnormal value is repaired by using a BP neural network.
According to the technical scheme, the pavement technical condition prediction method provided by the embodiment of the invention is used for preprocessing the pavement technical grade data, the pavement type data and the pavement maintenance data related to the pavement technical condition to obtain a reliable data set, so that a more accurate pavement technical condition exponential decay prediction result is obtained.
On the basis of the foregoing embodiment, in this embodiment, the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by using, as input data, road surface technical grade sample data, road surface type sample data, and road surface maintenance sample data of a sample road surface, which are related to a road surface technical condition, and by using, as output data, a prediction score corresponding to the road surface technical condition of the sample road surface, and specifically includes:
acquiring pavement technical grade sample data, pavement type sample data and pavement maintenance sample data of a sample pavement, which are related to the pavement technical condition;
dividing pavement technical grade sample data, pavement type sample data and pavement maintenance sample data of the sample pavement, which are related to the pavement technical condition, into an initial training data set and a test data set according to a preset proportion to serve as sample input data, training a pavement technical condition prediction model by adopting a strategy of non-overlapping change updating of the initial training data set and the test data set according to a first relation model, and determining the pavement technical condition prediction model by adopting a prediction score corresponding to the pavement technical condition of the sample pavement as output data until the prediction score corresponding to the pavement technical condition of the sample pavement meets a preset training end condition;
wherein the first relationship model comprises:
wherein the content of the first and second substances,
representing a training sample xiTraining error of (d), omega (f)k) Regular terms representing the kth tree, K representing the total number of trees, fkDenotes the k-th particleThe number of the trees is such that,
representing a training sample xiPredicted result of (1), xiRepresents training samples, Obj (θ) represents a loss function, n represents the total number of training samples, i represents the ith sample, y representsiRepresenting a training sample xiThe true value of (d).
In this embodiment, it should be noted that the principle of the road technical condition prediction model training is to fix data features of a first regression tree that have been learned through a first iteration, and add a new regression tree model to compensate for error improvement accuracy, where the tree model refers to a single decision tree model in machine learning as a base learner. Specifically, an original training set is input into the 1 st regression tree to generate a weak learning model, after training errors generated by the weak learning model on training set data are collected, a new error data set is formed to serve as new training data, the new error data set is input into the next regression tree to be trained, and a new error data set is generated, namely, the previous output of a plurality of regression trees is connected (in series) with the input of the next tree, and the process is circulated until a loss function Obj is smaller than an expected threshold value. The loss function is:
wherein the content of the first and second substances,
for a pavement index sample x in the original dataiTraining error of (d), omega (f)k) Representing some norm constraint for the kth tree, where the regularization constraint process can be implemented with either the L1 norm or the L2 norm; the regression tree is used for solving the regression problem, each leaf of the regression tree outputs a predicted value, and the final result is generally the average value of the output of elements in a training set contained in the leaf; the pavement technical condition index prediction model formula is
Where K represents the total number of trees, fkRepresentsThe kth tree, and
representative sample xiThe predicted result of (1).
In this embodiment, it should be noted that the loss function training error and the complexity (regular term) of the prediction model are two parts, and the expression is
Representing a training sample xiTraining error of (d), omega (f)k) For the regularization term of the kth tree, the following demonstration optimizes and solves the prediction model to find f (x), the algorithm adopted is to add each tree to the model one by one, and the whole algorithm process is as follows until the kth tree is stopped: initializing, adding a first tree to the prediction model, adding a second tree to the prediction model, and so on until the t-th tree is added to the prediction model:
therein is provided
Represents the pair after the t-th cycle
The resulting score, so the objective function becomes:
complexity of training model is ft(x)＝wq(x),w∈RT,q:Rd→ {1,2, … T }, q (x) denotes the position of the sample x in the tree, w is the leaf weight sequence, T denotes the treeThe number of leaf nodes, so the complexity can be expressed as
The number of leaves is represented by gamma, and the L2 modulus of w is squared
And (4) showing.
In this embodiment, data related to road surface technical conditions in all regions in province F are summarized, data road sections in different years in a data set are different in number, manual screening can be performed due to the fact that program analysis decay rules cannot be directly input, data fusion is performed by taking road section names as marks, road surface technical grades and road surface type indexes are quantized, and road surface technical grade data and road surface type data are obtained. And then, taking 70% of historical data sets of different years as initial training data sets, taking 30% of the historical data sets as test data sets, adopting a non-overlapping transformation updating and parameter collocation scheme for verifying the initial training data sets and the test data sets one by one, specifically referring to fig. 4, inputting test historical data of a certain year, outputting a prediction result of a prediction value by a prediction model, and comparing and analyzing the prediction value and a real value of the next year to obtain whether the prediction value and the real value are close or not and whether the exponential decay trend of the road surface changing along with time can be well restored or not.
As can be seen from the above technical solutions, embodiments of the present invention provide a road technical condition prediction method, in which a pre-trained road technical condition prediction model is established, the road technical condition prediction model is trained by using a non-overlapping change updating strategy of the initial training data set and the test data set until a preset training end condition is met, the trained road technical condition prediction model is obtained, and a prediction result is output, and the road technical condition prediction model obtains a prediction model with higher prediction accuracy by adjusting and optimizing model parameters.
On the basis of the foregoing embodiment, in this embodiment, the performing normalization processing on the reliable data set specifically includes:
according to a second relation model, carrying out normalization processing on the reliable data set;
wherein the second relational model comprises:
wherein x is*Representing the processed value, x representing the value to be processed, min being the minimum value of the value to be processed, and max being the maximum value of the value to be processed.
In this embodiment, it should be noted that, because different characteristic variables have different measurement units, the value range of each characteristic variable is different greatly, and the original data value is directly used for analysis, the data with a large value will cover the influence of the data with a small value on the target variable, so that, to avoid the phenomenon of model overfitting caused by the data distribution difference of different characteristic variables, the original data is normalized, and the data is mapped into the range of 0 to 1 by the method, and the formula is as follows:
wherein x is*Representing the processed value, x representing the value to be processed, min being the minimum value of the value to be processed, and max being the maximum value of the value to be processed.
On the basis of the above embodiment, in this embodiment, the method further includes:
according to the third correlation model, estimating the prediction effect of the road surface technical condition prediction model by adopting a complex correlation coefficient, a root mean square error and an average absolute value error;
wherein the third relationship model comprises:
wherein R is2Denotes the complex correlation coefficient, RMSE denotes the root mean square error, MAE denotes the mean absolute error, i denotes the ith sample, fiDenotes the predicted value of the i-th sample, yiThe true value of the ith sample is represented,
represents the average of all real values and N represents the total number of samples.
In this embodiment, the prediction effect of the trained road surface technical condition prediction model is evaluated by using a complex correlation coefficient, a root mean square error and an average absolute value error, R2Denotes the complex correlation coefficient, rmse (root Mean Square error) denotes the root Mean Square error, and mae (Mean Absolute error) denotes the Mean Absolute error.
For better understanding of the present embodiment, for example:
the method comprises the steps of carrying out regional detection on each economic area of the province W, wherein the province W has five economic areas which are an area A, an area B, an area C, an area D and an area E respectively, the economic areas are different levels and distinctive regional economic units formed on the basis of labor regional division, each economic area has different development targets and strategic positioning, and different detection and maintenance plans are presented on the basis of highway pavement foundation construction, so that research precision is distinguished, and a machine learning model is established mainly by dividing province data and five economic area data to complete pavement performance prediction and analysis of the province A. Considering the respective road surface detection data of the five zones, a prediction model is established zone by zone, so that the prediction result is more fit with the actual road surface condition of each zone, and the road surface performance PQI prediction performance of five economic zones is shown in Table 2:
TABLE 2 road Performance PQI prediction Performance for five major economic zones
| Economic zone | RMSE | MAE | R2 |
| Region A | 5.195 | 3.117 | 0.818 |
| Region B | 4.401 | 2.651 | 0.702 |
| C region | 4.455 | 2.795 | 0.666 |
| D region | 4.589 | 3.034 | 0.637 |
| Region E | 4.153 | 1.638 | 0.777 |
Fig. 5 to 9 are a schematic diagram of a prediction result of an a region (fig. 5) taking PQI as an example, a schematic diagram of a prediction result of a B region (fig. 6) taking PQI as an example, a schematic diagram of a prediction result of a C region (fig. 7) taking PQI as an example, a schematic diagram of a prediction result of a D region (fig. 8) taking PQI as an example, a schematic diagram of a prediction result of an E region (fig. 9) taking PQI as an example, and fig. 10 is a schematic diagram of road surface performance PQI prediction performance of five major economic zones obtained according to fig. 5 to 9, respectively. From the combination of FIGS. 5 to 10, it can be seen from the prediction results that A, B and R of E region2Are all higher, wherein R of A region2The prediction result is more than 0.8, and the prediction result is more accurate; here, it should be noted that, in general, R is2Above 0.8 this prediction can be used, but this also requires a distinction based on different data, such as R for aggregate particles2This prediction can also be used at 0.76; network R is not basically adjusted for predicting LTPP North American pavement performance2The content of the compound (B) is 0.9 or more, and the effect is considered to be better as approaching 1, and the effect is considered to be unusable if the content is less than 0.5.
On the basis of the above embodiment, in this embodiment, the method further includes:
the road surface technical condition prediction result is a road surface technical condition prediction result of the PQI index;
according to a fourth relational model, calculating a road surface technical condition prediction result of the PQI index;
the fourth relational model includes:
PQI＝ωPCIPCI+ωRQIRQI+ωRDIRDI+ωPBIPBI+ωPWIPWI+ωSRISRI
wherein PQI represents the road surface service performance condition, PCI represents the road surface damage condition, and omegaPCIDenotes the weight of PCI in PQI, RQI denotes the road surface running quality index, omegaRQIRepresents the weight of RQI in PQI, and RDI represents the road rut depth index, omegaRDIRepresenting the weight of RDI in PQI, PBI TableIndex, omega, for indicating a road jumpPBIRepresents the weight of PBI in PQI, PWI represents the road wear index, ωPWIRepresents the weight of PWI in PQI, SRI represents the road skid resistance index, omegaSRIRepresents the weight of SRI in PQI.
In this embodiment, it should be noted that PQI represents the service performance of the road surface, which is a comprehensive index for road surface detection and investigation specified in "evaluation standard of road technical conditions", and includes various contents such as road surface damage, road surface flatness, road surface rutting, road surface vehicle jumping, road surface abrasion, road surface skid resistance, and road surface structural strength (the contents of cement road surface and asphalt road surface are different). The weights in the formula are defined according to the evaluation criteria of the road technical conditions, for example, as shown in table 3:
TABLE 3 PQI subentry index weights
Note: the road surface anti-skid performance index SRI and the road surface abrasion index PWI are one of the two indexes.
Fig. 11 is a schematic structural diagram of a road surface technical condition prediction apparatus according to an embodiment of the present invention, and as shown in fig. 11, the apparatus includes: an acquisition module 201, a prediction module 202, and a determination module 203, wherein:
the acquisition module 201 is configured to acquire road surface technical grade data, road surface type data, and road surface maintenance data related to a road surface technical condition;
the prediction module 202 is configured to input the road surface technical grade data, the road surface type data, and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition;
the determining module 203 is configured to determine the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface;
the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
The road surface technical condition prediction device provided by the embodiment of the invention can be specifically used for executing the road surface technical condition prediction method of the embodiment, the technical principle and the beneficial effect are similar, and specific reference can be made to the embodiment, and details are not repeated here.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device, and referring to fig. 12, the electronic device specifically includes the following contents: a processor 301, a communication interface 303, a memory 302, and a communication bus 304;
the processor 301, the communication interface 303 and the memory 302 complete mutual communication through the bus 304; the communication interface 303 is used for realizing information transmission between related devices such as modeling software, an intelligent manufacturing equipment module library and the like; the process 301 is for calling a computer program in the memory 302, and the processor when executing the computer program realizes the methods provided by the above method embodiments, for example, the processor when executing the computer program realizes the following steps: acquiring pavement technical grade data, pavement type data and pavement maintenance data related to pavement technical conditions; inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition; determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface; the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
Based on the same inventive concept, yet another embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, is implemented to perform the methods provided by the above-mentioned method embodiments, for example, acquiring road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions; inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition; determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface; the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
In addition, in the present invention, terms such as "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Moreover, in the present invention, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Furthermore, in the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A road surface technical condition prediction method is characterized by comprising the following steps:
acquiring pavement technical grade data, pavement type data and pavement maintenance data related to pavement technical conditions;
inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition;
determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface;
the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
2. A road surface technical condition prediction method according to claim 1, characterized by further comprising:
preprocessing the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition;
the preprocessing comprises the steps of utilizing a neural network to carry out abnormal value restoration on road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions to obtain a reliable data set corresponding to the road surface technical grade data, the road surface type data and the road surface maintenance data;
and carrying out normalization processing on the reliable data set.
3. A road surface technical condition prediction method according to claim 1 or 2, wherein the road surface technical condition prediction model is obtained by training based on a machine learning algorithm using, as input data, road surface technical grade sample data, road surface type sample data, and road surface maintenance sample data of a sample road surface, which are related to a road surface technical condition, and using, as output data, a prediction score corresponding to the road surface technical condition of the sample road surface, and specifically includes:
acquiring pavement technical grade sample data, pavement type sample data and pavement maintenance sample data of a sample pavement, which are related to the pavement technical condition;
dividing pavement technical grade sample data, pavement type sample data and pavement maintenance sample data of the sample pavement, which are related to the pavement technical condition, into an initial training data set and a test data set according to a preset proportion to serve as sample input data, training a pavement technical condition prediction model by adopting a strategy of non-overlapping change updating of the initial training data set and the test data set according to a first relation model, and determining the pavement technical condition prediction model by adopting a prediction score corresponding to the pavement technical condition of the sample pavement as output data until the prediction score corresponding to the pavement technical condition of the sample pavement meets a preset training end condition;
wherein the first relationship model comprises:
wherein the content of the first and second substances,
representing a training sample xiTraining error of (d), omega (f)k) Regular terms representing the kth tree, K representing the total number of trees, fkA (k) th tree is shown,
representing a training sample xiPredicted result of (1), xiRepresents training samples, Obj (θ) represents a loss function, n represents the total number of training samples, i represents the ith sample, y representsiRepresenting a training sample xiThe true value of (d).
4. A road surface technical condition prediction method according to claim 2, characterized in that the normalization of the reliable data set specifically comprises:
according to a second relation model, carrying out normalization processing on the reliable data set;
wherein the second relational model comprises:
wherein x is*Representing the processed value, x representing the value to be processed, min being the minimum value of the value to be processed, and max being the maximum value of the value to be processed.
5. A road surface technical condition prediction method according to claim 3, characterized by further comprising:
according to the third correlation model, estimating the prediction effect of the road surface technical condition prediction model by adopting a complex correlation coefficient, a root mean square error and an average absolute value error;
wherein the third relationship model comprises:
wherein R is2Denotes the complex correlation coefficient, RMSE denotes the root mean square error, MAE denotes the mean absolute error, i denotes the ith sample, fiDenotes the predicted value of the i-th sample, yiThe true value of the ith sample is represented,
represents the average of all real values and N represents the total number of samples.
6. A road surface technical condition prediction method according to claim 1, characterized by further comprising:
the road surface technical condition prediction result is a road surface technical condition prediction result of the PQI index;
according to the fourth relational model, calculating a road surface technical condition prediction result of the PQI index;
the fourth relational model includes:
PQI＝ωPCIPCI+ωRQIRQI+ωRDIRDI+ωPBIPBI+ωPWIPWI+ωSRISRI
wherein PQI represents the road surface service performance condition, PCI represents the road surface damage condition, and omegaPCIIndicates the weight of PCI in PQI, RQI indicates waySurface running quality index, omegaRQIRepresents the weight of RQI in PQI, and RDI represents the road rut depth index, omegaRDIRepresents the weight of RDI in PQI, PBI represents the road jump index, omegaPBIRepresents the weight of PBI in PQI, PWI represents the road wear index, ωPWIRepresents the weight of PWI in PQI, SRI represents the road skid resistance index, omegaSRIRepresents the weight of SRI in PQI.
7. A road surface technical condition prediction device is characterized by comprising:
the acquisition module is used for acquiring road surface technical grade data, road surface type data and road surface maintenance data related to the road surface technical condition;
the prediction module is used for inputting the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition into a road surface technical condition prediction model to obtain a prediction score corresponding to the road surface technical condition;
the determining module is used for determining the technical condition of the road surface according to the prediction score corresponding to the technical condition of the road surface;
the road surface technical condition prediction model is obtained by training based on a machine learning algorithm by adopting road surface technical grade sample data, road surface type sample data and road surface maintenance sample data which are related to the road surface technical condition of a sample road surface as input data and adopting a prediction score corresponding to the road surface technical condition of the sample road surface as output data.
8. The road surface technical condition prediction apparatus according to claim 6, characterized by further comprising:
the data preprocessing module is used for preprocessing the road surface technical grade data, the road surface type data and the road surface maintenance data related to the road surface technical condition;
the preprocessing comprises the steps of utilizing a neural network to carry out abnormal value restoration on road surface technical grade data, road surface type data and road surface maintenance data related to road surface technical conditions to obtain a reliable data set corresponding to the road surface technical grade data, the road surface type data and the road surface maintenance data;
and carrying out normalization processing on the reliable data set.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the road surface condition prediction method according to any one of claims 1 to 6 when executing the program.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the road surface condition prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041591.9A CN112241808A (en) | 2020-09-28 | 2020-09-28 | Road surface technical condition prediction method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041591.9A CN112241808A (en) | 2020-09-28 | 2020-09-28 | Road surface technical condition prediction method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112241808A true CN112241808A (en) | 2021-01-19 |
Family
ID=74171879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011041591.9A Pending CN112241808A (en) | 2020-09-28 | 2020-09-28 | Road surface technical condition prediction method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112241808A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966393A (en) * | 2021-03-26 | 2021-06-15 | 深圳大学 | Road surface vehicle-jumping index calculation method, device, equipment and readable storage medium |
| CN117079149A (en) * | 2023-10-18 | 2023-11-17 | 磐安县文溪测绘有限公司 | Road surface condition detection system and method based on machine learning |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832581A (en) * | 2017-12-15 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Trend prediction method and device |
| CN108427658A (en) * | 2018-03-12 | 2018-08-21 | 北京奇艺世纪科技有限公司 | A kind of data predication method, device and electronic equipment |
| CN108596396A (en) * | 2018-04-28 | 2018-09-28 | 中国公路工程咨询集团有限公司 | One kind is based on the modified pavement performance prediction of maintenance history and maintenance process and device |
| CN108960426A (en) * | 2018-07-09 | 2018-12-07 | 吉林大学 | Road grade Synthesize estimation system based on BP neural network |
| CN109190257A (en) * | 2018-09-07 | 2019-01-11 | 东南大学 | A kind of prediction technique of Freeway Performance Indicators decay |
| WO2019019189A1 (en) * | 2017-07-28 | 2019-01-31 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining estimated time of arrival |
| CN109697515A (en) * | 2018-12-28 | 2019-04-30 | 深圳高速工程顾问有限公司 | Pavement of road management method, device, storage medium and computer equipment |
| CN109711722A (en) * | 2018-12-26 | 2019-05-03 | 江苏北极星交通产业集团有限公司 | A kind of net grade road maintenance management decision system |
| CN109801282A (en) * | 2019-01-24 | 2019-05-24 | 湖北大学 | Pavement behavior detection method, processing method, apparatus and system |
| CN109948957A (en) * | 2019-04-30 | 2019-06-28 | 天津天保市政有限公司 | A kind of town road net grade Maintenance Design aid decision-making system |
| CN109993223A (en) * | 2019-03-26 | 2019-07-09 | 南京道润交通科技有限公司 | Pavement Condition prediction technique, storage medium, electronic equipment |
| CN111105332A (en) * | 2019-12-19 | 2020-05-05 | 河北工业大学 | Highway intelligent pre-maintenance method and system based on artificial neural network |
| CN111612224A (en) * | 2020-05-06 | 2020-09-01 | 中咨公路养护检测技术有限公司 | Road surface multilane condition prediction and maintenance planning method |
| CN111652520A (en) * | 2020-06-04 | 2020-09-11 | 招商局重庆交通科研设计院有限公司 | Pavement maintenance intelligent decision system and method based on big data |
-
2020
- 2020-09-28 CN CN202011041591.9A patent/CN112241808A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019019189A1 (en) * | 2017-07-28 | 2019-01-31 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining estimated time of arrival |
| CN107832581A (en) * | 2017-12-15 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Trend prediction method and device |
| CN108427658A (en) * | 2018-03-12 | 2018-08-21 | 北京奇艺世纪科技有限公司 | A kind of data predication method, device and electronic equipment |
| CN108596396A (en) * | 2018-04-28 | 2018-09-28 | 中国公路工程咨询集团有限公司 | One kind is based on the modified pavement performance prediction of maintenance history and maintenance process and device |
| CN108960426A (en) * | 2018-07-09 | 2018-12-07 | 吉林大学 | Road grade Synthesize estimation system based on BP neural network |
| CN109190257A (en) * | 2018-09-07 | 2019-01-11 | 东南大学 | A kind of prediction technique of Freeway Performance Indicators decay |
| CN109711722A (en) * | 2018-12-26 | 2019-05-03 | 江苏北极星交通产业集团有限公司 | A kind of net grade road maintenance management decision system |
| CN109697515A (en) * | 2018-12-28 | 2019-04-30 | 深圳高速工程顾问有限公司 | Pavement of road management method, device, storage medium and computer equipment |
| CN109801282A (en) * | 2019-01-24 | 2019-05-24 | 湖北大学 | Pavement behavior detection method, processing method, apparatus and system |
| CN109993223A (en) * | 2019-03-26 | 2019-07-09 | 南京道润交通科技有限公司 | Pavement Condition prediction technique, storage medium, electronic equipment |
| CN109948957A (en) * | 2019-04-30 | 2019-06-28 | 天津天保市政有限公司 | A kind of town road net grade Maintenance Design aid decision-making system |
| CN111105332A (en) * | 2019-12-19 | 2020-05-05 | 河北工业大学 | Highway intelligent pre-maintenance method and system based on artificial neural network |
| CN111612224A (en) * | 2020-05-06 | 2020-09-01 | 中咨公路养护检测技术有限公司 | Road surface multilane condition prediction and maintenance planning method |
| CN111652520A (en) * | 2020-06-04 | 2020-09-11 | 招商局重庆交通科研设计院有限公司 | Pavement maintenance intelligent decision system and method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| JU HUYAN: ""Development of Machine Learning Based Analytical Tools for Pavement Performance Assessment and Crack Detection"", UWSPACE, pages 98 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966393A (en) * | 2021-03-26 | 2021-06-15 | 深圳大学 | Road surface vehicle-jumping index calculation method, device, equipment and readable storage medium |
| CN112966393B (en) * | 2021-03-26 | 2024-01-12 | 深圳大学 | Road surface jump index calculation method |
| CN117079149A (en) * | 2023-10-18 | 2023-11-17 | 磐安县文溪测绘有限公司 | Road surface condition detection system and method based on machine learning |
| CN117079149B (en) * | 2023-10-18 | 2024-02-09 | 磐安县文溪测绘有限公司 | Road surface condition detection system and method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112733442B (en) | Construction method of road surface long-term performance prediction model based on deep learning | |
| CN111105332A (en) | Highway intelligent pre-maintenance method and system based on artificial neural network | |
| CN106934237A (en) | Radar cross-section redaction measures of effectiveness creditability measurement implementation method | |
| Alqahtani et al. | Artificial neural networks incorporating cost significant items towards enhancing estimation for (life-cycle) costing of construction projects | |
| CN111160728A (en) | Road and bridge maintenance decision optimization method and device | |
| CN113408869A (en) | Power distribution network construction target risk assessment method | |
| CN112241808A (en) | Road surface technical condition prediction method, device, electronic equipment and storage medium | |
| CN112163669A (en) | Pavement subsidence prediction method based on BP neural network | |
| CN113869768A (en) | Method, device, equipment and readable medium for evaluating strength of industrial chain | |
| CN113918538A (en) | Newly-built road maintenance data migration system based on artificial neural network | |
| CN116739376A (en) | Highway pavement preventive maintenance decision method based on data mining | |
| CN115948964A (en) | Road flatness prediction method based on GA-BP neural network | |
| CN116933946A (en) | Rail transit OD passenger flow prediction method and system based on passenger flow destination structure | |
| CN111967308A (en) | Online road surface unevenness identification method and system | |
| CN111222678A (en) | Road surface technical condition prediction method | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| Yang | Road crack condition performance modeling using recurrent Markov chains and artificial neural networks | |
| Patil et al. | Comparative analysis of construction cost estimation using artificial neural networks | |
| CN113706328A (en) | Intelligent manufacturing capability maturity evaluation method based on FASSA-BP algorithm | |
| CN111639837B (en) | Road network service performance evaluation method and device, storage medium and terminal | |
| Aboshady et al. | A fuzzy risk management framework for the Egyptian real estate development projects | |
| CN112308305A (en) | Multi-model synthesis-based electricity sales amount prediction method | |
| Rejani et al. | Upgradation of pavement deterioration models for urban roads by non-hierarchical clustering | |
| CN113762791B (en) | Railway engineering cost management system | |
| CN115270637A (en) | Underground drainage pipeline maximum stress prediction method based on GBRT |
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 |