CN116882709B - Road construction intelligent supervision method based on big data analysis and storage medium - Google Patents
Road construction intelligent supervision method based on big data analysis and storage medium Download PDFInfo
- Publication number
- CN116882709B CN116882709B CN202311133900.9A CN202311133900A CN116882709B CN 116882709 B CN116882709 B CN 116882709B CN 202311133900 A CN202311133900 A CN 202311133900A CN 116882709 B CN116882709 B CN 116882709B
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- traffic
- road construction
- construction
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000007405 data analysis Methods 0.000 title claims abstract description 14
- 238000013500 data storage Methods 0.000 title description 2
- 239000000463 material Substances 0.000 claims abstract description 31
- 230000001413 cellular effect Effects 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012546 transfer Methods 0.000 claims description 6
- CIWBSHSKHKDKBQ-JLAZNSOCSA-N Ascorbic acid Chemical compound OC[C@H](O)[C@H]1OC(=O)C(O)=C1O CIWBSHSKHKDKBQ-JLAZNSOCSA-N 0.000 claims description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 14
- 230000008859 change Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000009499 grossing Methods 0.000 description 7
- 238000010606 normalization Methods 0.000 description 7
- 230000032258 transport Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 239000003102 growth factor Substances 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Abstract
The application discloses an intelligent road construction supervision method based on big data analysis and a storage medium; definition: each cell represents a traffic segment with traffic flow attributes. Attributes:representing the traffic flow of cells located in row i and column j at time t. And (5) updating the state:the method realizes the improvement of the traffic smoothness during the road construction by predicting the traffic flow. By reasonably arranging the construction plan and the material transportation frequency, unnecessary interference of construction on traffic flow is avoided. This helps to reduce traffic congestion and improve the traffic efficiency of the road. The intelligent road construction supervision method enables a constructor to grasp traffic variation trend more accurately by predicting traffic flow. This enables the constructor to adjust the construction strategy, avoiding large-scale construction during peak traffic hours. Therefore, the traffic efficiency of the city is improved, and traffic delay caused by construction is reduced.
Description
Technical Field
The application relates to the technical field of constructional engineering, in particular to an intelligent road construction supervision method based on big data analysis and a storage medium.
Background
In the construction engineering, road construction involves interference of public transportation systems and traffic flows, so that a certain supervision method is required to minimize the influence on traffic. The road is an important traffic channel of a city, and the maintenance of traffic flow is very important for guaranteeing travel, business activities and emergency services of citizens. In the road construction process, traffic interruption or deceleration can cause traffic jam, increase accident risk and even influence the passing of emergency vehicles. Traffic jams and interruptions can negatively impact the economic activity of a city. Traffic jams can lead to delays in personnel and cargo, increase transportation costs, impact business activities and logistics, and thus reduce urban production efficiency and economic growth.
The roads connect different areas in the city, so that public facilities such as hospitals, schools, business areas and the like can smoothly operate. Therefore, maintaining connectivity of traffic is critical to the proper operation of the city. The construction engineering involves the use of urban public resources, and construction parties should bear corresponding social responsibility when using the resources, in an effort to minimize the interference to citizens and ensure the rationality and sustainability of the construction process.
For the above reasons, it is important to employ a certain supervision method to reduce the interference to traffic. This may include planning reasonable construction times, traffic guiding measures, flow monitoring and prediction, traffic detour schemes, etc. Through a scientific supervision method, the negative influence on traffic operation can be reduced to the greatest extent while the development of the building engineering is ensured, and the sustainable development of cities is promoted.
Therefore, an intelligent road construction supervision method based on big data analysis and a storage medium are provided.
Disclosure of Invention
In view of the above, the embodiments of the present application wish to provide an intelligent road construction supervision method and a storage medium based on big data analysis, so as to solve or alleviate the technical problems existing in the prior art, that is, through a scientific supervision method, the negative influence on traffic operation can be reduced to the greatest extent while ensuring the progress of construction engineering, and the sustainable development of cities is promoted, so that at least one beneficial choice is provided for the method;
the technical scheme of the embodiment of the application is realized as follows:
the first aspect;
an intelligent road construction supervision method based on big data analysis;
summary (a):
the method is based on a cellular automaton model, traffic flow information in big data is analyzed, traffic conditions of road sections nearby road construction are predicted, comparison and decision are conducted by combining with a D-S evidence theory, and material transportation frequency is further judged and adjusted according to a threshold value, so that interference of construction on traffic is reduced.
(II) content:
(2.1) STEP-1: traffic flow prediction utilizes cellular automata:
definition: each cell represents a traffic segment with traffic flow attributes.
Attributes:representing the traffic flow of cells located in row i and column j at time t.
And (5) updating the state:where α and β are model parameters for linearly translating traffic flow.
(2.2) STEP-2: D-S evidence theory alignment and decision:
defining the assumption: h1 represents "prediction accuracy", and H2 represents "prediction inaccuracy".
Calculating trust and uncertainty: merge rule calculation using D-S evidence theoryAnd a corresponding uncertainty.
Judging and deciding: according toAnd decides whether to continue with the next operation.
(2.3) STEP-3: threshold value judging and adjusting material transportation frequency:
normalization: will actually traffic flowMapped to interval [0, 1]]Calculation of。
Setting a threshold value: setting Threshold according toAnd comparing with the threshold value, and judging whether the threshold value is exceeded.
Adjusting the frequency: if it isAnd if the threshold value is exceeded, the material transportation frequency is reduced, and the interference between construction and traffic is avoided.
And (III) parameter setting and adjustment:
the settings of alpha and beta need to be determined based on data analysis and experimentation to accommodate actual changes in traffic flow.
The Threshold value Threshold may be adjusted by historical data, traffic operating criteria, and actual evaluations to ensure adaptation to different traffic conditions.
(IV) application and advantages:
the method is suitable for urban road construction, can reduce traffic jam and improve traffic running efficiency. Through big data analysis and intelligent decision, the influence of construction on traffic is reduced, and the traffic smoothness and the citizen life quality are maintained.
(V) summarizing;
through prediction, comparison and threshold judgment, the interference to traffic is reduced to the greatest extent in the road construction process. The method can be applied to urban traffic planning and management, and provides effective support and guidance for urban traffic operation.
A second aspect;
a storage medium having stored therein program instructions for performing the intelligent road construction supervision method as described above.
In the storage medium, program instructions for executing the road construction intelligent supervision method are stored. These program instructions may be written in a variety of programming languages, such as Python, c++, java, etc., to accommodate different computer systems and platforms. Specifically, the program instructions include the following:
(1) A data processing and analyzing module: the instructions are used for processing traffic flow information in big data and carrying out operations such as prediction, normalization and the like. They can pre-process and analyze the data according to the actual requirements.
(2) D-S evidence theory module: these instructions are used to implement the alignment and decision steps in the D-S evidence theory. They calculate the confidence and uncertainty of the hypothesis to make a decision.
(3) Threshold judgment and adjustment module: the instructions are used for determining whether the material transportation frequency needs to be adjusted according to comparison of the normalized traffic flow and the threshold value. They enable an automatic adjustment according to traffic conditions.
(4) Parameter setting module: these instructions are used to set and adjust parameters in the model, which can be optimized and adjusted based on data analysis and experimental results.
(5) Output and feedback module: these instructions are used to generate regulatory results and decisions and to provide the necessary feedback. The output may be traffic flow predictions, decision results, suggested material transportation frequencies, etc.
(6) By storing these program instructions in a storage medium, the computer system can read, execute, and update these instructions as needed, thereby implementing automated operations of the intelligent road construction supervision method.
Summarizing, compared with the prior art, the intelligent road construction supervision method and the storage medium based on big data analysis provided by the application have the following beneficial effects:
1. promotion of traffic fluency: the method realizes the improvement of the traffic smoothness during the road construction by predicting the traffic flow. By reasonably arranging the construction plan and the material transportation frequency, unnecessary interference of construction on traffic flow is avoided. This helps to reduce traffic congestion and improve the traffic efficiency of the road.
2. Increase of urban traffic efficiency: the intelligent road construction supervision method enables a constructor to grasp traffic variation trend more accurately by predicting traffic flow. This enables the constructor to adjust the construction strategy, avoiding large-scale construction during peak traffic hours. Therefore, the traffic efficiency of the city is improved, and traffic delay caused by construction is reduced.
3. The risk of traffic accidents is reduced: during road construction, traffic confusion and irregularities often increase the risk of traffic accidents. The intelligent supervision method can avoid traffic jam caused by construction, reduce the possibility of traffic accidents and improve the safety of road traffic.
4. Improving the travel experience of citizens: when the road is constructed, citizens often suffer from problems such as traffic jam, noise, inconvenience and the like. Through effective supervision and adjustment, the intelligent supervision method is beneficial to reducing the adverse factors, improves the travel experience of citizens, and improves the living environment of cities.
5. Reasonable utilization of resources: the intelligent supervision method can adjust the material transportation frequency according to actual conditions, so that excessive resource waste is avoided. This includes reducing unnecessary material transportation, reducing fuel consumption, etc., contributing to environmental protection and rational utilization of resources.
6. Urban sustainable development: the method is helpful for realizing sustainable development of cities by reducing the interference of road construction on traffic and environment. Smooth and efficient traffic will promote the development of urban economy and improve the quality of life of citizens.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are necessary for the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a comparative schematic diagram of a third and fourth embodiment of the present application;
fig. 2 is a cellular automaton evolution diagram according to a second embodiment of the present application;
FIG. 3 is a control program diagram of an eighth embodiment of the present application;
fig. 4 is a control program diagram of an eighth embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the application will be readily understood, a more particular description of the application will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit of the application, whereby the application is not limited to the specific embodiments disclosed below;
embodiment one: a road construction intelligent supervision method based on big data analysis comprises the following steps:
STEP-1: in this step, first traffic flow data of the current time step is acquired, which data depict traffic conditions of different road segments. Then, with the help of the cellular automaton model, the present embodiment can predict the traffic flow of the road section near the road construction of the next time step. The core idea of this process is to infer future traffic flow by information transfer and interaction between cells (representing road segments) based on historical data and specific factors (e.g., time, weather, road type, etc.).
STEP-2: in this step, the present embodiment combines the predicted value obtained in the previous step with the traffic flow data of the big data output as two different evidences. Then, the embodiment introduces the two evidences into the D-S evidence theory, compares and verifies the accuracy of the prediction made by the cellular automaton model in the previous step. The specific process comprises the following key points:
s2.1, hypothesis construction: the present embodiment constructs two hypotheses, namely "prediction accurate" (H1) and "prediction inaccurate" H2), representing the prediction situation of the cellular automaton model.
S2.2, evidence combination: the present embodiment uses the merging rule of the D-S evidence theory, taking the predicted value as one evidence (evidence 1), and the traffic flow data output by the big data as the other evidence (evidence 2). By merging, the present embodiment obtains the confidence level of these two evidences on each hypothesis.
S2.3, decision judgment: the present embodiment compares the confidence level of these two pieces of evidence on the "prediction accuracy" assumption. If evidence 1 is significantly more trusted on this assumption than evidence 2, indicating that the prediction is more accurate, the present embodiment may proceed to the next step.
STEP-3: if the accuracy of the prediction in the previous step of verification is verified, the present embodiment will proceed to the next step. In this step, the present embodiment compares the predicted value with a preset threshold value. This threshold is a threshold limit used to determine if traffic flow is outside of an acceptable range. If the predicted value exceeds the threshold, the present embodiment will perform the following operations:
s3.1, numerical normalization: first, the present embodiment normalizes the predicted values and maps them to the interval [0, 1] for comparison and judgment.
S3.2, threshold comparison: next, the present embodiment compares the normalized predicted value with a preset threshold value. If the normalized value exceeds the threshold value, the traffic flow is larger, and the influence of construction needs to be further controlled.
S3.3, frequency adjustment: in the event that the threshold is exceeded, the present embodiment will take steps to reduce the frequency of material transportation during road construction to reduce traffic interference. This can be achieved by reducing the number of shipments, adjusting the shipping time, etc.
Through the series of steps, the intelligent road construction supervision method based on big data analysis can predict traffic flow, verify prediction accuracy and adjust material transportation frequency when necessary, so that the interference of construction on traffic is reduced to the greatest extent, and the efficiency and quality of urban traffic are improved.
Embodiment two: according to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
in STEP-1:
cell definition: in the embodiment, each road section is regarded as a cell, and C i,j Cells located in a row i and a column j at a time t represent traffic segments near road construction;
cell neighbor definition: let N i,j Representing a neighbor set of cells located in row i and column j, representing a neighbor set of cells located in row i and column j i,j A set of cells that are adjacent and affect their state update:
；
these neighbor cells and current cell C i,j Is related to the status update of (a);
cell properties: each cell C i,j Has an attribute Traffic (t) representing the Traffic flow through the link at time t; this attribute is a real number reflecting the traffic conditions of the current time step:
；
: the traffic flow of the cells located in row i and column j has a value at time step t, which is the traffic flow.
Specifically, the attribute Traffic (t) plays a key role in the cellular automaton model, which is an important attribute of each cell in the model, to represent the Traffic flow through the road section at time t. The following is a further extension of the attribute Traffic (t), including its influencing factors and actual meaning:
(1) Comprehensive consideration of influencing factors:
the value of (c) is affected by a number of factors, which may be time, weather, road type, special events, etc. In practical applications, these factors can be taken into account to construct a more accurate traffic flow model. For example, traffic flow may increase significantly during peak hours for a road segment and decrease during rainy or holidays.
(2) Actual meaning of traffic flow:
reflecting the number of vehicles passing through a particular road segment at time t. The practical significance of this attribute is that it can help the present embodiment understand and predict traffic conditions. A high traffic flow may mean traffic congestion and a low traffic flow may mean traffic congestionAnd (3) unblocking. Through the real-time monitoring and prediction of traffic flow, the embodiment can better manage urban traffic, provide real-time traffic information and reduce congestion and delay.
(3) Utilization of historical data:
has great significance for predicting future traffic flows. By analyzing the historical data, the embodiment can find rules such as periodic variation, trend and the like of traffic flow, so that future traffic conditions can be predicted more accurately. The cellular automaton model can make more reasonable prediction by combining the past information, and the accuracy of the prediction is improved.
Further, the method comprises the steps of,the cellular automaton model represents important information of traffic flow, integrates various influencing factors, and has practical traffic significance. Through comprehensive analysis of the attribute and utilization of historical data, the embodiment can realize more accurate traffic flow prediction and provide powerful support for implementation of the intelligent road construction supervision method.
In this embodiment, the linear transfer function:
；
alpha and beta are parameters of the model for linearly converting the traffic flow of the current time step into a predicted value of the next time step.
In particular, the linear transfer function is a key part of the cellular automaton model, which is used to predict the traffic flow for the next time step. The meaning and influencing factors of this function will be further extended as follows:
the linear transfer function is a mathematical expression for the traffic flow at the current time stepConversion to the prediction value of the next time step +.>This conversion is linear, meaning that the predicted value is a linear combination of the current values, controlled by the parameters α and β.
Specific: referring to fig. 2, α is a trend of increasing or decreasing traffic flow. If α is greater than 1, the predicted value will be greater than the current value, suggesting that traffic flow may increase. If α is between 0 and 1, the predicted value will be smaller than the current value, indicating that traffic flow may be decreasing. The larger the value of α, the more violent the traffic flow changes and vice versa. The white area in the figure is the predicted traffic flow frequency float.
Specific: beta is a constant term representing the reference value of traffic flow for the next time step without other influencing factors. It can be used to adjust the overall prediction level of the model. If beta is larger, the reference value of the predicted value is higher; if β is small, the reference value of the predicted value is low.
It will be appreciated that the linear transfer function can still take into account historical data and trends in predicting traffic flow. By adjusting the parameters α and β, the present embodiment can make predictions based on the trend of the historical traffic flow. If the historical data indicate that the traffic flow is in an ascending trend, the embodiment can set alpha to be larger than 1 so as to embody the characteristic of growth. Linear conversion functionIs one of the key mechanisms of cellular automaton models, which converts information of past traffic flows into predictions of future traffic flows. Reasonable prediction can be made according to historical data and trend through alpha and beta, so that more accurate traffic flow prediction is provided for the intelligent road construction supervision method.
Example III
According to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
alpha and beta are linear growth models: the traffic flow varies in proportion to the current flow, i.e. the traffic flow increases linearly with time;
alpha is a constant k greater than 1 to represent an increase in traffic flow; beta is a positive number b greater than 1, representing the basic traffic flow:
；
if alpha is greater than 1 and the value is continuously increasing, the current state is increased at a speed which is increased, so that the predicted traffic flow is increased; beta adds a reference value to the current state and the state remains at a basic level even if no external factors affect it.
In this embodiment, α and β are linear growth models, and the traffic flow varies in proportion to the current flow, i.e., the traffic flow increases linearly with time. Where α represents the growth factor of the traffic flow, and β represents the basic traffic flow, i.e., the reference value of the traffic flow without the influence of external factors.
(1) Alpha acts as a growth factor: alpha is a key parameter in a linear growth model, which represents the rate of increase of traffic flow. If α is greater than 1, which represents a faster rate of increase in traffic flow, the current state will increase at a progressively higher rate. This means that traffic flow will show a gradual increase in the trend at future time steps. The magnitude of the value of α may represent the degree of traffic flow increase.
(2) Beta is taken as the basic traffic flow: on the other hand, β represents the basic traffic flow, i.e., the reference level of traffic flow without the influence of external factors. Traffic flow remains at this basic level even without special events or influencing factors. This can be understood as the normal level of traffic, reflecting the basic use of the road.
(3) Combined action of α and β: the alpha and beta act together, so that the linear growth model can reasonably predict the change of the future traffic flow according to the current traffic flow and the growth trend. If a is greater than 1 and the value is continuously increased, the predicted traffic flow increases with the increasing speed over time, reflecting the increasing trend. The presence of beta ensures that the traffic flow remains at a relatively stable reference value even in the absence of disturbances from external factors. Through reasonable setting of alpha and beta, the embodiment can more accurately predict the change of the future traffic flow by using a linear growth model, and provides powerful traffic flow prediction support for the intelligent road construction supervision method.
For example, please refer to calculation mode 1 in fig. 1: let us consider the traffic flow of a road construction area, which wants to use a linear growth model to predict traffic flow changes for several time steps in the future. In this example, the present embodiment will select the following parameter values:
alpha (growth factor): let α=1.2 denote a 20% increase in traffic flow per time step.
Beta (basic traffic flow): let β=100, denote that the reference value of the traffic flow is 100 when there is no external influence.
The present embodiment will now use these parameters to predict traffic flow changes for three time steps in the future. Assuming that the traffic flow for the current time step is:
；
time step t=0:
；
time step t=1: according to the linear growth model:
；
time step t=2:
；
time step t=3:
；
and repeatedly carrying out the cycle;
by way of this example, the present embodiment can see that traffic flow increases progressively with time in a linearly increasing trend, according to the selected parameter values. The growth factor alpha controls the growth rate and the basic traffic flow beta provides a reference value for the traffic flow. This derivation demonstrates how the linear growth model predicts from parameters and applies in intelligent supervision of road construction.
Example IV
According to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
alpha and beta are smoothing models: traffic flow remains unchanged all the time;
α is a constant ϵ approaching 1 to maintain the smoothness of the traffic flow, and β is a constant b greater than 1, representing the basic traffic flow:
；
this embodiment differs from embodiment three in that in the smoothing model, the meaning of α and β is redefined in this embodiment. At this time, α represents a constant ϵ approaching 1 for maintaining the smoothness of the traffic flow, while β still represents the basic traffic flow.
In the smoothing model ϵ is a constant that is less than 1 but approaching 1. Its function is to keep the traffic flow stable, and even if the traffic flow is affected by external factors, the traffic flow change is relatively slow. By setting ϵ close to 1, the present embodiment ensures that the traffic flow changes relatively smoothly, reducing the instability caused by severe fluctuations in traffic flow.
Specifically, the action of beta: as in the previous explanation, β represents the basic traffic flow, i.e., the reference value of the traffic flow without the influence of external factors.
Specifically, the synergy of α and β: in the smoothing model, α and β act together such that the predicted traffic flow is relatively stable. By setting α to a constant ϵ close to 1, the present embodiment maintains the smoothness of the traffic flow, while the traffic flow still has a substantial level by the presence of β. This synergy ensures the smoothness and stability of the traffic flow changes.
Specifically, the applicable scenario: the smoothing model is applicable to situations where traffic flow stability needs to be maintained, such as in relatively stable road segments or periods of no significant change. The intelligent monitoring system can help to prevent severe fluctuation of traffic flow, so that intelligent monitoring of road construction is more reliable and effective. By adopting the alpha and beta newly defined in the smooth model, the embodiment can realize the stable prediction of the traffic flow, thereby providing more stable traffic flow prediction support for intelligent supervision of road construction.
For example, referring to the second part of the calculation method of fig. 1, let us consider the traffic flow of a relatively stable road area, and the present embodiment expects to use a smoothing model to predict the traffic flow change for several time steps in the future. In this example, the present embodiment will select the following parameter values:
α (constant ϵ approaching 1): assuming α=0.95, representing the stationarity of traffic flow, the flow does not change much per time step.
Beta (basic traffic flow): let β=80, it means that the reference value of the traffic flow is 80 when there is no external influence.
The present embodiment will now use these parameters to predict traffic flow changes for three time steps in the future. Assuming that the traffic flow for the current time step is:
；
time step t=0:
；
time step t=1: according to the smoothing model:
；
time step t=2:
；
time step t=3:
；
example five
According to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
in STEP-2: D-S evidence theory: this embodiment requires two hypotheses to be aligned: h1 Indicating that the prediction is accurate and H2 indicates that the prediction is inaccurate. Based on the D-S evidence theory, the present embodiment determines which hypothesis is more reliable based on the calculation of confidence and uncertainty to decide whether to perform STEP-3.
H1: the prediction is accurate;
h2: the prediction is inaccurate;
bel (H1): the trust degree of H1;
pl (H1): uncertainty of H1;
bel (H2): the confidence level of H2;
pl (H2): uncertainty of H2;
wherein the calculation of the confidence and uncertainty is obtained by cross-calculating Bel and Pl. The specific calculation is as follows:
；
in this formula, what the present embodiment calculates is the confidence level for the hypothesis H1, namely Bel (H1). This confidence is based on a combination of two pieces of evidence: one is evidence about traffic flowThe other is evidence about prediction accuracy +.>。
The trust level is calculated based on the Dempster synthesis rule in the D-S evidence theory, which considers the consensus and contradiction of the two evidences. Here, the present embodiment combines two pieces of evidence to calculate the degree of trust for hypothesis H1. The molecular part in the formula represents the degree of commonality of the two pieces of evidence, i.eThis value is larger if both pieces of evidence support the same hypothesis to some extent.
The denominator part represents the combination of the co-recognition and contradiction of the two evidences, namely:
；
this value will be smaller if there is a discrepancy between the two evidences. By taking into account the consensus and contradiction, the calculation of the confidence level can reflect the relative confidence level for hypothesis H1. The calculation of confidence is used to compare the predicted accuracy assumption with the inaccuracy assumption. If the confidence level for assumption H1 (prediction is accurate) is large, the present embodiment can relatively make sure that the prediction is accurate, and thus decide to perform STEP-3. The calculation process helps the embodiment to make decisions based on data and evidence under the condition of uncertainty, so that the accuracy and reliability of intelligent supervision of road construction are improved;
；
；
；
if Bel (H1) is greater than Bel (H2), then this embodiment considers H1 more trusted, so STEP-3 may be executed, and vice versa.
Specifically, in D-S evidence theory, in addition to confidence (Belief), there is an important concept of uncertainty (Plausibility). Uncertainty is used to indicate the degree to which a hypothesis is not supported, i.e., the degree of negation of the hypothesis. Thus, uncertainty is a measure of the degree of negativity of an hypothesis. In D-S evidence theory, the uncertainty of one hypothesis is equal to the confidence level for its complement (i.e., its counter-proposition). Therefore, text { Pl } (H_1) is the negation of assumption H1, i.e., H1 is not believed.
Based on this principle, the present embodiment can obtain the following calculation relationship:
；
uncertainty over hypothesis H1 is equal to the extent to which hypothesis H2 is not believed. That is, if the present embodiment does not believe that the prediction is inaccurate, then the assumption that the prediction is accurate is not determined;
；
the confidence level for hypothesis H2 is equal to the uncertainty for hypothesis H1. That is, if the present embodiment does not determine a hypothesis that the prediction is accurate, it is believed that the prediction is inaccurate;
；
uncertainty over hypothesis H2 is equal to the extent to which hypothesis H1 is not believed. As with the first formula, this is a way of calculating uncertainty.
It will be appreciated that by comparing the confidence level and uncertainty of two hypotheses, it is determined which hypothesis is more trusted. If uncertainty over hypothesis H1 is greater, then the present embodiment will more believe that inaccurate hypothesis H2 is predicted. The comparison and judgment process is helpful for evaluating the accuracy of prediction in intelligent road construction supervision, so that whether to execute subsequent steps or not is determined, and the effectiveness and accuracy of supervision are improved.
Example six
According to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
in STEP-3:
the range of traffic flow may vary greatly, and this embodiment desirably maps traffic flow to a uniform interval when comparing and thresholding. This is the effect of the normalized mapping. The embodiment normalizes the traffic flowMapped to interval [0, 1]]Expressed as->：
；
MinTraffic and MaxTraffic are the minimum and maximum traffic flow, respectively. This mapping allows traffic flows to be compared and judged over a uniform interval.
After normalization, the embodiment can judge whether the material transportation frequency of road construction needs to be reduced according to the preset threshold value so as to reduce the interference to traffic. The threshold is an adjustable parameter that is used to determine when to take an intervention. By mapping traffic flow normalization to the [0, 1] interval and setting a proper threshold, the embodiment can more accurately judge the change of traffic flow and take corresponding measures when the change exceeds the threshold, thereby minimizing the interference of road construction on traffic. The setting of the threshold is adjusted according to actual needs and conditions to ensure coordination and effectiveness between road construction and traffic flow.
Example seven
According to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
in STEP-3: also includes Threshold value by comparisonAnd Threshold determines whether further reduction in material transport frequency is required:
if it isAnd if the speed exceeds Threshold, the material transportation frequency in road construction is further reduced, so that the interference on traffic is reduced.
Threshold is a fixed percentage of the average traffic flow output by the large data source.
In this embodiment, the threshold is set to a fixed percentage of the average traffic flow output from the large data source. This means that the present embodiment can obtain an average traffic flow by analyzing the historical traffic flow data, and take a certain percentage of this average flow as a threshold. The purpose of this is to set a relatively reasonable criterion for determining whether traffic flow is abnormal or above average based on historical data.
Specifically, the principle of adjusting the material transportation frequency is as follows: once the traffic flow exceeds the threshold value after the normalized mapping, it is desirable to further reduce the material transportation frequency to reduce the interference to traffic. This is because traffic flow exceeding the threshold may cause traffic congestion, affecting normal traffic. Here, the adjustment of the material transport frequency is achieved by reducing the frequency and the number of material transports. This means that in case of a large traffic flow, the present embodiment will reduce the material transportation in the road construction area, thereby reducing the disturbance to traffic. This can be achieved by adjusting the plan and frequency of material transport, ensuring coordination of road construction and traffic.
It will be appreciated that in STEP-3, the normalized traffic flow is comparedAnd a preset threshold value, the embodiment can judge whether the current traffic flow exceeds a normal level. If the threshold is exceeded, it is desirable to further reduce the material transport frequency to reduce the disturbance to traffic. The threshold value is set based on the historical data, so that the abnormal condition of the traffic flow can be judged more accurately. The adjustment of the material transportation frequency is used for guaranteeing the fluency and the safety of traffic and ensuring that the road construction cannot cause unnecessary interference to the traffic.
Example eight
According to the above specific implementation manner and embodiment, the present embodiment further provides the following technical solutions:
referring to fig. 3-4, the present embodiment further provides a storage medium having program instructions stored therein for performing the method according to embodiments one to seven, wherein the logic is shown in the form of c++ pseudo code, and the principle is as follows:
STEP-1: traffic Prediction using Cellular Automaton: in each time step, the program uses the cellular automaton model to predict traffic flow for the next time step. And the cellular automaton model predicts the traffic flow condition of the next time step according to the traffic flow at the current moment and the conditions of surrounding road sections.
STEP-2:D-S Evidence Theory Comparison: in this step, the program compares the two hypotheses using D-S evidence theory (H1: accurate prediction, H2: inaccurate prediction). By calculating Belief and Plausibility, it is decided whether STEP-3 is further performed. If the confidence level of the accurate prediction is higher than that of the inaccurate prediction, judging whether the material transportation frequency needs to be adjusted according to the threshold value.
STEP-3: material Transport Adjustment based on Threshold: if the step is judged to be needed to be further executed through the D-S evidence theory, the program compares the normalized traffic flow with the threshold according to the threshold. If the normalized traffic flow exceeds the threshold, an operation of adjusting the material transportation frequency is performed to reduce traffic interference.
Key functions:
PredictTraffic (Ci, j, t+1): the function predicts traffic flow conditions for the next time step using a cellular automaton model in each time step. This function estimates future traffic flow based on traffic information at the current time and the status of surrounding road segments.
Calculotie belifefandplausibility (Ci, j, t+1): this function calculation assumes the Belief and Plausibility of H1 and H2 for comparison of D-S evidence theory. Based on the confidence level of prediction accuracy and prediction inaccuracy, it is determined whether STEP-3 is further executed.
Normazedtrafic (Ci, j, t): the function is used to map traffic flow normalization to intervals [0, 1], such that traffic flows are compared within a unified interval. This function performs normalization based on minimum and maximum traffic flows.
Reduced materials transport frequency (Ci, j): the function reduces the material transportation frequency according to the situation so as to reduce the interference of road construction on traffic. If the normalized traffic flow exceeds the threshold, this function is invoked to reduce the material transportation frequency.
Claims (3)
1. The intelligent road construction supervision method based on big data analysis comprises the traffic flow data of the current time step output by a big data source and is characterized by comprising the following steps:
STEP-1: receiving traffic flow data of the current time step, and predicting the traffic flow of a road section near the road construction of the next time step by using a cellular automaton model;
STEP-2: taking the predicted numerical value and traffic flow data output by a big data source as two evidences, importing the two evidences into a D-S evidence theory for comparison, verifying the prediction accuracy of the cellular automaton in STEP-1, and determining whether to execute STEP-3;
STEP-3: if STEP-2 agrees to execute the STEP, comparing the preset threshold value with the predicted value of STEP-1, and if the threshold value is exceeded, reducing the material transportation frequency in road construction;
in STEP-1:
cell definition: let C i,j Cells located in a row i and a column j at a time t represent traffic segments near road construction;
cell neighbor definition: let N i,j Representing a neighbor set of cells located in row i and column j, representing a neighbor set of cells located in row i and column j i,j A set of cells that are adjacent and affect their state update:
；
cell properties: each cell C i,j Has an attribute Traffic (t) representing the Traffic flow through the link at time t:
；
: traffic flow at time step t for cells located in row i, column j;
in STEP-1, the traffic flow for the next time STEP is predicted using the following linear transfer function:
；
alpha and beta are linear growth models or smooth models;
when α and β are linear growth models, α is a constant greater than 1 to represent an increase in traffic flow; beta is a positive number greater than 1, representing the basic traffic flow;
when α and β are smooth models: alpha is a constant approaching 1 to keep the stability of the traffic flow, and beta is a constant greater than 1 to represent the basic traffic flow;
in STEP-2:
definition hypothesis H 1 And assume H 2 ：H 1 Accurate representation and prediction, H 2 Representing mispredictionDetermining; calculation of H using merging rules of D-S evidence theory 1 Trust Bel (H) 1 ) And H 2 Trust Bel (H) 2 ) The method comprises the steps of carrying out a first treatment on the surface of the If Bel (H) 1 ) Greater than Bel (H) 2 ) STEP-3 is executed, otherwise not executed;
in STEP-3:
by normalizingMapped to interval [0, 1]]Expressed as：
；
MinTraffic and MaxTraffic are the minimum and maximum traffic flow, respectively;
in STEP-3: by comparison ofAnd determining whether the material transportation frequency needs to be reduced by a preset threshold value:
if it isIf the threshold exceeds a predetermined threshold, the frequency of material transportation during road construction needs to be reduced.
2. The intelligent supervision method for road construction according to claim 1, wherein: the predetermined threshold is a fixed percentage of the average traffic flow output by the large data source.
3. A storage medium, characterized by: program instructions for executing the intelligent supervision method for road construction according to any one of claims 1 to 2 are stored in the storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311133900.9A CN116882709B (en) | 2023-09-05 | 2023-09-05 | Road construction intelligent supervision method based on big data analysis and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311133900.9A CN116882709B (en) | 2023-09-05 | 2023-09-05 | Road construction intelligent supervision method based on big data analysis and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116882709A CN116882709A (en) | 2023-10-13 |
| CN116882709B true CN116882709B (en) | 2023-12-01 |
Family
ID=88260805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311133900.9A Active CN116882709B (en) | 2023-09-05 | 2023-09-05 | Road construction intelligent supervision method based on big data analysis and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882709B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117077987B (en) * | 2023-10-16 | 2024-01-02 | 湖南省通晓信息科技有限公司 | Environmental sanitation management method based on cellular automaton and storage medium |
| CN117314879A (en) * | 2023-10-19 | 2023-12-29 | 甘肃路桥飞宇交通设施有限责任公司 | Self-adaptive operation and maintenance judging method and monitoring device for road indication board |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9633560B1 (en) * | 2016-03-30 | 2017-04-25 | Jason Hao Gao | Traffic prediction and control system for vehicle traffic flows at traffic intersections |
| CN108647833A (en) * | 2018-05-21 | 2018-10-12 | 西南交通大学 | Select the method, apparatus of construction |
| CN109003437A (en) * | 2018-07-06 | 2018-12-14 | 中国电建集团华东勘测设计研究院有限公司 | A kind of construction area traffic impact overall target calculation method |
| CN113610283A (en) * | 2021-07-23 | 2021-11-05 | 广州市北二环交通科技有限公司 | Highway road occupation construction plan optimization method, device, medium and product based on simulation evaluation |
| CN115130881A (en) * | 2022-07-06 | 2022-09-30 | 日照市计量科学研究院 | Road construction monitoring method and system based on big data |
| CN115392557A (en) * | 2022-08-22 | 2022-11-25 | 北京交通大学 | Station passenger flow state monitoring method and system based on video and AFC data fusion |
| CN116129645A (en) * | 2023-02-22 | 2023-05-16 | 辽宁艾特斯智能交通技术有限公司 | Traffic flow prediction method, device and storage medium for expressway construction area |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8880380B2 (en) * | 2007-12-21 | 2014-11-04 | Honda Motor Co., Ltd. | Crashworthiness design methodology using a hybrid cellular automata algorithm for the synthesis of topologies for structures subject to nonlinear transient loading |
-
2023
- 2023-09-05 CN CN202311133900.9A patent/CN116882709B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9633560B1 (en) * | 2016-03-30 | 2017-04-25 | Jason Hao Gao | Traffic prediction and control system for vehicle traffic flows at traffic intersections |
| CN108647833A (en) * | 2018-05-21 | 2018-10-12 | 西南交通大学 | Select the method, apparatus of construction |
| CN109003437A (en) * | 2018-07-06 | 2018-12-14 | 中国电建集团华东勘测设计研究院有限公司 | A kind of construction area traffic impact overall target calculation method |
| CN113610283A (en) * | 2021-07-23 | 2021-11-05 | 广州市北二环交通科技有限公司 | Highway road occupation construction plan optimization method, device, medium and product based on simulation evaluation |
| CN115130881A (en) * | 2022-07-06 | 2022-09-30 | 日照市计量科学研究院 | Road construction monitoring method and system based on big data |
| CN115392557A (en) * | 2022-08-22 | 2022-11-25 | 北京交通大学 | Station passenger flow state monitoring method and system based on video and AFC data fusion |
| CN116129645A (en) * | 2023-02-22 | 2023-05-16 | 辽宁艾特斯智能交通技术有限公司 | Traffic flow prediction method, device and storage medium for expressway construction area |
Non-Patent Citations (2)
| Title |
|---|
| "基于城市交通拥堵预测的主动信号控制方法研究";江航;《中国博士学位论文全文数据库工程科技II辑(第12期);第C034-39页 * |
| A Generic Methodological Framework for Cyber-ITS:Using Cyber-infrastructure in ITS Data Analysis Cases;Xia yingjie;《Fundamenta informaticase》;第133卷;第 35-53页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116882709A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116882709B (en) | Road construction intelligent supervision method based on big data analysis and storage medium | |
| Walraven et al. | Traffic flow optimization: A reinforcement learning approach | |
| Yueming et al. | Emergency evacuation model and algorithms | |
| Huang et al. | Opportunistic intermittent control with safety guarantees for autonomous systems | |
| CN114839943A (en) | Cascade power station gate control strategy generation and rolling optimization method and system | |
| Ramezani et al. | A link partitioning approach for real-time control of queue spillbacks on congested arterials | |
| Zhu et al. | A fuzzy robust nonlinear programming model for stream water quality management | |
| CN114999182A (en) | Vehicle flow prediction method, device and equipment based on LSTM feedback mechanism | |
| Jiang et al. | Hybrid perimeter control with real-time partitions in heterogeneous urban networks: An integration of deep learning and MPC | |
| US20240046283A1 (en) | Methods and iot systems for industrial gas demand regulation based on smart gas | |
| CN110705806B (en) | Electric quantity prediction method based on capacity utilization hours | |
| Sun et al. | Emission monitoring dispatching of drones under vessel speed fluctuation | |
| EP4057084A1 (en) | Control apparatus, control method, and control program | |
| Xiong et al. | Factors and economic evaluation of Transnational Investment Risks | |
| CN113469410A (en) | Power grid maximum consumption capability online calculation method and device considering new energy uncertainty | |
| Pasquale et al. | Optimization of time‐varying feedback controller parameters for freeway networks | |
| Chou | Fuzzy forecast based on fuzzy time series | |
| Hossain et al. | Impact Assessment of Machine Learning Algorithms On Resource Efficiency And Management In Urban Developments | |
| Chen | Logistics Distribution Path Optimization Using Support Vector Machine Algorithm under Different Constraints | |
| Bugarski et al. | Fuzzy expert system for adaptive vessel traffic control on one-way section on navigable canal | |
| Chen et al. | A new GM (1, 1) model based on piecewise rational quadratic monotonicity-preserving interpolation spline | |
| Guo et al. | Short-term traffic flow prediction algorithm for expressway based on long short-term memory and support vector regression | |
| Kotsialos et al. | A hierarchical ramp metering control scheme for freeway networks | |
| Zhang et al. | Real-time optimization of urban channel gate control based on a segmentation hydraulic model | |
| Tang et al. | Resilient ramp control for highways facing stochastic perturbations |
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 |