CN116911464A - Intelligent construction site traffic demand prediction method based on artificial intelligence algorithm - Google Patents
Intelligent construction site traffic demand prediction method based on artificial intelligence algorithm Download PDFInfo
- Publication number
- CN116911464A CN116911464A CN202310938580.8A CN202310938580A CN116911464A CN 116911464 A CN116911464 A CN 116911464A CN 202310938580 A CN202310938580 A CN 202310938580A CN 116911464 A CN116911464 A CN 116911464A
- Authority
- CN
- China
- Prior art keywords
- construction
- traffic
- level
- daily
- congestion
- 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 216
- 238000010276 construction Methods 0.000 title claims abstract description 144
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 20
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 13
- 238000013439 planning Methods 0.000 claims abstract description 27
- 238000007726 management method Methods 0.000 claims abstract description 17
- 238000003062 neural network model Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 101
- 239000000463 material Substances 0.000 claims description 50
- 238000012546 transfer Methods 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 6
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000007704 transition Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000003111 delayed effect Effects 0.000 claims description 3
- 238000004445 quantitative analysis Methods 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims description 2
- 239000004568 cement Substances 0.000 claims description 2
- 239000011083 cement mortar Substances 0.000 claims description 2
- 238000000576 coating method Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 239000004570 mortar (masonry) Substances 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims 1
- 230000006855 networking Effects 0.000 claims 1
- 238000010187 selection method Methods 0.000 claims 1
- 230000008520 organization Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 239000004035 construction material Substances 0.000 abstract 1
- 238000009435 building construction Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004088 simulation Methods 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
- G06Q10/04—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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q10/06316—Sequencing of tasks or work
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent building site traffic demand prediction method based on an artificial intelligence algorithm, which comprises the following steps: designing a project construction period traffic demand prediction model, and providing a solving method for model parameters; considering fluctuation of a construction procedure and a personnel configuration plan in a construction area, and classifying the procedure according to a time sequence rule of construction strength; and analyzing main influencing factors of engineering delay, respectively designing a neural network model according to the characteristics of each type of procedure, and determining the influencing coefficients of the influencing factors on daily traffic demand of each type of procedure. The method provided by the invention comprehensively considers the influence of the traffic environment in the construction area and the surrounding of the construction area on the daily traffic demand of the construction material transportation vehicles, and the proposed prediction method can be better applicable to different engineering projects, accurately predicts the daily traffic demand, and is beneficial to dynamically realizing the management and the monitoring of the cargo transportation vehicles entering and exiting each construction area daily, the traffic organization route planning and the transverse and longitudinal dispatching management.
Description
Technical Field
The invention relates to the field of construction site traffic scheduling, in particular to an intelligent construction site traffic demand prediction method based on an artificial intelligence algorithm.
Background
Along with the development of high-speed, continuous, stable and coordinated economy in China, the current building engineering has the characteristics of complex building structure, short construction period, high construction requirement, large volume and the like. This places higher demands on overall construction efficiency and effective engagement between the procedures. The rationality of material transportation in the construction period has a great influence on the on-schedule delivery of building projects. However, at present, when many building construction units perform project management work, the method of modeling simulation does not accurately grasp traffic rationality in a short period, and the randomness is relatively high during the development of construction traffic organization work. Therefore, the construction schedule cannot be dynamically adjusted according to the actual construction progress, traffic organization and management and control are optimized, and the phenomena of procedure conflict, personnel shortage or personnel floating in the construction are caused, so that the overall progress of engineering is seriously affected, and serious economic and manpower losses are caused.
On the other hand, blind dispatching of goods and arrangement of truck approach can also cause massive parking and inefficiency of trucks, etc., or cause no truck to arrive at the approach resulting in idle construction area. If the materials actually transported to the construction area can not meet the construction requirements of each working procedure, working procedure conflict can occur, so that the materials in the construction site, a parking lot, crane equipment, management personnel and the like are idle, manpower and material resources are wasted, and the engineering delivery time is difficult to be ensured. In addition, for construction sites with special positions, the limited space resources outside the sites also bring great challenges to engineering material transportation.
The existing method is more focused on the arrangement of temporary roads outside a construction area and the optimization of complex road network lines for the analysis of daily traffic, does not consider the characteristics of personnel distribution, material distribution and construction planning of construction projects, and lacks consideration of different process characteristics of the construction projects. In addition, the existing method can not accurately predict the daily traffic volume for the condition of road network congestion caused by the lack of daily traffic volume and the evaluation of the influence of the existing method on the material transportation vehicles.
Disclosure of Invention
The invention aims to: in order to overcome the defects in the prior art, the invention designs a daily traffic demand prediction model and provides a solving method for model parameters; considering fluctuation of construction procedures and personnel configuration plans in a construction area, classifying the procedures according to a time sequence rule of construction strength, and determining an influence coefficient of influence factors in the construction process on daily traffic demand of each procedure; meanwhile, a model based on data driving is constructed to evaluate the congestion degree of the traffic network around the construction area in the prediction period, and the daily traffic planning transfer quantity is calculated according to the congestion degree. The daily traffic quantity prediction model can more accurately predict the daily traffic demand quantity of a construction unit, is beneficial to dynamically realizing the management and monitoring of goods transportation vehicles entering and exiting each construction area daily, the planning of traffic organization routes and the transverse and longitudinal scheduling, sets reasonable traffic control measures for conflict points with larger traffic demand quantity, and ensures that traffic organization tasks fall to corresponding management staff, so that a schedule is effectively implemented.
The technical scheme is as follows: in order to solve the technical problems, the invention adopts the following technical scheme:
an intelligent building site traffic demand prediction method based on an artificial intelligence algorithm comprises the following steps:
(1) Calculating the daily average traffic demand, and constructing a project construction period traffic demand prediction model;
(2) Classifying the working procedures according to the time sequence rule of the construction strength, and determining the influence coefficient of the influence factors in the construction project process on the daily average traffic demand of each working procedure;
(3) Evaluating the congestion degree of the traffic network around the construction area in the prediction period, and calculating the daily traffic planning transfer quantity;
(4) And solving the daily traffic demand in the prediction period according to the solved influence coefficient and the daily traffic planning transfer quantity.
Preferably, in step (1), the project construction period traffic demand prediction model calculation method is as follows:
in which Q ij The material transport requirements for the jth process with the ith completion are required for future T days. For material demand Q ij On the known days of completion T, carrying capacity C of nth carrier n On the basis of (1), the daily traffic demand can be calculatedThe daily average traffic volume is the daily traffic demand volume obtained under the condition that each process task is uniformly distributed in a planning period.
Coefficient H dj The influence degree of factors such as the process progress, weather conditions, construction equipment technical level, construction personnel number and the like on the daily traffic is shown on the day j. H d The solution process of (2) will be specifically expanded in step (2).
Variable F d To represent the amount of traffic transfer for the system planning, and the traffic conditions used to describe the complex road network will also have an impact on the daily traffic of the cargo.
M is the maximum number of vehicles provided by the construction unit, and the daily traffic S is finally obtained d Should be less than the maximum number of vehicles M that can be provided by the construction unit.
Preferably, in the step (2), the method for selecting the input and output variables of the classifier model for classifying the procedure according to the time sequence rule of the construction strength comprises the following steps:
the invention classifies the time sequence rule of the construction strength of the working procedure according to four aspects of the history data, such as the construction progress requirement, the process characteristics, the mutual influence between adjacent working procedures and the number supply of personnel and supporting facilities, and the quantitative value method of the specific variables comprises the following steps:
the current construction period progress χ of the jth procedure j And engineering progress y j The expression of (2) is in percent.
Aiming at the quantitative analysis of the characteristics related to construction of the process, the invention selects the ratio s of the material with special requirements in the process materials j To express.
Aiming at the influence of the completion condition of adjacent working procedures on the engineering progress of the working procedures, the invention selects the variable w j-1 And w j+1 To characterize such features. w (w) j-1 Representing the effect of the last adjacent process on the progress of that process,wherein D is j-1 The number of days on which the task representing the last adjacent process was planned to be completed in the cycle,/for example>The task representing the last adjacent process is within the periodDays required for the actual completion. If w j-1 Negative number represents that the previous adjacent working procedure does not finish the task according to the plan, delay is needed, and a slowing effect exists on the progress of the working procedure; w (w) j-1 And the number is positive, represents the advanced completion plan of the last adjacent process, and promotes the development of the process. />Wherein ΔD represents the number of days that the task of the next adjacent process needs to be urgent or completion can be delayed, D j Representing the number of days planned to be completed in the cycle.
The on-schedule development of the process requires not only proper arrangement, but also sufficient investment of various professional construction teams and workers and various equipment and materials. The personnel construction configuration and the resource supply allocated to different processes by the project construction unit at each stage of the construction period are often different. For some projects with high priority, more manpower and material resources can be input into a construction unit in the early stage of the working procedure construction period; items with low priority are put into less resources in the same time period. Thus, the present invention employs discrete variables to separately express the supply of various types of resources.Wherein (1)>Material supply on behalf of shippers associated with the procedure, < >>Wherein N is g To theoretically require the amount of material for this process,indicating the amount of material that the actual supplier can supply to the process. />Constructor configuration of construction team> Wherein N is p For the number of people theoretically required for this procedure, < >>Indicating the number of people that the actual team can provide to the process; />Representing the supply of material resources such as construction equipment and the like>Wherein N is m For the transverse scheduling and construction of the procedure which is theoretically required, the number of equipment required, +.>Indicating the number of devices that can be provided to the process in the actual field.
In the aspect of selecting model output, the label Out put= {1,2,3} is defined as output directly according to the construction period and engineering progress relation of the case.
Wherein 1,2,3 represent 3 different relationships of construction period and engineering progress: early stage is slow and later stage is fast (Type 1), and the progress is basically unanimous (Type 2), early stage is fast and later stage is slow (Type 3). There is no priority or precedence between the relationships.
Because the change difference of the working procedure construction progress in the construction period is large, and the influence factors are numerous, the historical data cannot be accurately classified only according to the two-dimensional relation between the construction period and the engineering, and therefore the following sample label classification rules are set:
if m is 1 ＝0，
Preferably, in the step (2), the present invention trains the basic algorithm of the process classifier by using the SVM as a time sequence rule according to the construction strength, and has an input variable set for each process j And output variable output j And the process is classified more accurately by adopting a hierarchical two-classification method, whether the classification is Type1 is finished firstly, and then the classification of Type2 and Type3 is carried out.
Preferably, in the step (2), the method for solving the influence coefficient of the influence factor on the daily average traffic demand of each working procedure in the construction project process is as follows:
for each class of process, the Input variables that affect the coefficient model are other than Input j In addition to the factors of the people and the environment, the influence of the people and the environment on the engineering progress is considered.
The human influence is mainly reflected in the management efficiency of the construction unit, and if the construction site of the process lacks professional management staff or the professional level and quality of the management staff allocated to the process are low, the progress of the whole process is negatively affected. The invention selects the management efficiency m j To characterize the influence of the manager on the construction progress of the process j, the value of the variable is related to the conference communication frequency, the timeliness of information feedback and the time for solving the sudden problem.
Whether the working procedure can be carried out smoothly or not is also influenced by weather, especially the weather is limited on the construction process, and the cement mortar, various coatings and other finishing materials can be solidified and frozen when the air temperature is too low; when the rainfall is too high, mortar cement can be washed away and lost in the wall building engineering, pit and ditch water accumulation can occur, and the progress of the whole process is influenced because concrete is seriously washed away.The invention selects the duty ratio of the construction process restricted by weather in the process materialsTo express.
In summary, the input of the influence coefficient model is as follows:
for each class of process, the output variable of the influence coefficient model is the change between the actual daily traffic and the daily average traffic:
wherein S is dat For the actual daily traffic demand in the historical data, S da And (5) planning the daily average traffic demand.
The invention adopts a feedback neural network model as a model of training coefficients, and utilizes Input obtained by historical data 2j And H d And training a model.
Preferably, in the step (3), the method for evaluating the congestion degree of the traffic network around the construction area in the prediction period comprises the following steps:
firstly, predicting and fitting a daily traffic congestion index on a material transportation line by adopting an ARIMA algorithm, wherein the ARIMA model has the following structure:
in the method, in the process of the invention,ε t random interference sequences that are zero-mean white noise, and random interference is independent of past sequence values. X-shaped articles t-1 ,χ t-2 ,χ t-p To predict before the periodDaily traffic congestion index, coefficient on material transportation route of day pCan be obtained by fitting a regression model through SPSS.
The method for acquiring the daily traffic congestion index χ on the material transportation route comprises the following steps: taking 15 minutes as a statistical interval to obtain the average travel speed of each road section in the road network; according to the average travel speed grade division of road sections (see table 1), judging the running grade of each road section, namely counting the mileage proportion of the road section at the 5 th running level in the road of each grade; calculating the congestion mileage proportion of the regional (total) road network by using the weighting of the mileage (VKT), wherein the recommended value of the weighting coefficient is shown in table 2 and table 3; obtaining a 15-minute traffic congestion index based on a linear conversion relation between the 15-minute traffic congestion index and the congestion mileage proportion; and taking an arithmetic average value of the traffic congestion indexes of 15 minutes in the peak time period of the morning and evening to obtain a working day traffic congestion index, and taking an arithmetic average value of the traffic congestion indexes of 15 minutes in the period of 6:00am-22:00pm to obtain a holiday traffic congestion index. The average travel speed grade dividing method comprises the following steps: if the research road section is a expressway, the average travel speed is greater than 65km/h and is 1 level, greater than 50km/h and less than or equal to 65km/h and is 2 level, greater than 35km/h and less than or equal to 50km/h and is 3 level, greater than 20km/h and less than or equal to 35km/h and is 4 level, and less than or equal to 20km/h and is 5 level; if the research road section is a main road, the average travel speed is greater than 45km/h and is 1 level, greater than 35km/h and less than or equal to 45km/h and is 2 level, greater than 25km/h and less than or equal to 35km/h and is 3 level, greater than 15km/h and less than or equal to 25km/h and is 4 level, and less than or equal to 15m/h and is 5 level; if the research road section is a secondary trunk road, the average travel speed is greater than 35km/h and is 1 level, greater than 25km/h and less than or equal to 35km/h and is 2 level, greater than 15km/h and less than or equal to 25km/h and is 3 level, greater than 10km/h and less than or equal to 15km/h and is 4 level, and less than or equal to 10km/h and is 5 level; if the research road section is a branch, the average travel speed is greater than 35km/h and is 1 level, greater than 25km/h and less than or equal to 35km/h is 2 level, greater than 15km/h and less than or equal to 25km/h is 3 level, greater than 10km/h and less than or equal to 15km/h is 4 level, and less than or equal to 10km/h is 5 level.
Secondly, the congestion degree of traffic road networks around a construction area in a prediction period is evaluated, the traffic congestion condition of a road section can be divided into 5 grades according to China 'urban road traffic congestion evaluation index System', and 1-5 represent very smooth running, slight congestion, moderate congestion and serious congestion respectively. The grading rule is as follows: if the daily traffic congestion index is more than or equal to 0 and less than or equal to 2, the road network congestion level is 1; if the daily traffic congestion index is more than 2 and less than or equal to 4, the road network congestion level is 2; if the daily traffic congestion index is more than 4 and less than or equal to 6, the road network congestion level is 3; if the daily traffic congestion index is more than 6 and less than or equal to 8, the road network congestion level is 4; and if the daily traffic congestion index is more than 8 and less than or equal to 10, the road network congestion level is 5.
Preferably, in the step (3), the calculation rule of the daily traffic plan transition amount is:
setting a road congestion level reference E of a system planning transfer quantity according to historical empirical data base Transfer optimum percentage Δd; according to the daily traffic demand of each day in the prediction period obtained by the previous model, setting the congestion condition to be higher than the datum line E base The number of days of d h The traffic demand on each day isCongestion conditions below baseline E base The number of days of d I . The system plan transition amount for each day is then derived from the following equation:
the transfer is made during the planned period, at the system level, and the total transfer amount is kept to be 0 during the period. In traffic congestion sections, especially frequently congested intersections, mass-transit trucks will experience significant delays therein, thereby affecting the punctuality of the cargo traffic and the progress of the construction on the day. The more serious the traffic jam condition is, the more obvious the influence on construction production and subsequent procedures is, the daily average traffic demand The less likely it is to complete on time, and therefore the greater the amount of planning transfer required.
Preferably, in the step (4), the S constructed in the step (1) is carried in according to the influence coefficient solved in the step (2) and the daily traffic planning transfer solved in the step (3) d The model can be used for solving the daily traffic demand in the prediction period.
The beneficial effects are that: according to the intelligent building site traffic demand prediction method based on the artificial intelligence algorithm, from the aspects of process characteristics, material characteristics, personnel management, equipment supply and the like, complex relations between related variables and daily traffic demand are analyzed, and three modes of process change are determined: the process is classified by fast and then slow, uniform change and slow and then fast; aiming at each procedure under each type of mode, the influence coefficient influencing the fluctuation of the daily traffic demand in the construction area is explored, and H based on the neural network is developed and tested d A predictive model; meanwhile, the method also discusses that the congestion of the complex road network around the construction area adjusts the daily traffic demand, calculates the daily traffic planning transfer quantity, coordinates the daily traffic demand of each day in a short period on the basis of the existing transportation path and the medium-term planning, can promote the completion of the planning, and can more truly fit the actual field condition.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
FIG. 2 is an exemplary diagram of a process mode of an embodiment of the present invention; in the construction process, the time sequence rule of the construction strength can be roughly divided into three types of early stage, slow stage, late stage and slow stage (a), wherein the front and back progress is basically consistent (b), and the early stage, the fast stage and the slow stage (c).
Detailed Description
In order that the invention may be more readily understood, a more particular description of the invention will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
1-2 (a), (b) and (c), the intelligent construction site traffic demand prediction method based on the artificial intelligence algorithm disclosed by the embodiment of the invention comprises the following steps:
s1, calculating the daily average traffic demand, and constructing a project construction period traffic demand prediction model;
specifically, the material demand Q required to be completed by the ith process in the future T days is obtained according to a schedule ij On the known days of completion T, carrying capacity C of nth carrier n On the basis of (1), the daily traffic demand can be calculatedThe daily average traffic volume is the daily traffic demand volume obtained under the condition that each process task is uniformly distributed in a planning period.
The present embodiment assumes that there are three steps to be performed in the next prediction period, the prediction period is t=5 days, and the material demand required to be completed for each step is specifically:
in the present embodiment of the present invention,
comprehensively considering the influences of factors such as relevant process progress, weather conditions, construction equipment technical level, construction number and the like, the maximum number of vehicles M which can be provided by a construction unit, and the influence of the traffic conditions of a complex road network on daily traffic of goods, constructing a building construction daily traffic demand prediction model oriented to an intelligent building site, wherein the building construction daily traffic demand prediction model comprises the following steps:
s2, classifying the working procedures according to the time sequence rule of the construction strength, and determining the influence coefficient of the influence factors in the construction project process on the daily average traffic demand of each working procedure:
the invention classifies the time sequence rule of the construction strength of the working procedure according to four aspects of the history data, such as the construction progress requirement, the process characteristics, the mutual influence between adjacent working procedures and the number supply of personnel and supporting facilities, and the quantitative value method of the specific variables comprises the following steps:
the current construction period progress x of the jth procedure j And engineering progress y j The expression of (2) is in percent.
Aiming at the quantitative analysis of the characteristics related to construction of the process, the invention selects the ratio s of the material with special requirements in the process materials j To express.
Aiming at the influence of the completion condition of adjacent working procedures on the engineering progress of the working procedures, the invention selects the variable w j-1 And w j+1 To characterize such features. w (w) j-1 Representing the effect of the last adjacent process on the progress of that process,wherein D is j-1 The number of days on which the task representing the last adjacent process was planned to be completed in the cycle,/for example>The task representing the last adjacent process is actually completed for the required number of days in the cycle. If w j-1 Negative number represents that the previous adjacent working procedure does not finish the task according to the plan, delay is needed, and a slowing effect exists on the progress of the working procedure; w (w) j-1 And the number is positive, represents the advanced completion plan of the last adjacent process, and promotes the development of the process. />Wherein ΔD represents the number of days that the task of the next adjacent process needs to be urgent or completion can be delayed, D j Representing the number of days planned to be completed in the cycle.
For supply of various resourcesQuantitative description is made, wherein,material supply on behalf of shippers associated with the procedure, < >>Wherein N is g For the amount of material theoretically required for this procedure, < >>Indicating the amount of material that the actual supplier can supply to the process. />Constructor configuration of construction team>Wherein N is p For the number of people theoretically required for this procedure, < >>Indicating the number of people that the actual team can provide to the process; />Representing the supply of material resources such as construction equipment and the like>Wherein N is m For the transverse scheduling and construction of the procedure which is theoretically required, the number of equipment required, +.>Indicating the number of devices that can be provided to the process in the actual field.
In the aspect of selecting model Output, the label output= {1,2,3} is defined as Output directly according to the relation between the construction period and the engineering progress existing in the case.
Wherein 1,2,3 represent 3 different relationships of construction period and engineering progress: early stage is slow and later stage is fast (Type 1), and the progress is basically unanimous (Type 2), early stage is fast and later stage is slow (Type 3). There is no priority or precedence between the relationships.
Because the change difference of the working procedure construction progress in the construction period is large, and the influence factors are numerous, the historical data cannot be accurately classified only according to the two-dimensional relation between the construction period and the engineering, and therefore the following sample label classification rules are set:
if m is 1 ＝0，
The invention uses SVM as a basic algorithm for training a process classifier according to the time sequence rule of construction strength, and for each process j, an input variable set is provided And output variable output j And the process is classified more accurately by adopting a hierarchical two-classification method, whether the classification is Type1 is finished firstly, and then the classification of Type2 and Type3 is carried out.
The method for solving the influence coefficient of the influence factors on the daily average traffic demand of each procedure in the construction project process is as follows:
the inputs to the influence coefficient model are as follows:
wherein m is j For describing the construction of the working procedure j by the management personnelThe influence of the progress, the value of the variable is related to the communication frequency of the conference, the timeliness of information feedback and the time for solving the burst problem;is used for representing the duty ratio of the construction process which is limited by weather in the process materials.
For each class of process, the output variable of the influence coefficient model is the change between the actual daily traffic and the daily average traffic:
wherein S is dat For the actual daily traffic demand in the historical data, S da And (5) planning the daily average traffic demand.
The invention adopts a feedback neural network model as a model of training coefficients, and utilizes Input obtained by historical data 2j And H d And training a model.
And S3, evaluating the congestion degree of the traffic network around the construction area in the prediction period.
Firstly, predicting and fitting a daily traffic congestion index on a material transportation line by adopting an ARIMA algorithm, wherein the ARIMA model has the following structure:
in the method, in the process of the invention,ε t random interference sequences that are zero-mean white noise, and random interference is independent of past sequence values. X is x t-1 ,χ t-2 ,χ t-p To predict the daily traffic congestion index, coefficient, on the material transportation route p days before the periodFitting through SPSSAnd obtaining a regression model.
The method for acquiring the daily traffic congestion index χ on the material transportation route comprises the following steps: taking 15 minutes as a statistical interval to obtain the average travel speed of each road section in the road network; according to the average travel speed grade division of road sections (see table 1), judging the running grade of each road section, namely counting the mileage proportion of the road section at the 5 th running level in the road of each grade; calculating the congestion mileage proportion of the regional (total) road network by using the weighting of the mileage (VKT), wherein the recommended value of the weighting coefficient is shown in table 2 and table 3; obtaining a 15-minute traffic congestion index based on a linear conversion relation between the 15-minute traffic congestion index and the congestion mileage proportion; and taking an arithmetic average value of the traffic congestion indexes of 15 minutes in the peak time period of the morning and evening to obtain a working day traffic congestion index, and taking an arithmetic average value of the traffic congestion indexes of 15 minutes in the period of 6:00am-22:00pm to obtain a holiday traffic congestion index.
TABLE 1 average trip speed class classification for road segments
TABLE 2 recommended vehicle mileage (VKT) ratio (workday)
| Expressway | Main road | Secondary trunk road | Branch circuit | Totalizing | |
| Peak time period | 0.19 | 0.43 | 0.15 | 0.23 | 1.00 |
| Average over the whole day | 0.20 | 0.41 | 0.16 | 0.23 | 1.00 |
TABLE 3 recommended value for the mileage (VKT) ratio (weekend)
| Expressway | Main road | Secondary trunk road | Branch circuit | Totalizing | |
| Average over the whole day | 0.20 | 0.41 | 0.16 | 0.23 | 1.00 |
Secondly, the congestion degree of traffic networks around the construction area in the prediction period is evaluated, the traffic congestion condition of the road section can be divided into 5 grades (shown in table 1) according to China 'urban road traffic congestion evaluation index system', and 1 to 5 represent very smooth running, smoothness, slight congestion, moderate congestion and serious congestion respectively.
TABLE 4 road Congestion level and daily traffic Congestion index correspondence table (Unit: km/h)
| Road network congestion level | 1 | 2 | 3 | 4 | 5 |
| Daily traffic congestion index | [0,2] | (2,4] | (4,6] | (6,8] | (8,10] |
The calculation rule of the daily traffic planning transfer quantity is as follows:
setting a road congestion level reference E of a system planning transfer quantity according to historical empirical data base Transfer optimum percentage Δd; according to the daily traffic demand of each day in the prediction period obtained by the previous model, setting the congestion condition to be higher than the datum line E base The number of days of d h The traffic demand on each day isCongestion conditions below baseline E base The number of days of d l . The system plan transition amount for each day is then derived from the following equation:
in this embodiment, the road congestion level reference R base =4, Δd% =15%, the maximum number of vehicles M that the construction unit can provide, and the model predicts the road congestion level and the influence coefficient for each day as follows:
| t+1 | t+2 | t+3 | t+4 | t+5 | |
| road congestion level E d | 3 | 3 | 4 | 5 | 4 |
| Influence coefficient H d | 0.74 | 1.3 | 0.89 | 1.13 | 1.119 |
| D d ×H d | 26 | 45 | 31 | 39 | 39 |
The daily traffic plan transfer amount for each day is:
when d=t+4, E t+4 >E base ，
When d=t+1, d=t+2, E t+1 ＝E t+2 <E base ，
When d=t+3, d=t+5, E t+3 ＝E t+5 ＝E base ,F d ＝0。
S4, solving the daily traffic demand in the prediction period according to the solved influence coefficient and the daily traffic planning transfer quantity:
the calculated influence coefficient and the calculated daily traffic planning transfer quantity F d S of the carry-over construction d The model can solve the daily traffic demand in the prediction period, and specifically comprises the following steps:
it is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.
Claims (7)
1. An intelligent building site traffic demand prediction method based on an artificial intelligent algorithm is applied to an intelligent building site scene in an intelligent networking environment, and comprises the following steps:
s1, calculating the daily average traffic demand, and constructing a project construction period traffic demand prediction model;
s2, classifying the working procedures according to a time sequence rule of the construction strength, and determining an influence coefficient of influence factors in the construction project process on daily average traffic demand of each working procedure;
s3, evaluating the congestion degree of the traffic network around the construction area in the prediction period, and calculating the daily traffic planning transfer quantity;
s4, acquiring the daily traffic demand in the prediction period according to the solved influence coefficient and the daily traffic planning transfer quantity.
2. The intelligent building site traffic demand prediction method based on the artificial intelligence algorithm according to claim 1, wherein the daily average traffic demand D in step S1 d The method is characterized in that the method is obtained under the condition that each procedure and task are evenly distributed in a planning period:
in which Q ij The material transportation requirement amount which is finished by the ith process is needed by the jth process in the future T days; c (C) n Is the carrying capacity of the nth carrying tool.
3. The intelligent building site traffic demand prediction method based on the artificial intelligence algorithm as claimed in claim 2, wherein the daily traffic demand in step S4 is:
in the formula, the coefficient H dj The influence degree of factors of the process progress, weather conditions, construction equipment technical level and construction personnel number on the daily traffic is expressed on the day j;
variable F d To represent the traffic transfer volume planned by the system on the d day, and the traffic condition used for describing the complex road network will also have an effect on the daily traffic volume of goods;
m is the maximum number of vehicles which can be provided by the construction unit, and the daily traffic demand S is finally obtained d Should be less than the maximum number of vehicles M that can be provided by the construction unit.
4. The intelligent construction site traffic demand prediction method based on the artificial intelligence algorithm according to claim 1, wherein in step S2, the selection method of the input and output variables of the classifier model for classifying the procedures according to the time sequence rule of the construction strength is as follows:
the construction strength time sequence rule of the working procedure is classified by determining the four aspects of construction progress requirement, process characteristics, interaction between adjacent working procedures and quantity supply of personnel and supporting facilities from historical data, and the quantitative value method of the specific variables is as follows:
current work of j-th working procedureStage progress x j And engineering progress y j The expression of (2) is expressed in percent;
for quantitative analysis of the characteristics of the process, the ratio s of the material with special requirements in the process material is selected j To express;
aiming at the influence of the completion condition of the adjacent working procedure on the engineering progress of the working procedure, a variable w is selected j-1 And w j+1 To characterize such features; w (w) j-1 Representing the effect of the last adjacent process on the progress of that process,wherein D is j-1 The number of days on which the task representing the last adjacent process was planned to be completed in the cycle,/for example>The number of days required for the task representing the last adjacent process to be actually completed in the period; if w j-1 Negative number represents that the previous adjacent working procedure does not finish the task according to the plan, delay is needed, and a slowing effect exists on the progress of the working procedure; w (w) j-1 Is positive, represents the advanced completion plan of the last adjacent process, and promotes the expansion of the process; />Wherein ΔD represents the number of days that the task of the next adjacent process needs to be urgent or completion can be delayed, D j Representing the number of days planned to be completed in the period;
the on-schedule development of the working procedures not only needs proper arrangement, but also needs sufficient investment of various professional construction teams and workers and various devices and materials; the personnel construction configuration and the resource supply allocated to different working procedures by project construction units at each stage of construction period are often different; for some projects with high priority, more manpower and material resources can be input into a construction unit in the early stage of the working procedure construction period; items with low priority are put into less resources in the same time period; thus, the present invention employs discrete variables to separately express the supply of various resourcesGiving a situation;wherein (1)>Material supply on behalf of shippers associated with the procedure, < >>Wherein N is g For the amount of material theoretically required for this procedure, < >>Indicating the amount of material that the actual supplier can supply to the process; />Constructor configuration of construction team> Wherein N is p For the number of people theoretically required for this procedure, < >>Indicating the number of people that the actual team can provide to the process;representing the supply of material resources such as construction equipment and the like>Wherein N is m For the transverse scheduling and construction of the procedure which is theoretically required, the number of equipment required, +.>Indicating the number of devices that can be provided to the process in the actual field;
in the aspect of selecting model Output, directly defining a label output= {1,2,3} as Output according to the relation between the construction period and the engineering progress existing in the case;
wherein 1,2,3 represent 3 different relationships of construction period and engineering progress: early stage slow and late stage fast (Type 1), front and back progress basically consistent (Type 2), early stage fast and late stage slow (Type 3); the relationships have no priority and no sequence;
because the change difference of the working procedure construction progress in the construction period is large, and the influence factors are numerous, the historical data cannot be accurately classified only according to the two-dimensional relation between the construction period and the engineering, and therefore the following sample label classification rules are set:
if m is 1 ＝0，
Training a basic algorithm of a process classifier by using SVM as a time sequence rule according to construction strength, wherein for each process j, an input variable set is provided And output variable output j And the process is classified more accurately by adopting a hierarchical two-classification method, whether the classification is Type1 is finished firstly, and then the classification of Type2 and Type3 is carried out.
5. The intelligent construction site traffic demand prediction method based on the artificial intelligence algorithm as claimed in claim 1, wherein in the step S2, the method for solving the influence coefficient of the influence factor in the construction project process on the daily average traffic demand of each process is as follows:
for each class of process, the Input variables that affect the coefficient model are other than Input j The influence of people and environment on the engineering progress is considered in addition to the factors in (a);
the influence of people is mainly reflected in the management efficiency of a construction unit, and if the construction site of the process lacks professional management staff or the professional level and quality of the management staff which is distributed to be responsible for the process are low, the progress of the whole process can be negatively influenced; the invention selects the management efficiency m j Describing the influence of a manager on the construction progress of the process j, wherein the value of the variable is related to the conference communication frequency, the timeliness of information feedback and the time for solving the burst problem;
whether the working procedure can be carried out smoothly or not is also influenced by weather, especially the weather is limited on the construction process, and the cement mortar, various coatings and other finishing materials can be solidified and frozen when the air temperature is too low; when the rainfall is too high, mortar cement is washed away and lost in the wall building engineering, pit and ditch water accumulation can occur, and the progress of the whole process is influenced because concrete is seriously washed away; the invention selects the duty ratio of the construction process restricted by weather in the process materialsTo express;
in summary, the input of the influence coefficient model is as follows:
for each class of process, the output variable of the influence coefficient model is the change between the actual daily traffic and the daily average traffic:
wherein S is dat For the actual daily traffic demand in the historical data, S da The daily average traffic demand is planned;
the feedback neural network model is used as a model of training coefficients, and Input obtained by using historical data is utilized 2j And H d And training a model.
6. The intelligent construction site traffic demand prediction method based on the artificial intelligence algorithm according to claim 1, wherein in step S3, the method for evaluating the congestion degree of the traffic network around the construction area in the prediction period is as follows:
firstly, predicting and fitting a daily traffic congestion index on a material transportation line by adopting an ARIMA algorithm, wherein the ARIMA model has the following structure:
in the method, in the process of the invention,ε t random interference sequences that are zero-mean white noise, and the random interference is independent of past sequence values; x-shaped articles t-1 ,x t-2 ,x t-p To predict the daily traffic congestion index, coefficient, on the material transportation route p days before the periodCan be obtained by fitting a regression model through SPSS;
the method for acquiring the daily traffic congestion index x on the material transportation route comprises the following steps: taking 15 minutes as a statistical interval to obtain the average travel speed of each road section in the road network; judging the running grade of each road section according to the road section average travel speed grade dividing method; counting the mileage proportion of the road section at the 5 th level of operation in each level of road; calculating the congestion mileage proportion of the regional (total) road network by using the weighting of the mileage (VKT); obtaining a 15-minute traffic congestion index based on a linear conversion relation between the 15-minute traffic congestion index and the congestion mileage proportion; taking an arithmetic average value of the traffic congestion indexes of 15 minutes in the peak time period of the morning and evening to obtain a working day traffic congestion index, and taking an arithmetic average value of the traffic congestion indexes of 15 minutes in the period of 6:00am-22:00pm to obtain a holiday traffic congestion index; the average travel speed grade dividing method comprises the following steps: if the research road section is a expressway, the average travel speed is greater than 65km/h and is 1 level, greater than 50km/h and less than or equal to 65km/h and is 2 level, greater than 35km/h and less than or equal to 50km/h and is 3 level, greater than 20km/h and less than or equal to 35km/h and is 4 level, and less than or equal to 20km/h and is 5 level; if the research road section is a main road, the average travel speed is greater than 45km/h and is 1 level, greater than 35km/h and less than or equal to 45km/h and is 2 level, greater than 25km/h and less than or equal to 35km/h and is 3 level, greater than 15km/h and less than or equal to 25km/h and is 4 level, and less than or equal to 15m/h and is 5 level; if the research road section is a secondary trunk road, the average travel speed is greater than 35km/h and is 1 level, greater than 25km/h and less than or equal to 35km/h and is 2 level, greater than 15km/h and less than or equal to 25km/h and is 3 level, greater than 10km/h and less than or equal to 15km/h and is 4 level, and less than or equal to 10km/h and is 5 level; if the research road section is a branch, the average travel speed is greater than 35km/h and is 1 level, greater than 25km/h and less than or equal to 35km/h is 2 level, greater than 15km/h and less than or equal to 25km/h is 3 level, greater than 10km/h and less than or equal to 15km/h is 4 level, and less than or equal to 10km/h is 5 level;
secondly, the congestion degree of traffic road networks around a construction area in a prediction period is evaluated, the traffic congestion condition of a road section can be divided into 5 grades according to China 'urban road traffic congestion evaluation index System', and 1-5 represent very smooth running, smoothness, slight congestion, moderate congestion and serious congestion respectively; the grading rule is as follows: if the daily traffic congestion index is more than or equal to 0 and less than or equal to 2, the road network congestion level is 1; if the daily traffic congestion index is more than 2 and less than or equal to 4, the road network congestion level is 2; if the daily traffic congestion index is more than 4 and less than or equal to 6, the road network congestion level is 3; if the daily traffic congestion index is more than 6 and less than or equal to 8, the road network congestion level is 4; and if the daily traffic congestion index is more than 8 and less than or equal to 10, the road network congestion level is 5.
7. The intelligent building site traffic demand prediction method based on the artificial intelligence algorithm as claimed in claim 2, wherein in the step S3, the calculation rule of the daily traffic planning transfer amount is:
setting a road congestion level reference E of a system planning transfer quantity according to historical empirical data base Transfer optimum percentage Δd; according to the daily traffic demand of each day in the prediction period obtained by the previous model, setting the congestion condition to be higher than the datum line E base The number of days of d h The traffic demand on each day isCongestion conditions below baseline E base The number of days of d l The method comprises the steps of carrying out a first treatment on the surface of the The system plan transition amount for each day is then derived from the following equation:
making transfers during the planned period, at the system level, and keeping the total transfer volume should be 0 during the period; in traffic congestion road sections, particularly frequently-occurring congestion intersections, a large amount of delay occurs in a truck for transporting materials, so that the punctuality of cargo transportation and the construction progress of the same day are affected; the more serious the traffic jam condition is, the more obvious the influence on construction production and subsequent procedures is, the daily average traffic demand The less likely it is to complete on time, and therefore the greater the amount of planning transfer required.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310938580.8A CN116911464A (en) | 2023-07-27 | 2023-07-27 | Intelligent construction site traffic demand prediction method based on artificial intelligence algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310938580.8A CN116911464A (en) | 2023-07-27 | 2023-07-27 | Intelligent construction site traffic demand prediction method based on artificial intelligence algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911464A true CN116911464A (en) | 2023-10-20 |
Family
ID=88354736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310938580.8A Pending CN116911464A (en) | 2023-07-27 | 2023-07-27 | Intelligent construction site traffic demand prediction method based on artificial intelligence algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911464A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117789504A (en) * | 2024-02-28 | 2024-03-29 | 苏州申亿通智慧运营管理有限公司 | Intelligent commanding and dispatching method and system for urban tunnel traffic |
-
2023
- 2023-07-27 CN CN202310938580.8A patent/CN116911464A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117789504A (en) * | 2024-02-28 | 2024-03-29 | 苏州申亿通智慧运营管理有限公司 | Intelligent commanding and dispatching method and system for urban tunnel traffic |
| CN117789504B (en) * | 2024-02-28 | 2024-05-03 | 苏州申亿通智慧运营管理有限公司 | Intelligent commanding and dispatching method and system for urban tunnel traffic |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102044149B (en) | City bus operation coordinating method and device based on time variant passenger flows | |
| CN110097234B (en) | Intelligent dispatching method and system for industrial cigarette transportation | |
| CN109886491A (en) | A kind of routine bus system two stages Optimization Scheduling of magnanimity operation data driving | |
| CN105857350A (en) | High-speed rail train driving method based on section profile passenger flow | |
| CN116911464A (en) | Intelligent construction site traffic demand prediction method based on artificial intelligence algorithm | |
| CN109774750A (en) | A kind of dynamic dispatching space-time decision-making technique based on virtual coupled mode | |
| CN113919650A (en) | Train operation scheme optimization compilation method and system | |
| Zheng et al. | Urban logistics delivery route planning based on a single metro line | |
| Zhang et al. | An automatic real-time bus schedule redesign method based on bus arrival time prediction | |
| US6922593B2 (en) | Control of items in a complex system by using fluid models and solving continuous linear programs | |
| Miao et al. | Highly Automated Electric Vehicle (HAEV)-based mobility-on-demand system modeling and optimization framework in restricted geographical areas | |
| Zhang et al. | A dynamic shared bikes rebalancing method based on demand prediction | |
| US7433742B2 (en) | Control of items in a complex system by using fluid models and solving continuous linear programs | |
| CN112669595B (en) | Network taxi booking flow prediction method based on deep learning | |
| Oliskevych | Dynamic scheduling of highway cargo transportation | |
| CN108711028B (en) | Distributed computation-based solid waste classified transportation multistage cooperative decision making system | |
| He et al. | Machine Learning based integrated pedestrian facilities planning and staff assignment problem in transfer stations | |
| CN101697250B (en) | Modified method for predicting section, travel route and time of city bus | |
| Deng et al. | Research on bus passenger traffic forecasting model based on gps and ic card data | |
| Lu et al. | Comparing PROMODEL and SDESA in modeling construction operations | |
| Chen et al. | Regional public transportation scheduling model based on welfare economics and DEA | |
| CN115271260B (en) | Road-rail transport capacity prediction method, device, equipment and readable storage medium | |
| Puskás et al. | Conceptual framework for heavy-duty vehicle platooning in physical internet systems | |
| Burinskiene | The Concept Towards Transportation Infrastructure and Its Capacity | |
| Marunich et al. | Passenger transportation: reliable information support |
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 |