CN116739160A - Method and system for intelligently managing and controlling hub passenger flow space-time oriented to universe - Google Patents
Method and system for intelligently managing and controlling hub passenger flow space-time oriented to universe Download PDFInfo
- Publication number
- CN116739160A CN116739160A CN202310667332.4A CN202310667332A CN116739160A CN 116739160 A CN116739160 A CN 116739160A CN 202310667332 A CN202310667332 A CN 202310667332A CN 116739160 A CN116739160 A CN 116739160A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- passenger
- time
- hub
- density
- 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 58
- 238000012544 monitoring process Methods 0.000 claims abstract description 46
- 238000012546 transfer Methods 0.000 claims abstract description 18
- 238000007726 management method Methods 0.000 claims description 53
- 230000006870 function Effects 0.000 claims description 25
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 210000002569 neuron Anatomy 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 241000700605 Viruses Species 0.000 claims description 13
- 238000013461 design Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000002265 prevention Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 230000002776 aggregation Effects 0.000 claims description 11
- 238000004220 aggregation Methods 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 230000004308 accommodation Effects 0.000 claims description 3
- 238000012888 cubic function Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000452 restraining effect Effects 0.000 claims description 3
- 238000013215 result calculation Methods 0.000 claims description 3
- 230000008602 contraction Effects 0.000 claims 1
- 238000011176 pooling Methods 0.000 claims 1
- 238000013519 translation Methods 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000011217 control strategy Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000014599 transmission of virus Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000012795 verification 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- 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
- G06N3/048—Activation functions
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B11/00—Apparatus for validating or cancelling issued tickets
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Human Resources & Organizations (AREA)
- Computational Mathematics (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Algebra (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a universal-domain-oriented hub passenger flow space-time intelligent control method and system, comprising the following steps: s100, acquiring the number of passenger flows of the in-out station and the transfer passenger flows of the hub by combining the AFC data, the ticket purchasing data and the video monitoring data, and counting the number of the passenger flows at the passenger flow generation point in the unit time period; collecting historical passenger flow operation information and facility layout information in the hub, and predicting the density and flow of newly-increased passenger flow of the hub based on historical passenger flow data and real-time video monitoring data; s200, determining key nodes of each passenger flow passing path according to the type of facilities in the hub and the passenger flow route condition; s300, obtaining predicted passenger flow operation and facility distribution conditions on each passenger flow passing path, analyzing passenger flow passing characteristics, calculating newly-increased passenger flow passing time, and taking the newly-increased passenger flow passing time as a priority judgment basis of arrival sequence of key nodes; s400, generating a corresponding control scheme.
Description
Technical Field
The invention belongs to the technical field of hub traffic management, and particularly relates to a universal-domain-oriented hub passenger flow space-time intelligent management and control method and system.
Background
The hub plays a key role in urban traffic, and reasonable and effective traffic organization is a guarantee for the function of the hub. The junction venue is closed and has a complex structure, a large amount of passenger flows gather in the junction venue, and measures for reducing the virus transmission risk of the junction comprise disinfection, current limiting, station sealing, station throwing and the like. By controlling the passenger flow density in the hub, ensuring a certain social distance is a key to controlling the risk of virus transmission of the hub.
Existing hub passenger flow management is achieved by improving existing facilities, adjusting management and control strategies and planning and designing passenger flow paths so as to avoid passenger flow gathering in the hub. However, in the actual situation, the class of the hub is complex, the passenger flow attribute has larger difference, and the conventional management and control strategy implementation lacks effective theoretical guidance in consideration of the influence of the scale of the hub, and has poor universality. On the other hand, the traffic efficiency of the passenger flow is influenced by the layout structure in the station, the passenger flow evacuation network structure, traffic facilities and management strategies, and the organization and management of the passenger flow need to be designed by combining the traffic characteristics of the passenger flow, so that scientific basis is provided for formulating the passenger flow management strategies of the hub station. Meanwhile, the management and control strategy proposed by the published patent document (CN 111080016A) only aims at the passenger flow gathering nodes in the hub to independently formulate an evacuation strategy, and the connection of each node in the hub station is not considered, so that the passenger flow gathering phenomenon is easily transferred between the nodes, and the effectiveness of passenger flow management is difficult to ensure.
In combination with the reality condition, the method and the system are limited by the field scale of the junction, and part of the junction is difficult to spatially separate the passenger flow on the passenger flow transfer path, so the method and the system for intelligently managing and controlling the junction passenger flow time and space are creatively provided for the whole domain, and the time and the number of the passenger flow reaching each node in the junction field station are constrained by comprehensively considering the key nodes in the passenger flow passing process through identification, so that the aggregation density of the passenger flow is ensured to be at a lower level, and the risk of virus transmission is reduced.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a universal-domain-oriented hub passenger flow space-time intelligent control method and system.
The invention aims at realizing the following technical scheme:
a universal-domain-oriented hub passenger flow space-time intelligent management and control method comprises the following steps:
s100: the method comprises the steps of combining AFC data, ticket purchasing data and video monitoring data to obtain the number of passenger flows of a hub in-out station and passenger flows of a transfer station, regarding a hub entrance and a passenger-out station as passenger flow generating points, and counting the number of passenger flows of the passenger flow generating points in a unit time period; collecting historical passenger flow operation information and facility layout information in the hub, and predicting the density and flow of newly-increased passenger flow of the hub based on historical passenger flow data and real-time video monitoring data;
S200: according to the type of facilities in the hub and the condition of passenger flow routes, determining key nodes of each passenger flow passage path to serve as important references for subsequent passenger flow management and control;
s300: the method comprises the steps of obtaining predicted passenger flow operation and facility distribution conditions on each passenger flow passing path, analyzing passenger flow passing characteristics, calculating newly-increased passenger flow passing time, and taking the newly-increased passenger flow passing time as a priority judgment basis of key node passenger flow arrival sequence;
s400: according to the density and flow of the newly increased passenger flow of the hub predicted in the step S100; according to real-time video monitoring data of each key node, predicting the passenger flow density of the key node, determining the passenger flow arrival quantity allowed by each key node by calculating the passenger flow traffic capacity of each key node, and distributing the passenger flow arrival quantity to the passenger flow generation point and the key node by combining the passenger flow generation point to the key node and traffic characteristics among the key nodes to serve as the basis of passenger flow control in unit time, and generating a corresponding control scheme.
Further, the step S100 is specifically as follows:
s110: dividing passenger flows in the hub into three categories according to the traffic purpose of the passenger flows in the hub: inbound and outbound passenger flows and in-station transfer passenger flows; the in-station passenger flow, the in-station transfer downlink passenger flow and the out-station passenger flow and the in-station transfer uplink passenger flow respectively represent the passenger flow input and output of the hub;
The AFC data is used as passenger in-out data acquired and generated by the urban rail transit automatic fare collection system, and the number of passenger in-out in unit time can be obtained through the AFC data; acquiring the quantity of transfer passenger flows and the approximate flow direction of the passenger flows in the unit time of the hub according to the ticket purchase order information of the passengers;
s120: based on historical video monitoring data, collecting passenger flow density and flow in a hub, and establishing a short-time prediction model of the operation condition of the hub passenger flow by using a wavelet neural network, wherein the wavelet neural network structure is divided into an input layer, an hidden layer and an output layer 3; the input layer is passenger flow operation data for training and testing; the output layer is the operation data of the predicted passenger flow; the excitation function of the hidden layer adopts Morlet function, and the output result of the hidden layer is as follows:
x i input parameters, w, of neuron node i of input layer of wavelet neural network ij A is the weight between the input layer and the hidden layer j Wavelet basis function h for hidden layer neuron node j Is a scale factor of b j Wavelet basis function h for hidden layer neuron node j Is the number of nodes of the input layer and the hidden layer, and h j The specific form of (2) is as follows:
the output result calculation formula of the wavelet neural network is as follows:
w jk H (j) is the output value on the node of the j-th hidden layer, and m is the number of the nodes of the output layer;
calculating a prediction error e of the wavelet neural network, wherein yn (k) is an actual value, and y (k) is a predicted value of an output layer:
the weights and function coefficients are corrected by the resulting prediction error, in the following wayWeights between input layer and hidden layer at g iteration and g+1st iteration, respectively, ++>Weights between hidden layer and output layer at g iteration and g+1st iteration, respectively, ++>The expansion factor of the wavelet basis function h (j) of the h hidden layer neuron node at the g iteration and the g+1th iteration respectively, < ->The shift factor of the wavelet basis function h ((j) of the h hidden layer neuron node in the g iteration and the g+1th iteration respectively, and eta is the learning efficiency of the wavelet neural network:
the method mainly comprises the following steps:
s121: based on historical video monitoring data, passenger flow operation data are collected at 5min as time granularity for working days, non-working days and holidays respectively, and the collected passenger flow operation data are divided into a training set and a testing set;
s122: respectively applying wavelet neural networks to construct a short-term prediction model of the hinge passenger flow operation condition aiming at the working day, the non-working day and the holiday, applying a training set to train the short-term prediction model of the passenger flow operation condition, and applying a test set to verify the prediction precision of the short-term prediction model of the passenger flow operation condition;
S123: and extracting passenger flow operation data in the hub based on the real-time video monitoring data with 5min as time granularity, inputting a passenger flow operation condition short-time prediction model, and outputting predicted passenger flow operation data.
Further, setting a region of cross collection of passenger flows of walking facilities and distributed facilities as a key node; the walking facilities comprise channels, stairs, escalators, gate machines and security inspection facilities, and the distributed facilities comprise station halls and stations.
Further, the step S300 is specifically as follows:
s301: analyzing the key nodes through which the predicted passenger flows pass to obtain a passenger flow matrix R of each key node p p WhereinThe p number of the representative forward key node is u p Is a passenger flow of (1):
s302: the passenger flow in-out and transfer process involves a series of walking facilities and collecting and distributing facilities, including a platform F, a station hall H, a channel P, a stair S, an escalator E, a gate G and a security check facility C, the facilities are respectively numbered according to different facility types, and a passenger flow density matrix ρ of the facility at the moment t is defined t Passenger flow density matrix ρ t The inner element is the passenger flow density of the facilities corresponding to the respective numbers of different facility types;
s303: based on historical video monitoring data, passenger flow passing speed and density are collected, the relation between the passenger flow speed and the density is fitted, and a unitary cubic function is applied to describe the passenger flow passing speed of the facility.
S304: the key nodes and the passenger flow generating points and the key nodes are connected by walking facilities and distributed facilities, the time for the passenger flow to reach the key nodes is determined by the passenger flow passing characteristics of the facilities, and the passenger flow density matrix ρ of the facilities at the moment t is called t The passenger flow density of the facilities corresponding to the numbers of the different facility types in the building is calculated based on the S303 fitting result, and the number p of the key node is calculated to be u p Time of arrival of passenger flow at critical node
In the method, in the process of the invention,numbering u for the forward key node p p Y is the type of facility, n Y Number for facility of type Y, +.>Numbered n for time t Y Passenger flow density of facility Y, +.>Numbering u for the forward key node p p Whether or not to use the facility n in the passenger flow passing process Y Decision variables of->For facility n Y And delta T is delay time, and is caused by queuing, card swiping and security check operation, and is determined according to the actual traffic situation of the facility.
Further, S400 is specifically as follows:
s410: controlling the time of arrival of the passenger flow at the key node and the quantity of the passenger flow, and determining an optimized distribution model of the arrival time of the passenger flow and the quantity of the passenger flow;
s420: according to the optimized distribution model provided in the previous step, solving the distribution model by adopting a particle swarm algorithm;
S430: and (3) solving an optimal distribution model to obtain a distribution result, and matching with a management and control facility to realize the design of distribution model related variables, restraining the management and control of passenger flow generation points and key nodes on the time of passenger flow reaching the key nodes, and realizing the control by increasing the detour distance, guiding and controlling the passenger flow passing speed by staff and prohibiting the passing at set time.
Step S410 is specifically as follows:
s4101: the passenger flow density of the key nodes is a key index of virus prevention and control concern, and the passenger flow density control density ρ is set for each key node by combining the facility characteristics p ' Key node Density after predicting Δt timeConstraint management of passenger flows to critical node p is required, while +.>When the passenger flow density of the key node p meets the virus prevention and control requirements, the passenger flow is not required to be restrained;
generating a passenger flow density distribution thermodynamic diagram through video monitoring, taking a passenger flow density distribution peak value and a corresponding area thereof as a control basis, and specifically comprising the following steps of:
judging density peak value of monitoring areaWhether or not is greater than a guest flow control density ρ set by a critical node p ' if youNo control need be started; if->Further judging that the area is larger than the control density rho p ' aggregation area S sup The method comprises the steps of carrying out a first treatment on the surface of the If S sup Is larger than the high-density passenger flow centralized control area S p ' then require the actuation of the controls, if S sup ＜S p The management and control are not required to be started, and the staff is guided to evacuate the small-scale aggregation;
s4102: the congestion dissipation efficiency of the key nodes determines the time and the quantity of the constraint on the passenger flow, and the traffic capacity Q of the key nodes is determined according to the facility types of the key nodes and the congestion passenger flow dissipation rule p The amount of blocked passenger flow is expressed by the following formula:
in the method, in the process of the invention,for passenger flow u to critical node p p Arrival rate, per person/minute; />And->The number of blocked passengers on the key node p at the moments t and t+delta t; />And->The number of blocked passengers on the key node of the platform area F at the moment t and t+delta t; lambda (lambda) l The number of people on the train is permitted for train l;
s4103: considering the unbalance of passenger flow distribution in the hub, and on the premise of ensuring epidemic prevention safety, a passenger flow rate distribution model of each time period of passenger flow is formulated by taking the minimum total passenger flow delay time as a target:
equation (4-3) is an objective function,numbering u for the forward key node p p Is the number of passenger flows; />Numbering u for the forward key node p p Is the number of passenger flows; />Numbering u for the forward key node p p The number of times of passenger flow diversion; />And p is numbered u for the forward key node p The design of the d-th split passenger flow reaches the key node time; />Numbering u for the design to go to the critical node p p The number of passenger flows of the d-th partial flow, of ∈>Is numbered n Y The predicted passenger flow density of facility Y;
time of arrival of passenger flow design at critical nodeThe constraint of passing facilities and collecting and distributing facilities on the passing efficiency of the passenger flow is met, and the design time of the passenger flow reaching the key node is ensured to be not less than the time of the passenger flow reaching the key node under the constraint condition of the facilities by formulating the constraint (4-4); the sum of the number of divided passenger flows expressed by the formula (4-5) is equal to the number u of the key node p p Is the total number of passenger flows; (4-6) and (4-7) represent that the number of traffic arriving at the critical node or the station area critical node is not greater than the number of traffic permitted to be arrived at by the facility; and the passenger flow quantity of the passenger flow reaching the key node is selected by guiding the passenger flow to select other routes, so that the spatial diversion is realized, or the control requirement is realized by controlling the area to pass the number of people.
The invention also provides a universal-domain-oriented hub passenger flow space-time intelligent management and control system, which comprises:
the passenger flow monitoring unit comprises an AFC system, a ticket purchasing information detection system and a video monitoring system, wherein the AFC system is used for acquiring the passenger flow of a passenger flow entering and exiting a station within a set time, the ticket purchasing information detection system is used for acquiring the general flow direction of the passenger flow in a junction station, and the video monitoring system is used for preprocessing an image shot by a video and performing feature extraction and classification identification to complete statistics of the passenger flow and the passenger flow density;
The passenger flow data analysis unit is used for finishing training the wavelet neural network model by inputting passenger flow operation data acquired by the historical video monitoring data, storing models of different time, facilities, weather, workdays and rest day types, and finishing prediction of passenger flow operation conditions by the passenger flow data acquired by the passenger flow monitoring unit;
the passenger flow control decision unit predicts the passenger flow density of the subsequent time through the passenger flow density of the collected key nodes and compares the passenger flow density with the critical passenger flow density of the control implementation so as to judge whether to start the subsequent passenger flow control measures;
the passenger flow management and control scheme generating unit outputs an allocation result of each time period for allowing each passenger flow to go to the key node as a reference basis of a subsequent management and control scheme by inputting each passenger flow to the key node and the passenger flow accommodation capacity of the key node;
and the passenger flow management and control scheme feedback unit is used for generating a corresponding management and control scheme by referring to the generated passenger flow distribution scheme and transmitting the generated scheme to the hub management center.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the method is characterized in that the method for controlling the time-space intelligent control of the junction passenger flow facing the whole domain is realized when the processor executes the program.
The invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the universe-oriented hub passenger flow space-time intelligent management and control method.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1. according to the invention, passenger flow data of the junction are collected, characteristics and rules of passenger flow passing are analyzed to predict the passenger flow, a walking facility where the phenomenon of passenger flow aggregation in the junction is easy to occur and a passenger flow cross-gathering area of a distributed facility are set as key nodes, the passenger flow in the junction is managed and controlled in a multi-level manner according to the order of passing through the key nodes, and the time of each passenger flow reaching the key nodes and the number of the passenger flows are comprehensively managed.
2. The implementation of the invention can effectively guide the passenger flow management of the junction, and provides a theoretical basis for the comprehensive management of the passenger flow by establishing an optimized distribution model of the arrival time and the quantity of the passenger flow, and on the other hand, the key nodes in the junction are regarded as the whole comprehensive consideration to formulate a passenger flow management and control scheme, so that the phenomenon that the passenger flow gathering area is transferred and excessive pressure is increased for the passenger flow passing in other areas in the junction due to the adoption of passenger flow evacuation measures only aiming at a single passenger flow gathering area can be prevented. Meanwhile, the passenger flow space-time separation is realized by restraining the traffic quantity and time of the passenger flow in the junction, and the defect that the existing passenger flow space separation management and control has strict requirements on junction sites is overcome.
3. The invention can overcome the defect of delay in the starting of the existing passenger flow control by predicting the passenger flow running condition to decide whether to start the passenger flow control. The key nodes in the hub are identified to serve as main places for passenger flow management, so that 'point-to-point substitution surface' management and control are realized, the requirement of passenger flow management and control accuracy can be met, and the existing passenger flow data is fully utilized. In consideration of virus prevention and control, a method for judging the aggregation degree of the passenger flow is improved, the passenger flow local aggregation density is identified by using a passenger flow density distribution thermodynamic diagram to serve as a basis for management and control, the passenger flow density of key nodes is restrained, so that excessive aggregation of personnel is avoided, the risk of virus transmission is controlled, and meanwhile, the method has positive influence on the aspect of hub safety guarantee.
Drawings
FIG. 1 is a flow chart of a method for controlling the flow of the central passenger flow space-time intelligent control facing the whole domain in the embodiment;
FIG. 2 is a schematic diagram showing the connection relationship between the facilities of the passenger flow in the hub:
FIG. 3 is a network structure diagram of a short-term predictive model of the central button passenger flow behavior in the present embodiment;
FIG. 4 is a flow chart of the flow of the central passenger flow space-time intelligent control start decision in the embodiment facing the whole domain;
FIG. 5 is a schematic diagram of a system for controlling the space-time intelligent control of the hub passenger flow facing the whole domain in the embodiment;
FIG. 6 is a diagram showing a system configuration of a passenger flow monitoring unit in the present embodiment;
FIG. 7 is a block diagram of a system for controlling decision units of a guest flow according to the present embodiment.
Detailed Description
The invention is described in further detail below with reference to the drawings and the specific examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment provides a universal-domain-oriented hub passenger flow space-time intelligent control method, which has a flow shown in fig. 1 and comprises the following specific steps:
s100: the method comprises the steps of combining AFC data, ticket purchasing data and video monitoring data to obtain the number of passenger flows of a hub in-out station and passenger flows of a transfer station, regarding a hub entrance and a passenger-out station as passenger flow generating points, and counting the number of passenger flows of the passenger flow generating points in a unit time period; collecting historical passenger flow operation information and facility layout information in the hub, and predicting the flow and density of passenger flow generated by the hub based on historical passenger flow data and real-time video monitoring data;
s200: according to the type of facilities in the hub and the condition of passenger flow routes, determining key nodes of each passenger flow passage path to serve as important references for subsequent passenger flow management and control;
s300: the method comprises the steps of obtaining predicted passenger flow operation and facility distribution conditions on each passenger flow passing path, analyzing passenger flow passing characteristics, calculating newly generated passenger flow passing time, and taking the newly generated passenger flow passing time as a priority judgment basis of key node passenger flow arrival sequence;
S400: according to real-time video monitoring data of each key node, predicting the passenger flow density of the key node, determining the passenger flow arrival quantity allowed by each key node by calculating the passenger flow traffic capacity of each key node, and distributing the passenger flow arrival quantity to the passenger flow generation point and the key node by combining the passenger flow generation point to the key node and traffic characteristics among the key nodes to serve as the basis of passenger flow control in unit time, and generating a corresponding control scheme.
Specifically, the specific content of S100 is as follows:
s110: the passenger flow in the junction can be divided into three categories according to the passenger flow passing purposes in the junction, wherein the passenger flow passing purposes in the junction are different to cause different passing routes: inbound passenger flow, outbound passenger flow, in-station transfer passenger flow. The in-station passenger flow, the in-station transfer downlink passenger flow and the out-station passenger flow and the in-station transfer uplink passenger flow respectively represent the passenger flow input and output of the hub;
the AFC data is used as passenger in-out data acquired and generated by the urban rail transit automatic fare collection system, and the number of passenger in-out in unit time can be obtained through the AFC data. The number of the downstream passenger flows in the junction is relatively distributed in the space of the passenger flows, so that direct statistics is inconvenient, and the number of the upstream passenger flows and the downstream passenger flows in the junction unit time and the general flow direction of the passenger flows are obtained through the ticket purchase order information of passengers.
S120: based on historical video monitoring data, collecting passenger flow density and flow in a hub, and establishing a short-time prediction model of the operation condition of the hub by using a wavelet neural network, wherein the wavelet neural network structure is divided into an input layer, an hidden layer and an output layer 3 layers, as shown in fig. 3, the input layer adopts 4 neuron nodes, and the hidden layer adopts 6 neuron nodes; the input layer is passenger flow operation data for training and testing; the output layer is the operation data of the predicted passenger flow; the excitation function of the hidden layer adopts Morlet function, and the output result of the hidden layer is as follows:
x i input parameters, w, of neuron node i of input layer of wavelet neural network ij A is the weight between the input layer and the hidden layer j Wavelet basis function h for hidden layer neuron node j Is a scale factor of b j Wavelet basis function h for hidden layer neuron node j Is the number of nodes of the input layer and the hidden layer, and h j The specific form of (2) is as follows:
the output result calculation formula of the wavelet neural network is as follows:
w jk h ((j) is the output value on the node of the j-th hidden layer and m is the number of the nodes of the output layer) is the weight between the hidden layer and the output layer;
calculating a prediction error e of the wavelet neural network, wherein yn (k) is an actual value, and y (k) is a predicted value of an output layer:
The weights and function coefficients are corrected by the resulting prediction error, in the following wayFor the weights between the input layer and the hidden layer at the g-th iteration and the g+1th iteration,/o>For the weights between the hidden layer and the output layer at the g-th iteration and the g+1th iteration,/for>The expansion factor of the wavelet basis function h (j) of the h hidden layer neuron node at the g iteration and the g+1th iteration, < +.>For the shift factor of the wavelet basis function h (j) of the h hidden layer neuron node in the g iteration and the g+1th iteration, η is the learning efficiency of the wavelet neural network:
s121: based on historical video monitoring data, passenger flow operation data are collected at 5min as time granularity for working days, non-working days and holidays respectively, and the collected passenger flow operation data are divided into a training set and a testing set;
s122: respectively applying wavelet neural networks to construct a short-time prediction model of the operation condition of the passenger flow of the junction aiming at working days, non-working days and holidays, applying a training set to train the model, and applying a testing set to verify the prediction precision of the model;
s123: and extracting passenger flow operation data in the hub based on the real-time video monitoring data with 5min as time granularity, inputting the passenger flow operation data into a model, and outputting predicted passenger flow operation data.
Specifically, in step S200: the passenger flow needs to pass through various walking facilities and collecting facilities in the passing process, and finally arrives at a platform to prepare for taking a bus or finish the outbound through an outbound gate. Fig. 2 illustrates a connection relationship of a passenger flow passing through facilities in a certain hub, F, H, P, S, E, G, C represents a platform, a station hall, a passageway, a stair, an escalator, a gate and a security check facility, and subscript numerals represent facility numbers. The passenger flow passing efficiency on different facilities is different, and because the passenger flow passes continuously in the junction, people are likely to gather before facilities with poor passing efficiency to form crowd gathering so as to increase the risk of virus transmission, and the reasons such as unmatched facility passing capacity and unbalanced passenger flow distribution can cause the occurrence of passing bottlenecks, so that the passenger flow cross gathering areas of walking facilities and collecting and distributing facilities are set as key nodes; the walking facilities comprise channels, stairs, escalators, gate machines and security inspection facilities, and the distributed facilities comprise station halls and stations.
Specifically, the specific steps of S300 are as follows:
s301: analyzing the key nodes for predicting the passing of the passenger flow to obtain a passenger flow matrix R of each key node p p Wherein The p number of the representative forward key node is u p Is a passenger flow of (1):
s302: the process of entering and exiting the passenger flow and transferring the passenger flow involves a series of facilities including walking facilities and distributed facilities, namely a platform F, a station hall H, a channel P, a stair S, an escalator E, a gate G and a security check facility C, so that a passenger flow density matrix of the facilities at the moment t is defined, the passenger flow density matrix of the stairs is used for illustration,numbered n for time t s The passenger flow density of the stairs of the (a) considers that the difference exists between the characteristics of the passenger flow which goes up and down the stairs, so that the stairs which go up and down the stairs can be respectively seen for the stairs which pass in two directionsNumbering only ascending and descending unidirectional stairs:
s303: the passenger flow density of facilities can influence the passing efficiency of passenger flow, the passenger flow density of channels and stairs can obviously influence the selection of the walking speed of the passenger flow due to the high degree of freedom of the passenger flow, the escalator, the gate and the security inspection facilities are mainly limited by the passing capacity of the facilities, the passing speed is generally a fixed value, and the passenger flow delay is mainly caused by queuing caused by the accumulation of the passenger flow and also can be used as an important node for epidemic prevention control. Based on historical video monitoring data, the passenger flow passing speed and density are collected, the relation between the passenger flow speed and the density is fitted, the passenger flow passing speed of the facility is described by applying a unitary cubic function, and the relation between the passenger flow speed and the density of the stairs is described.
In the method, in the process of the invention,is numbered n s The density of the stairs in passenger flow is +.>Passenger flow speed->Is a parameter of the fit.
S304: the key nodes and the passenger flow generating points and the key nodes are connected by walking facilities and distributed facilities, the time for the passenger flow to reach the key nodes is determined by the passenger flow passing characteristics of the facilities, and the passenger flow density matrix ρ of the facilities at the moment t is called t The passenger flow density of the facilities corresponding to the numbers of the different facility types is based on S303Calculating the passenger flow passing speed according to the result, thereby calculating the number u of the p-oriented key node p Time of arrival of passenger flow at critical node
In the method, in the process of the invention,numbering u for the forward key node p p Y is the type of facility, n Y Number for facility of type Y, +.>Numbered n for time t Y Passenger flow density of facility Y, +.>Numbering u for the forward key node p p Whether or not to use the facility n in the passenger flow passing process Y Decision variables of->For facility n Y And delta T is delay time, and is caused by operations such as queuing, card swiping, security check and the like, and is determined according to the actual traffic situation of the facilities.
Specifically, the specific steps of S400 are as follows:
s410: the method comprises the following steps of controlling the arrival time of the passenger flow to the node and the quantity of the passenger flow, and determining an optimized distribution model of the arrival time of the passenger flow and the quantity of the passenger flow, wherein the optimized distribution model comprises the following contents:
S4101: the passenger flow density of the key nodes is a key index of virus prevention and control concern, and the passenger flow density control density ρ is set for each key node by combining the facility characteristics p ' Key node Density after predicting Δt timeConstraint management of passenger flows to critical node p is required, while +.>When the passenger flow density of the key node p meets the virus prevention and control requirements, the passenger flow is not required to be restrained;
the distribution of the passenger flows in the hub on facilities is uneven, the gate and the channel are used for explaining, the passenger flows need to be subjected to operations such as card swiping and coin inserting when passing through the gate, so that the passenger flows are easy to gather before the gate due to the difference of the passing efficiency, the passenger flows can be quickly accelerated to a normal level after passing through the gate, the gathering can be quickly dissipated, and the density of the passenger flows is obviously different before and after the facilities for the same facility; for the channel, the distribution of the passenger flow in the cross section is found to have the characteristics of high density in the middle area and low density of the passenger flow close to the wall at the two sides through field investigation. For the risk of viral transmission, localized excessive accumulation of passenger flow creates a greater risk.
In order to more properly describe the risk of virus transmission, the number of passengers and the area of the area monitored by video cannot be simply taken as the study object. Generating a passenger flow density distribution thermodynamic diagram through video monitoring, taking a passenger flow density distribution peak value and a corresponding area thereof as a control basis, wherein the specific process shown in fig. 4 is as follows:
Judging density peak value of monitoring areaWhether or not is greater than a guest flow control density ρ set by a critical node p ' if youNo control need be started; if->It is necessary to further determine that the area is greater than the control density ρ p ' aggregation area S sup The method comprises the steps of carrying out a first treatment on the surface of the If S sup A passenger flow high-density concentration control area S of more than or equal to p ' then require the actuation of the controls, if S sup ＜S p The management and control are not required to be started, and the staff is guided to evacuate the small-scale aggregation;
s4102: the congestion dissipation efficiency of the key nodes determines the time and the quantity of the constraint on the passenger flow, and the traffic capacity Q of the key nodes is determined according to the facility types of the key nodes and the congestion passenger flow dissipation rule p For key nodes of the platform area, passenger flows can be discharged only by taking trains, so that crowded passenger flows in the key nodes of the platform area are dissipated; considering the intermittent occurrence of traffic inside the hub and the explosive nature of traffic, the number of blocked traffic is expressed by the following formula:
in the method, in the process of the invention,for passenger flow u to critical node p p Arrival rate, per person/minute; />And->The number of blocked passengers on the key node p at the moments t and t+delta t; / >And->The number of blocked passengers on the key node of the platform area F at the moment t and t+delta t; lambda (lambda) l The number of people on the train is permitted for train l;
s4103: considering the unbalance of passenger flow distribution in the hub, and on the premise of ensuring epidemic prevention safety, a passenger flow rate distribution model of each time period of passenger flow is formulated by taking the minimum total passenger flow delay time as a target:
equation (4-3) is an objective function,numbering u for the forward key node p p Is the number of passenger flows; />Numbering u for the forward key node p p Is the number of passenger flows; />Numbering u for the forward key node p p The number of times of passenger flow diversion; />And p is numbered u for the forward key node p The design of the d-th split passenger flow reaches the key node time; />Numbering u for the design to go to the critical node p p The number of passenger flows of the d-th partial flow, of ∈>Is numbered n Y The predicted passenger flow density of facility Y;
the result of passenger flow right of way distribution influences the passing efficiency of passenger flow in facilities, the time for passenger flow design to reach key nodes should meet the constraint of passing facilities and collecting and distributing facilities on the passing efficiency of passenger flow, and the design time for passenger flow to reach key nodes is not less than the time for passenger flow to reach key nodes under the constraint condition of facilities by formulating constraint (4-4); equation (4-5) means that the sum of the number of split passenger flows should be equal to the number u of the forward key node p p Is the total number of passenger flows; (4-6) and (4-7) indicating that the amount of traffic arriving at the critical node or the critical node of the platform area is not greater than the amount of traffic permitted to be arrived at by the facility;
s420: aiming at the optimal distribution model provided by the invention, a heuristic algorithm is used for rapidly solving a large-scale problem, and a particle swarm algorithm is adopted for solving the model;
s430: for the distribution result obtained by solving the model, the design of the related variables of the model is realized by matching with a management and control facility, and the management and control of the time of the passenger flow reaching the node can be realized by increasing the detour distance, guiding and controlling the passenger flow passing speed by a worker, even prohibiting releasing at a specific time and other modes;
the number of the passenger flows reaching the nodes can be divided in space by guiding the passenger flows to select other routes, or the control requirement can be met by controlling the regional release number of people and the like.
A universe-oriented hub passenger flow space-time intelligent control system is shown in fig. 5, and comprises a passenger flow monitoring unit, a passenger flow data analysis unit, a passenger flow control decision unit, a passenger flow control scheme generation unit and a passenger flow control scheme feedback unit.
The passenger flow monitoring unit is shown in fig. 6, and comprises an AFC system, a ticket purchasing information detection system and a video monitoring system, wherein the AFC system is used for acquiring the passenger flow of the incoming and outgoing stations within a set time, the ticket purchasing information detection system is used for acquiring the general flow direction of the passenger flow in the junction station, and the video monitoring system is used for preprocessing the image shot by the video and performing feature extraction and classification identification to complete statistics of the passenger flow and the passenger flow density;
the passenger flow data analysis unit is used for finishing training the wavelet neural network model by inputting passenger flow operation data acquired by the historical video monitoring data, storing models of different time, facilities, weather, workdays and rest day types, and finishing prediction of passenger flow operation conditions by the passenger flow data acquired by the passenger flow monitoring unit;
the passenger flow control decision unit is shown in fig. 7 and comprises an initial control threshold setting module, a passenger flow density prediction module and a control decision feedback module. Predicting the passenger flow density of the subsequent time according to the acquired passenger flow density of the key node, and comparing the passenger flow density with the critical passenger flow density of the management and control implementation to judge whether to start the subsequent passenger flow management and control measures;
the passenger flow management and control scheme generating unit outputs an allocation result of each time period for allowing each passenger flow to go to the key node as a reference basis of a subsequent management and control scheme by inputting each passenger flow to the key node and the passenger flow accommodation capacity of the key node;
The passenger flow management and control scheme feedback unit generates a corresponding management and control scheme by referring to the generated passenger flow distribution scheme, and transmits the generated scheme to the hub management center.
The above examples of the present invention are only for describing the calculation model and calculation flow of the present invention in detail, and are not limiting of the embodiments of the present invention. It should be understood by those skilled in the art that other different types of changes or modifications may be made based on the above description, for example, considering the influence of the hub type and the passenger flow composition on the traffic efficiency, considering the influence of the epidemic prevention verification health code on the traffic, considering the influence of the train operation shift and the carrying capacity of other transportation modes, adjusting the traffic efficiency of the facility, etc., and all the embodiments cannot be exhausted herein, and all the obvious changes or modifications introduced by the technical scheme of the present invention are still within the scope of the present invention.
Finally, it should be pointed out that: the above examples are only intended to illustrate the computational process of the present invention and are not intended to be limiting. Although the invention has been described in detail with reference to the foregoing examples, it will be understood by those skilled in the art that the calculations described in the foregoing examples may be modified or equivalents substituted for some of the parameters thereof without departing from the spirit and scope of the calculation method of the invention.
The invention is not limited to the embodiments described above. The above description of specific embodiments is intended to describe and illustrate the technical aspects of the present invention, and is intended to be illustrative only and not limiting. Numerous specific modifications can be made by those skilled in the art without departing from the spirit of the invention and scope of the claims, which are within the scope of the invention.
Claims (9)
1. The utility model provides a pivot passenger flow space-time intelligent management and control method facing to the whole domain, which is characterized by comprising the following steps:
s100: the method comprises the steps of combining AFC data, ticket purchasing data and video monitoring data to obtain the number of passenger flows of a hub in-out station and passenger flows of a transfer station, regarding a hub entrance and a passenger-out station as passenger flow generating points, and counting the number of passenger flows of the passenger flow generating points in a unit time period; collecting historical passenger flow operation information and facility layout information in the hub, and predicting the density and flow of newly-increased passenger flow of the hub based on historical passenger flow data and real-time video monitoring data;
s200: according to the type of facilities in the hub and the condition of passenger flow routes, determining key nodes of each passenger flow passage path to serve as important references for subsequent passenger flow management and control;
S300: the method comprises the steps of obtaining predicted passenger flow operation and facility distribution conditions on each passenger flow passing path, analyzing passenger flow passing characteristics, calculating newly-increased passenger flow passing time, and taking the newly-increased passenger flow passing time as a priority judgment basis of key node passenger flow arrival sequence;
s400: according to the density and flow of the newly increased passenger flow of the hub predicted in the step S100; according to real-time video monitoring data of each key node, predicting the passenger flow density of the key node, determining the passenger flow arrival quantity allowed by each key node by calculating the passenger flow traffic capacity of each key node, and distributing the passenger flow arrival quantity to the passenger flow generation point and the key node by combining the passenger flow generation point to the key node and traffic characteristics among the key nodes to serve as the basis of passenger flow control in unit time, and generating a corresponding control scheme.
2. The method for intelligently managing and controlling the flow of hub passenger in space-time oriented to the whole domain according to claim 1, wherein the step S100 is specifically as follows:
s110: dividing passenger flows in the hub into three categories according to the traffic purpose of the passenger flows in the hub: inbound and outbound passenger flows and in-station transfer passenger flows; the in-station passenger flow, the in-station transfer downlink passenger flow and the out-station passenger flow and the in-station transfer uplink passenger flow respectively represent the passenger flow input and output of the hub;
The AFC data is used as passenger in-out data acquired and generated by the urban rail transit automatic fare collection system, and the number of passenger in-out in unit time can be obtained through the AFC data; acquiring the quantity of transfer passenger flows and the approximate flow direction of the passenger flows in the unit time of the hub according to the ticket purchase order information of the passengers;
s120: based on historical video monitoring data, collecting passenger flow density and flow in a hub, and establishing a short-time prediction model of the operation condition of the hub passenger flow by using a wavelet neural network, wherein the wavelet neural network structure is divided into an input layer, an hidden layer and an output layer 3; the input layer is passenger flow operation data for training and testing; the output layer is the operation data of the predicted passenger flow; the excitation function of the hidden layer adopts Morlet function, and the output result of the hidden layer is as follows:
x i input parameters, w, of neuron node i of input layer of wavelet neural network ij A is the weight between the input layer and the hidden layer j Wavelet basis function h for hidden layer neuron node j Is due to the expansion and contraction of (a)Son, b j Wavelet basis function h for hidden layer neuron node j Is the number of nodes of the input layer and the hidden layer, and h j The specific form of (2) is as follows:
the output result calculation formula of the wavelet neural network is as follows:
w jk H (j) is the output value on the node of the j-th hidden layer, and m is the number of the nodes of the output layer;
calculating a prediction error e of the wavelet neural network, wherein yn (k) is an actual value, and y (k) is a predicted value of an output layer:
the weights and function coefficients are corrected by the resulting prediction error, in the following wayWeights between input layer and hidden layer at g iteration and g+1st iteration, respectively, ++>Weights between hidden layer and output layer at g iteration and g+1st iteration, respectively, ++>The expansion factor of the wavelet basis function h (j) of the h hidden layer neuron node at the g iteration and the g+1th iteration respectively, < ->The translation factors of the wavelet basis functions h (j) of the h hidden layer neuron node in the g iteration and the g+1th iteration are respectively, and eta is the learning efficiency of the wavelet neural network:
the method mainly comprises the following steps:
s121: based on historical video monitoring data, passenger flow operation data are collected at 5min as time granularity for working days, non-working days and holidays respectively, and the collected passenger flow operation data are divided into a training set and a testing set;
s122: respectively applying wavelet neural networks to construct a short-term prediction model of the hinge passenger flow operation condition aiming at the working day, the non-working day and the holiday, applying a training set to train the short-term prediction model of the passenger flow operation condition, and applying a test set to verify the prediction precision of the short-term prediction model of the passenger flow operation condition;
S123: and extracting passenger flow operation data in the hub based on the real-time video monitoring data with 5min as time granularity, inputting a passenger flow operation condition short-time prediction model, and outputting predicted passenger flow operation data.
3. The method for intelligently managing and controlling the flow of central passenger in space-time oriented to the whole domain according to claim 1, wherein in step S200, the areas of cross-pooling of the passenger flows of walking facilities and distributed facilities are set as key nodes; the walking facilities comprise channels, stairs, escalators, gate machines and security inspection facilities, and the distributed facilities comprise station halls and stations.
4. The method for intelligently managing and controlling the flow of hub passenger in space-time oriented to the whole domain according to claim 1, wherein the step S300 is specifically as follows:
s301: analyzing the key nodes through which the predicted passenger flows pass to obtain a passenger flow matrix of each key node pR p WhereinThe p number of the representative forward key node is u p Is a passenger flow of (1):
s302: the passenger flow in-out and transfer process involves a series of walking facilities and collecting and distributing facilities, including a platform F, a station hall H, a channel P, a stair S, an escalator E, a gate G and a security check facility C, the facilities are respectively numbered according to different facility types, and a passenger flow density matrix ρ of the facility at the moment t is defined t Passenger flow density matrix ρ t The inner element is the passenger flow density of the facilities corresponding to the respective numbers of different facility types;
s303: based on historical video monitoring data, collecting passenger flow passing speed and density, fitting the relation between the passenger flow speed and the density, and describing the passenger flow passing speed of the facility by applying a unitary cubic function;
s304: the key nodes and the passenger flow generating points and the key nodes are connected by walking facilities and distributed facilities, the time for the passenger flow to reach the key nodes is determined by the passenger flow passing characteristics of the facilities, and the passenger flow density matrix ρ of the facilities at the moment t is called t The passenger flow density of the facilities corresponding to the numbers of the different facility types in the building is calculated based on the S303 fitting result, and the number p of the key node is calculated to be u p Time of arrival of passenger flow at critical node
In the method, in the process of the invention,numbering u for the forward key node p p Y is the type of facility, n Y Number for facility of type Y, +.>Numbered n for time t Y Passenger flow density of facility Y, +.>Numbering u for the forward key node p p Whether or not to use the facility n in the passenger flow passing process Y Decision variable, L nY For facility n Y And delta T is delay time, and is caused by queuing, card swiping and security check operation, and is determined according to the actual traffic situation of the facility.
5. The method for intelligently managing and controlling the flow of hub passenger in space time oriented to the whole domain according to claim 1, wherein the step S400 is specifically as follows:
s410: controlling the time of arrival of the passenger flow at the key node and the quantity of the passenger flow, and determining an optimized distribution model of the arrival time of the passenger flow and the quantity of the passenger flow;
s420: according to the optimized distribution model provided in the previous step, solving the distribution model by adopting a particle swarm algorithm;
s430: and (3) solving an optimal distribution model to obtain a distribution result, and matching with a management and control facility to realize the design of distribution model related variables, restraining the management and control of passenger flow generation points and key nodes on the time of passenger flow reaching the key nodes, and realizing the control by increasing the detour distance, guiding and controlling the passenger flow passing speed by staff and prohibiting the passing at set time.
6. The method for intelligently managing and controlling global hub passenger flows according to claim 5, wherein step S410 is specifically as follows:
s4101: the passenger flow density of key nodes is concerned with virus prevention and controlKey indexes and facility characteristics are combined to set passenger flow density control density rho for each key node p ' Key node Density after predicting Δt time Constraint management of passenger flows to critical node p is required, while +.>When the passenger flow density of the key node p meets the virus prevention and control requirements, the passenger flow is not required to be restrained;
generating a passenger flow density distribution thermodynamic diagram through video monitoring, taking a passenger flow density distribution peak value and a corresponding area thereof as a control basis, and specifically comprising the following steps of:
judging density peak value of monitoring areaWhether or not is greater than a guest flow control density ρ set by a critical node p ' if>No control need be started; if->Further judging that the area is larger than the control density rho p ' aggregation area S sup The method comprises the steps of carrying out a first treatment on the surface of the If S sup Is larger than the high-density passenger flow centralized control area S p ' then require the actuation of the controls, if S sup ＜S p The management and control are not required to be started, and the staff is guided to evacuate the small-scale aggregation;
s4102: the congestion dissipation efficiency of the key nodes determines the time and the quantity of the constraint on the passenger flow, and the traffic capacity Q of the key nodes is determined according to the facility types of the key nodes and the congestion passenger flow dissipation rule p The amount of blocked passenger flow is expressed by the following formula:
in the method, in the process of the invention,for passenger flow u to critical node p p Arrival rate, per person/minute; />And->The number of blocked passengers on the key node p at the moments t and t+delta t; / >And->The number of blocked passengers on the key node of the platform area F at the moment t and t+delta t; lambda (lambda) l The number of people on the train is permitted for train l;
s4103: considering the unbalance of passenger flow distribution in the hub, and on the premise of ensuring epidemic prevention safety, a passenger flow rate distribution model of each time period of passenger flow is formulated by taking the minimum total passenger flow delay time as a target:
equation (4-3) is an objective function,numbering u for the forward key node p p Is the number of passenger flows; />Numbering u for the forward key node p p Is the number of passenger flows; />Numbering u for the forward key node p p The number of times of passenger flow diversion; />And p is numbered u for the forward key node p The design of the d-th split passenger flow reaches the key node time; />Numbering u for the design to go to the critical node p p The number of passenger flows of the d-th partial flow, of ∈>Is numbered n Y The predicted passenger flow density of facility Y;
the time for the passenger flow to reach the key node is required to meet the constraint of the passing facilities and the collecting and distributing facilities on the passing efficiency of the passenger flow, and the time for the passenger flow to reach the key node is ensured to be not less than the time for the passenger flow to reach the key node under the constraint condition of the facilities by making constraint (4-4); the sum of the number of divided passenger flows expressed by the formula (4-5) is equal to the number u of the key node p p Is the total number of passenger flows; (4-6) and (4-7) represent that the number of traffic arriving at the critical node or the station area critical node is not greater than the number of traffic permitted to be arrived at by the facility; the passenger flow quantity of passenger flow reaching the key node is divided into different routes by guiding the passenger flow to realize space division or control the areaThe control requirement is realized by passing the number of people.
7. The utility model provides a pivot passenger flow space-time intelligent management and control system towards universe which characterized in that includes:
the passenger flow monitoring unit comprises an AFC system, a ticket purchasing information detection system and a video monitoring system, wherein the AFC system is used for acquiring the passenger flow of a passenger flow entering and exiting a station within a set time, the ticket purchasing information detection system is used for acquiring the general flow direction of the passenger flow in a junction station, and the video monitoring system is used for preprocessing an image shot by a video and performing feature extraction and classification identification to complete statistics of the passenger flow and the passenger flow density;
the passenger flow data analysis unit is used for finishing training the wavelet neural network model by inputting passenger flow operation data acquired by the historical video monitoring data, storing models of different time, facilities, weather, workdays and rest day types, and finishing prediction of passenger flow operation conditions by the passenger flow data acquired by the passenger flow monitoring unit;
The passenger flow control decision unit predicts the passenger flow density of the subsequent time through the passenger flow density of the collected key nodes and compares the passenger flow density with the critical passenger flow density of the control implementation so as to judge whether to start the subsequent passenger flow control measures;
the passenger flow management and control scheme generating unit outputs an allocation result of each time period for allowing each passenger flow to go to the key node as a reference basis of a subsequent management and control scheme by inputting each passenger flow to the key node and the passenger flow accommodation capacity of the key node;
and the passenger flow management and control scheme feedback unit is used for generating a corresponding management and control scheme by referring to the generated passenger flow distribution scheme and transmitting the generated scheme to the hub management center.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the globally oriented hub passenger flow space-time intelligent management method of any of claims 1 to 6 when the program is executed by the processor.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the universe oriented hub passenger flow space-time intelligent control method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310667332.4A CN116739160A (en) | 2023-06-06 | 2023-06-06 | Method and system for intelligently managing and controlling hub passenger flow space-time oriented to universe |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310667332.4A CN116739160A (en) | 2023-06-06 | 2023-06-06 | Method and system for intelligently managing and controlling hub passenger flow space-time oriented to universe |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116739160A true CN116739160A (en) | 2023-09-12 |
Family
ID=87905519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310667332.4A Pending CN116739160A (en) | 2023-06-06 | 2023-06-06 | Method and system for intelligently managing and controlling hub passenger flow space-time oriented to universe |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116739160A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172513A (en) * | 2023-11-03 | 2023-12-05 | 北京市运输事业发展中心 | Comprehensive transportation hub capacity scheduling system based on big data |
| CN117273285A (en) * | 2023-11-21 | 2023-12-22 | 北京市运输事业发展中心 | Passenger transport data acquisition system based on large passenger flow station of rail transit |
-
2023
- 2023-06-06 CN CN202310667332.4A patent/CN116739160A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172513A (en) * | 2023-11-03 | 2023-12-05 | 北京市运输事业发展中心 | Comprehensive transportation hub capacity scheduling system based on big data |
| CN117172513B (en) * | 2023-11-03 | 2024-02-02 | 北京市运输事业发展中心 | Comprehensive transportation hub capacity scheduling system based on big data |
| CN117273285A (en) * | 2023-11-21 | 2023-12-22 | 北京市运输事业发展中心 | Passenger transport data acquisition system based on large passenger flow station of rail transit |
| CN117273285B (en) * | 2023-11-21 | 2024-02-02 | 北京市运输事业发展中心 | Passenger transport data acquisition system based on large passenger flow station of rail transit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116739160A (en) | Method and system for intelligently managing and controlling hub passenger flow space-time oriented to universe | |
| Xu et al. | Capacity-oriented passenger flow control under uncertain demand: Algorithm development and real-world case study | |
| Wang et al. | Passenger-demands-oriented train scheduling for an urban rail transit network | |
| CN103632212B (en) | System and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow | |
| Yuan et al. | Passenger flow control strategies for urban rail transit networks | |
| Hadas et al. | Public-transit frequency setting using minimum-cost approach with stochastic demand and travel time | |
| CN107248006B (en) | Subway line passenger flow coordination control method based on hierarchical hierarchy | |
| Binart et al. | A 2-stage method for a field service routing problem with stochastic travel and service times | |
| CN105404850A (en) | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method | |
| CN108846514B (en) | Method for predicting demand of rail transit passenger flow evacuation in emergency | |
| CN115527369B (en) | Large passenger flow early warning and evacuation method under large-area delay condition of airport hub | |
| CN113850417A (en) | Passenger flow organization decision-making method based on station passenger flow prediction | |
| CN112488400A (en) | Traffic travel behavior regulation and control method based on block chain technology and travel plan sharing | |
| CN114037158A (en) | Passenger flow prediction method based on OD path and application method | |
| CN109872008A (en) | Urban Rail Transit safety evaluation and Enhancement Method based on bus traveler assignment | |
| Wang et al. | Smart dispatching and optimal elevator group control through real-time occupancy-aware deep learning of usage patterns | |
| Mutlu et al. | COVID-19 transmission risk minimization at public transportation stops using Differential Evolution algorithm | |
| Wang et al. | An Ensemble Learning Model for Short‐Term Passenger Flow Prediction | |
| CN113408926B (en) | Urban rail transit passenger flow distribution method under short interruption condition | |
| Mei et al. | A paradigm of intelligent evacuation route decision for metro station emergence based on social media | |
| CN116451867A (en) | Subway short-time passenger flow prediction method based on space-time travel path calibration | |
| CN111862637B (en) | Traffic information control method, system, storage medium, computer device, and terminal | |
| Ayman et al. | Neural Architecture and Feature Search for Predicting the Ridership of Public Transportation Routes | |
| Dou et al. | A cloud model-based method for passenger flow control at subway stations: A real-world case study | |
| Yang et al. | Temporal and spatial evolution of passenger flow in an urban rail transit network during station closure |
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 |