CN116443080B - Rail transit driving dispatching command method, system, equipment and medium - Google Patents
Rail transit driving dispatching command method, system, equipment and medium Download PDFInfo
- Publication number
- CN116443080B CN116443080B CN202310497726.XA CN202310497726A CN116443080B CN 116443080 B CN116443080 B CN 116443080B CN 202310497726 A CN202310497726 A CN 202310497726A CN 116443080 B CN116443080 B CN 116443080B
- Authority
- CN
- China
- Prior art keywords
- train
- running
- driving
- rail transit
- influence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000002159 abnormal effect Effects 0.000 claims abstract description 94
- 238000010586 diagram Methods 0.000 claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000008520 organization Effects 0.000 claims abstract description 6
- 238000005457 optimization Methods 0.000 claims description 31
- 238000012544 monitoring process Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000002787 reinforcement Effects 0.000 claims description 6
- 230000007306 turnover Effects 0.000 claims description 5
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000007726 management method Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 13
- 230000003993 interaction Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/10—Operations, e.g. scheduling or time tables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/04—Automatic systems, e.g. controlled by train; Change-over to manual control
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a method, a system, equipment and a medium for dispatching and commanding rail transit driving, and relates to the field of train operation organization. The method comprises the following steps: determining basic line parameters and planning operation data of a rail transit system, and acquiring comprehensive operation state information of the rail transit system; identifying an abnormal event according to the comprehensive running state information, and determining the influence of the abnormal event on running and the running situation of the train; according to basic line parameters, planning operation data, influence of abnormal events on driving and train operation situation, a dynamic train operation diagram is formulated; and generating and issuing a scheduling instruction according to the dynamic train running diagram. The invention can promote the automation degree of the track traffic dispatching command system from four aspects of information acquisition, information analysis, dispatching decision and dispatching instruction generation so as to adapt to fine management, enhance the emergency handling capability of abnormal events and effectively reduce the influence on passenger service.
Description
Technical Field
The invention relates to the field of train operation organization, in particular to a rail transit driving dispatching command method, a system, equipment and a medium.
Background
The rail transit has the characteristic of rapidness and punctuality, and is an important component of modern public transit. The urban rail is greatly developed, and the ground traffic pressure can be effectively relieved by constructing a comprehensive, green, safe and intelligent three-dimensional modern traffic system. The track traffic dispatching command is a special (dispatching) mechanism established by a transportation department, the organization and the command of daily transportation production of the track traffic are uniformly implemented, and the safety and the quasi-point operation of the train are ensured. Because the rail transit system is complex and huge, a person is difficult to schedule multiple resources at the same time, the rail transit system is divided into a plurality of professions/fields, different scheduling posts are arranged, and different resources are respectively scheduled. As a "brain" of a rail transit system, the importance of the dispatcher is self-evident.
Taking a full-automatic driving system as an example, the dispatching objects can be divided into three types of systems, information and driving. The dispatch posts associated with the system include power dispatch and environmental control dispatch, the dispatch posts associated with the information include passenger dispatch and information dispatch, and the dispatch posts associated with the drive include drive dispatch, vehicle dispatch, and vehicle base dispatch. Rail transit is a complex system that aims at serving passengers, whereas vehicles as the main carrier for transporting passengers are one of the important equipment for interacting with passengers, and is also the core of the whole system. Accordingly, driving is the most critical among three types of scheduling objects. Therefore, the rail traffic scheduling command takes the driving scheduling as the core, and each professional/department is tightly matched to finish the same macroscopic operation plan together and efficiently. Along with the continuous increase of passenger flow demands and newly-built lines, rail traffic operation is changed from single line to network, and the improvement of operation scale and driving density brings serious challenges to dispatching and commanding. Therefore, the intelligent level of the track traffic dispatching command system is improved, and the emergency handling capability of the abnormal event is enhanced, which is one of the important research directions of the track traffic system at present.
The track traffic fault causes and scenes are complex and various, the evolution process is very complex, and particularly under the condition of complex network and even a plurality of node faults, a dispatcher can not accurately judge the influence caused by the faults by depending on experience. Meanwhile, fault information collection and disposal means are limited, granularity of alarm information is insufficient, fault diagnosis efficiency is affected, a dispatcher needs to conduct a large amount of information interaction with equipment and personnel in the fault disposal process, and randomness and ambiguity of the information increase difficulty of fault influence analysis.
In addition, the formulation of an abnormal event handling scheme is a complex decision, and numerous factors such as fault type, fault influence range, time required for fault handling, train running interval and the like need to be considered. In the current actual operation process, the generation of a fault treatment scheme mainly depends on the experience of a dispatcher and manual analysis and treatment, the abnormal treatment operation is numerous, and the problems of incomplete information grasp, easy omission and the like exist. Meanwhile, the capability layers of the schedulers are uneven, the familiarity degree of part of the schedulers to equipment is low, necessary fault handling experience is lacked, and the problems of untimely trip response, improper handling and the like are easy to occur.
Finally, under the condition of abnormal events and disordered operation order, a dispatcher needs to comprehensively consider space-time factors, available resources and time given by a dispatching instruction, balance various operation indexes and form an operation diagram adjustment scheme in a short time. As the train running interval is further reduced, the propagation speed of the fault influence is increased, the number of affected trains and passengers is increased, and it is difficult for a dispatcher to form an optimal disposal strategy in a short time.
In summary, the existing rail transit driving dispatching command mode has the following defects:
1. the reasons and scenes of the abnormal events of the rail transit are complex and various, and at present, the driving dispatcher can not accurately analyze the influence range of the abnormal events by means of limited information and experience.
2. After an abnormal event occurs, the mode that the running diagram is manually adjusted by a running dispatcher has individual differences, and the problems of untimely reaction, improper treatment and the like easily occur.
3. The factors and resource constraints involved in the adjustment of the running diagram are complex, and the reduction of the train running interval leads to an increase in the number of affected trains and passengers, which makes it difficult for the dispatcher to form an optimal disposal strategy in a short time.
Disclosure of Invention
The invention aims to provide a method, a system, equipment and a medium for dispatching and commanding rail transit driving so as to realize automatic dispatching and commanding of rail transit driving, enhance the emergency handling capability of abnormal events and reduce the influence on passenger service.
In order to achieve the above object, the present invention provides the following solutions:
a dispatching command method for rail transit driving comprises the following steps:
determining basic line parameters and planning operation data of a rail transit system, and acquiring comprehensive operation state information of the rail transit system;
identifying an abnormal event according to the comprehensive running state information, and determining the influence of the abnormal event on running and the running situation of the train; the exception event includes: train delay, equipment and facility failure, sudden large passenger flow and abnormal external environment;
according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation, a dynamic train operation diagram is formulated;
and generating and issuing a scheduling instruction according to the dynamic train running diagram.
Optionally, determining basic line parameters and planning operation data of the rail transit system, and acquiring comprehensive operation state information of the rail transit system, which specifically includes:
determining basic line parameters of the rail transit system according to the actual line conditions of the rail transit system;
according to the operation condition of the rail transit system, determining the plan operation data of the rail transit system;
and acquiring the running state information of an electromechanical equipment monitoring system, an electric power monitoring system, a train running control system, a passenger information system and an environment monitoring system of the rail transit system, and converting unstructured information in the running state information into structured information to obtain comprehensive running state information.
Optionally, identifying an abnormal event according to the comprehensive running state information, and determining the influence of the abnormal event on running and the running situation of the train specifically includes:
identifying an abnormal event based on a neural network algorithm according to the comprehensive operation state information;
according to the comprehensive running state information, a knowledge graph oriented to track traffic driving scheduling is constructed, and the influence of an abnormal event on driving is determined according to the knowledge graph; the influence of the abnormal event on the driving comprises the following steps: the highest running speed of the train, the minimum train tracking interval, available train resources, the number of affected trains and the affected line area;
and determining the train running situation based on a discrete event dynamic system according to the influence of the abnormal event on the running.
Optionally, identifying an abnormal event based on a neural network algorithm according to the comprehensive operation state information specifically includes:
determining the type and duration of the abnormal event based on a neural network algorithm according to the comprehensive running state information;
determining the severity of the abnormal event according to the type and duration of the abnormal event;
and classifying and displaying different abnormal events according to the set processing priority and the severity.
Optionally, a dynamic train operation chart is formulated according to the basic line parameters, the plan operation data, the influence of the abnormal event on driving and the train operation situation, and the dynamic train operation chart specifically comprises:
constructing a discrete space-time network according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation;
taking the minimum linear weighted sum of each operation index as an objective function, and establishing a multi-objective mathematical optimization model based on the discrete space-time network; the operation indexes comprise: train delay time, number of cancelled train number, number of midway turn-back train number and passenger waiting time; the constraint conditions of the multi-objective mathematical optimization model comprise: network flow constraint, underbody turnover constraint, arrival/departure time constraint, service station constraint, stop time constraint, line resource constraint and train running situation constraint;
and solving the multi-objective mathematical optimization model by adopting a large-scale distributed solving method based on data driving to obtain a dynamic train running diagram.
Optionally, a data-driven large-scale distributed solving method is adopted to solve the multi-objective mathematical optimization model to obtain a dynamic train running diagram, which specifically comprises the following steps:
performing decentralized processing on the objective function and the constraint condition of the multi-objective mathematical optimization model by taking the train number as a unit to obtain a plurality of sub-optimization models;
performing simulation on train operation based on the discrete space-time network to obtain simulation data;
determining a train operation adjustment strategy according to the simulation data by adopting a reinforcement learning method;
and applying the train operation adjustment strategy, and sequentially solving each sub-optimization model according to the morning and evening of the departure time to obtain a dynamic train operation diagram.
Optionally, the scheduling instruction includes: electromechanical equipment scheduling instructions, power equipment scheduling instructions, driving equipment scheduling instructions, train operation information and passenger flow organization guiding information; the driving equipment scheduling instruction comprises: and (3) adjusting to time division, stop train number, start train number, on-line of a spare vehicle, change train operation intersection, midway turning back and single-line bidirectional operation.
A rail transit ride scheduling command system, comprising:
the information acquisition subsystem is used for determining basic line parameters and planning operation data of the rail transit system and acquiring comprehensive operation state information of the rail transit system;
the information analysis subsystem is used for identifying abnormal events according to the comprehensive running state information and determining the influence of the abnormal events on running and the running situation of the train; the exception event includes: train delay, equipment and facility failure, sudden large passenger flow and abnormal external environment;
the scheduling decision subsystem is used for making a dynamic train operation diagram according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation;
and the scheduling instruction generation subsystem is used for generating and issuing scheduling instructions according to the dynamic train running diagram.
The electronic equipment comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the rail transit driving dispatching command method.
A computer readable storage medium storing a computer program which when executed by a processor implements the rail transit traffic scheduling command method described above.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the track traffic scheduling method provided by the invention, comprehensive and accurate perception of the track traffic system information is realized by acquiring the comprehensive running state information of the track traffic system; the method has the advantages that through identifying the abnormal event and determining the influence of the abnormal event on driving and the running situation of the train, support can be provided for optimization decision; by formulating a dynamic train operation diagram according to basic line parameters, planning operation data, the influence of abnormal events on running and train operation situation, a dispatching strategy can be automatically generated, a mode of manually adjusting the train operation by a running dispatcher is replaced, and the working intensity of the dispatcher is reduced; by generating and issuing the scheduling instruction according to the dynamic train running diagram, the risk of further expansion caused by untimely issuing of the scheduling instruction by a person through a telephone is avoided. Therefore, the method and the system can improve the degree of automation of the track traffic dispatching command system from four aspects of information acquisition, information analysis, dispatching decision and dispatching instruction generation so as to adapt to fine management, enhance the emergency handling capability of abnormal events and effectively reduce the influence on passenger service.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a track traffic driving dispatching command method provided by the invention;
fig. 2 is a detailed schematic diagram of information interaction between a track traffic driving dispatching command system and other related subsystems of track traffic, which is provided by the invention;
fig. 3 is a block diagram of a track traffic dispatching command system provided by the invention;
fig. 4 is a flowchart of a specific implementation of the scheduling decision subsystem provided by the present invention.
Symbol description:
the system comprises an information acquisition subsystem-1, a first information acquisition module-11, a second information acquisition module-12, an information analysis subsystem-2, a scheduling decision subsystem-3, a scheduling instruction generation subsystem-4, an electromechanical equipment monitoring system-5, an electric power monitoring system-6, a train operation control system-7, a passenger information system-8 and an environment monitoring system-9.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a method, a system, equipment and a medium for dispatching and commanding rail transit driving so as to realize automatic dispatching and commanding of rail transit driving, enhance the emergency handling capability of abnormal events and reduce the influence on passenger service.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1, the present invention provides a method for dispatching and commanding a rail transit vehicle, which includes:
step S1: and determining basic line parameters and planning operation data of the rail transit system, and acquiring comprehensive operation state information of the rail transit system.
Step S2: identifying an abnormal event according to the comprehensive running state information, and determining the influence of the abnormal event on running and the running situation of the train; the exception event includes: train delays, equipment and facility failures, bursty large passenger flows, and external environmental anomalies.
Step S3: and according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation, a dynamic train operation diagram is formulated.
Step S4: and generating and issuing a scheduling instruction according to the dynamic train running diagram.
As shown in fig. 2 and fig. 3, in order to execute the corresponding method to achieve the corresponding functions and technical effects, the present invention further provides a track traffic driving dispatching command system, including:
the information acquisition subsystem 1 is used for determining basic line parameters and planning operation data of the rail transit system and acquiring comprehensive operation state information of the rail transit system.
The information analysis subsystem 2 is used for identifying abnormal events according to the comprehensive running state information and determining the influence of the abnormal events on running and the running situation of the train; the exception event includes: train delays, equipment and facility failures, bursty large passenger flows, and external environmental anomalies.
And the scheduling decision subsystem 3 is used for making a dynamic train operation diagram according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation.
And the scheduling instruction generation subsystem 4 is used for generating and issuing scheduling instructions according to the dynamic train running diagram.
The following describes in detail the method and system for dispatching and commanding the rail transit driving provided by the invention with reference to fig. 1 to 3.
Step S1: the method comprises the steps of determining basic line parameters and planning operation data of the rail transit system, and acquiring comprehensive operation state information of the rail transit system, wherein the method specifically comprises the following steps:
step S1.1: and determining the basic line parameters of the rail transit system according to the actual line conditions of the rail transit system. The basic circuit parameters specifically include: line speed limit section information, the number and the positions of stations, definition of uplink and downlink directions, vehicle section positions, the number of storage lines of each station and wiring lines.
Step S1.2: and determining the plan operation data of the rail transit system according to the operation condition of the rail transit system. The planning operation data specifically includes: train number timetable, train bottom turnover plan, minimum tracking interval, minimum turn-back time, set of spare bottoms, and time required for spare on-line.
Step S1.3: and acquiring the running state information of each professional system related to running, such as an electromechanical equipment monitoring system, an electric power monitoring system, a train running control system, a passenger information system, an environment monitoring system and the like of the rail transit system, and converting unstructured information in the running state information into structured information to obtain comprehensive running state information. Specifically, unstructured information processing refers to extracting structured relational data from unstructured information such as text, pictures, images, and audio/video.
Referring to fig. 2, a communication interface is established with an electromechanical equipment monitoring system 5, and the states of electromechanical equipment such as lines, vehicles, ventilation air conditioners, water supply and drainage, elevators, lighting equipment and the like are collected in real time; establishing a communication interface with the power monitoring system 6, and collecting the states of power supply equipment of the first, second and third loads in real time; establishing a communication interface with a train operation control system 7, and collecting the states of trackside equipment such as a signal machine, a switch machine and the like and the operation states (such as speed, position, driving mode and whether a quasi-point is needed) of an on-line service train in real time; establishing a communication interface with a passenger information system 8, and collecting the dynamic information of passengers at the station and the entrance information of the passengers in real time; an interface is established with the environment monitoring system 9, and whether foreign matter invasion, weather and natural disaster information exist or not is collected in real time.
For the collected information, analyzing the structural type characteristics of unstructured files such as texts, pictures, images, audio/video and the like, creating corresponding file templates, reading the content of the unstructured information through a conversion program, converting the unstructured information into a standard XML document by using different conversion rules, analyzing the mapping relation between the XML document and a relational database, extracting the relation in a targeted mode, and carrying out structural representation to form the relational database.
In the above procedure, step S1.1 and step S1.2 are implemented by the first information acquisition module 11 in the information acquisition subsystem 1, and step S1.3 is implemented by the second information acquisition module 12 in the information acquisition subsystem 1.
Step S2: identifying an abnormal event according to the comprehensive running state information, and determining the influence of the abnormal event on running and the running situation of the train, wherein the method specifically comprises the following steps of:
step S2.1: and identifying abnormal events based on a neural network algorithm according to the comprehensive running state information.
The step S2.1 specifically comprises the following steps: determining the type and duration of the abnormal event based on a neural network algorithm according to the comprehensive running state information; determining the severity of the abnormal event according to the type and duration of the abnormal event; and classifying and displaying different abnormal events according to the set processing priority and the severity. Preferably, the neural network algorithm is any one of a BP neural network, a convolutional neural network and a recurrent neural network.
In specific application, multi-professional information (i.e. comprehensive running state information) is monitored in real time, when an abnormal event occurs, the type and duration of the abnormal event are predicted by means of massive fault data, an artificial intelligent algorithm is applied, the severity of the abnormal event is estimated according to the type and duration of the abnormal event, different abnormal events are classified and displayed according to set processing priority and severity (each fault has a unique display mode), the faults are early warned through interface display colors, alarm forms (voice, images and the like), a dispatcher is timely prompted, and the abnormal events are convenient to identify.
Step S2.2: according to the comprehensive running state information, a knowledge graph oriented to track traffic driving scheduling is constructed, and the influence of an abnormal event on driving is determined according to the knowledge graph; the influence of the abnormal event on the driving comprises the following steps: the highest running speed of the train, the minimum train tracking interval, the available train resources, the affected train number and the affected train area.
The method comprises the steps of constructing a knowledge graph oriented to rail transit driving scheduling, fusing comprehensive running state information, exploring complex relations between each system of rail transit and train running, and analyzing influence of abnormal events on driving according to knowledge extracted and stored by the knowledge graph if abnormal events exist, wherein the knowledge graph mainly covers the aspects of highest running speed of a train, minimum train tracking interval, available train resources, affected train numbers, affected line areas and the like.
The construction process of the knowledge graph mainly comprises four parts of data acquisition, knowledge fusion and knowledge reasoning. The construction process of the knowledge graph mainly comprises the following aspects:
(1) The data source is an important guarantee of research completeness, so that data acquisition and processing are the basis of knowledge graph construction. The sources of urban rail transit driving dispatching knowledge graph data are mainly divided into two types, namely structured system operation data, semi-structured abnormal event handling records and unstructured abnormal event handling records.
(2) After the related data are acquired, knowledge extraction of knowledge graph data is required, and the influence of abnormal events can be expressed in the form of < entity, relation and entity > triples through three steps of entity extraction, attribute extraction and relation extraction, so that a directed network expressed by 'point' and 'side' is formed, the points in the graph represent the entities, and the sides represent the relation among the entities.
(3) Because urban rail transit is a complex system involving multiple professions, different description modes can be adopted for the same entity under different professions, so that knowledge fusion is adopted to integrate descriptions of the entity by different knowledge bases, complete descriptions of the entity are obtained through knowledge alignment, knowledge merging and entity disambiguation, and a high-quality knowledge base is never formed.
(4) Based on the existing knowledge, further adopting knowledge reasoning technology, and deducing unknown knowledge by extracting facts or summarizing and summarizing, namely obtaining new relation triples among entities by utilizing the existing triples in the atlas.
Step S2.3: and determining the train running situation based on a discrete event dynamic system according to the influence of the abnormal event on the running.
Specifically, according to the influence of abnormal events on driving and the interaction mechanism between a train-train and a train-passenger in the operation process, the generation and propagation processes of train delay are revealed, so that the running situation of the train in a subsequent station is deduced, and a foundation is laid for decision.
The interaction mechanism of the train-train refers to the interaction relation among trains, for example, the trains cannot share line resources at the same time, the interaction mechanism of the train-passenger refers to how passengers get on and off the train to influence the stop time in the stop process of the train, and the interaction mechanism can be obtained by defining a discrete event dynamic system (such as Petri network). After the Petri network is established, the evolution process of the system can be described, wherein the evolution process comprises the generation and propagation processes of train delay and the running situation of the train at the subsequent station.
Step S3: and according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation, a dynamic train operation diagram is formulated, so that the train operation order is recovered to be normal as soon as possible.
Preferably, the invention establishes a multi-objective mathematical optimization model based on a discrete space-time network, balances a plurality of operation indexes such as train delay time, number of cancelled train times, number of midway turn-back train times, waiting time of passengers and the like by using linear weighting, and can rapidly generate a high-quality dynamic operation diagram in a short time.
As shown in fig. 4, step S3 specifically includes:
step S3.1: and constructing a discrete space-time network according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation.
Specifically, the discrete space-time network needs to be established according to the time range influenced by the abnormal event and two types of data of important nodes in the subway line. The station/storage line in the line is abstracted into nodes, the operation of the train is abstracted into an operation arc, a stop arc and an arc for entering and exiting the storage line, the time period after the abnormal event occurs is discretized according to a certain time interval, the operation path of the train on the line can be drawn by selecting different operation arcs, and the discrete space-time network shown in the first part in fig. 4 is constructed. Wherein the horizontal axis represents time nodes (time series discretized at fixed time intervals, covering time ranges affected by abnormal events), the vertical axis represents nodes in space (stations, lines of storage, etc.) and the place where the horizontal axis and the vertical axis cross represents one space-time node (the physical meaning is that a train is at a certain position in a line at a certain time), and the arrow (also called an arc) connects two space-time nodes, so that train operation can be represented (for example, 8 points of a train start from a zoo station, 9 points reach a darcy gate station, which is two space-time nodes in a discrete space-time network, the arrow represents that the train passes through the two space-time nodes, and otherwise, no arrow exists).
The invention provides a formulated representation method for train operation by constructing a discrete space-time network, and builds arcs possibly occupied by all trains, so that 0-1 variable can be used as decision variable, 0 represents not occupying the current arc, 1 represents occupied, and the decision variable can be represented for mathematical modeling in the subsequent steps.
Step S3.2: taking the minimum linear weighted sum of each operation index as an objective function, and establishing a multi-objective mathematical optimization model based on the discrete space-time network; the operation indexes comprise: train delay time, number of cancelled train number, number of midway turn-back train number and passenger waiting time; the constraint conditions of the multi-objective mathematical optimization model comprise: network flow constraints, underbody turnover constraints, arrival/departure time constraints, service station constraints, stop time constraints, line resource constraints, and train operation situation constraints.
Specifically, train delay time z is selected 1 Number of times of cancellation z 2 Number of turns Z 3 Passenger waiting time z 4 The four operation indexes are linearly weighted and then used as an objective function of an optimization model, and the four operation indexes are expressed as follows:
z＝ω 1 z 1 +ω 2 z 2 +ω 3 z 3 +ω 4 z 4
wherein omega 1 ,ω 2 ,ω 3 ,ω 4 The weights corresponding to the four operation indexes represent the importance degree of the operation indexes. The invention presets several groups of different weight values in the track traffic driving dispatching command system, and provides different operation diagram adjustment schemes for the dispatcher, thereby facilitating the dispatcher to select according to individual preference, specific field conditions and the like.
By setting the constraint of the optimization model, the feasibility of the dynamic train running diagram can be ensured. The constraint conditions specifically include:
(1) The network flow constraint, i.e. the number of arcs in and out of station nodes in the discrete space-time network is equal, is expressed as:
where (i, j, t, t ') represents an arc connecting nodes i and j from time t to t',representing a set of arcs that are to be combined,indicating whether the train k occupies an arc (i, j, t, t'), for example>Representing a set of train numbers, +.>Representing a collection of station nodes.
(2) The underbody turnover constraint, i.e. one train number can only be engaged by another train number or by one spare underbody, is expressed as:
wherein,representing a collection of storage line nodes.
(3) The arrival/departure time constraint, namely, the relationship between the arrival/departure time and the decision variable is established, is expressed as:
wherein a is k,i And d k,i The arrival/departure times of the train k at the node i are respectively indicated.
(4) Service station constraints, i.e. establishing a relationship between service station instructions and decision variables, are expressed as:
wherein y is k,i Indicating whether the train number k serves the station node i.
(5) Stop time constraint, namely, limiting the stop time of a train to a certain range, is expressed as:
wherein d min And d max Representing the maximum and minimum values of the stop time, respectively, M being a sufficiently large positive number.
(6) Line resource constraints, i.e. for all line resources (including positive line, access section line, stock line), cannot be occupied by two bottoms simultaneously, are expressed as:
wherein h is min Represents the shortest tracking interval, d k′,i The departure time of the train number k 'at the node i is represented, and the interval between the arrival time of the train number k at one node and the departure time of the train number k' at the same node is larger than the shortest tracking interval h min 。
(7) And the train running situation constraint, namely limiting the arrival time of the corresponding train number according to the train running situation predicted by the information analysis subsystem, is expressed as follows:
wherein,and->Respectively representing the earliest arrival/departure time of the train number k predicted by the information analysis subsystem at the node i.
Step S3.3: and solving the multi-objective mathematical optimization model by adopting a large-scale distributed solving method based on data driving to obtain a dynamic train running diagram.
The step S3.3 specifically comprises: performing decentralized processing on the objective function and the constraint condition of the multi-objective mathematical optimization model by taking the train number as a unit to obtain a plurality of sub-optimization models; performing simulation on train operation based on the discrete space-time network to obtain simulation data; determining a train operation adjustment strategy according to the simulation data by adopting a reinforcement learning method; and applying the train operation adjustment strategy, and sequentially solving each sub-optimization model according to the morning and evening of the departure time to obtain a dynamic train operation diagram.
Because the number of trains, stations and lines is numerous and the coupling among constraint conditions is serious, the built matching model is difficult to solve quickly, the optimization model is solved by adopting a large-scale distributed solving method based on data driving, and the specific implementation steps are as follows:
(1) And analyzing the coupling degree of the constraint condition and the objective function with each train number, performing decentralized processing on the objective function and the constraint condition by taking the train number as a unit, and decomposing the original optimization model into a plurality of sub-optimization models.
Each sub-model is respectively optimized for a train number, and only the part containing the train number is reserved in an objective function and a constraint. Taking train delay time as an example, train delay time z in original objective function 1 Is to accumulate all the train numbers, expressed asWherein k represents the train number index,/->Represents the aggregate of all train passes, +.>The delay time of a certain train number k is represented, and other operation indexes are the same, so that the objective function in the sub-optimization model is
(2) And performing simulation on train operation based on the discrete space-time network, and learning operation adjustment experience from data obtained by the simulation by adopting a reinforcement learning method so as to determine a final train operation adjustment strategy. Specifically, simulation is carried out on train operation based on a discrete space-time network, delay propagation and deduction results of the train operation under different operation adjustment strategies are obtained, a large amount of train operation simulation data are obtained, reward values returned by simulation environments under different train operation data are set according to an objective function, and a reinforcement learning method is adopted to learn the train operation adjustment strategy according to the returned reward values. The reward value refers to the implementation condition of the operation index obtained according to the system deduction result under the specific operation adjustment strategy, the reinforcement learning is a continuous trial and error process, the lower the reward value obtained by the worse strategy is according to the process of optimizing the strategy, and the learning and optimization of the operation adjustment strategy are realized through iteration.
(3) The learned train operation adjustment strategy is used for processing the sub-optimization model taking the train number as a unit after decomposition, and the strategy is sequentially applied to solve according to the morning and evening of the departure time, so that a feasible dynamic train operation diagram is generated in a short time. The dynamic train running chart comprises a start-stop station of each train number, an arrival time of each station, an initial train storage line and a stop train storage line.
Step S4: generating and issuing a scheduling instruction according to the dynamic train running diagram, wherein the scheduling instruction comprises the following specific steps:
step S4.1: generating or extracting a driving equipment scheduling instruction according to the dynamic train operation diagram, and sending the driving equipment scheduling instruction to related professional equipment/personnel, wherein the driving equipment scheduling instruction comprises: and (3) adjusting to time-division, stopping/starting the train number, on-line the spare-vehicle, changing the train operation and crossing, turning back midway and running in a single-line bidirectional mode.
Step S4.2: and generating or extracting a plurality of specialized dispatching instructions (namely, electromechanical equipment dispatching instructions, power equipment dispatching instructions, train operation information and passenger flow organization guiding information) related to driving, such as electric power, electromechanical equipment, passenger service and the like according to the dynamic train operation diagram, and sending the generated or extracted specialized dispatching instructions to related specialized equipment/personnel.
The method comprises the steps of extracting a driving dispatching instruction, wherein the driving dispatching instruction can be issued after confirmation of a dispatcher in consideration of the fact that full automation is not achieved, and extracting the driving dispatching instruction according to an operation chart is beneficial to confirmation of the dispatcher and understanding and execution of other staff.
Further, the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor is used for running the computer program to enable the electronic equipment to execute the track traffic scheduling command method. The electronic device may be a server.
Further, the invention also provides a computer readable storage medium storing a computer program which when executed by a processor realizes the track traffic scheduling command method.
In summary, the invention provides a method, a system, equipment and a medium for dispatching and commanding rail transit driving, which can promote the automation degree of the dispatching and commanding system of rail transit driving from four aspects of information acquisition, information analysis, dispatching decision and dispatching instruction generation so as to adapt to fine management, enhance the emergency handling capability of abnormal events and effectively reduce the influence on passenger service.
Compared with the prior art, the invention has the following advantages:
(1) The comprehensive and accurate perception of the information of the rail transit system is realized.
(2) And the influence range of the abnormal event and the running situation of the train are intelligently analyzed, and support is provided for optimization decision.
(3) The dispatching strategy is automatically generated, a mode that a train operation dispatcher manually adjusts the train operation is replaced, and the working intensity of the dispatcher is reduced.
(4) And the scheduling instruction matched with the scheduling strategy is automatically extracted and issued, so that the risk of further expansion caused by untimely issuing of the scheduling instruction by a person through a telephone is avoided.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (9)
1. The track traffic driving dispatching command method is characterized by comprising the following steps of:
determining basic line parameters and planning operation data of a rail transit system, and acquiring comprehensive operation state information of the rail transit system;
identifying an abnormal event according to the comprehensive running state information, and determining the influence of the abnormal event on running and the running situation of the train; the exception event includes: train delay, equipment and facility failure, sudden large passenger flow and abnormal external environment;
according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation, a dynamic train operation diagram is formulated;
generating and issuing a scheduling instruction according to the dynamic train operation diagram;
according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation, a dynamic train operation diagram is formulated, and the dynamic train operation diagram specifically comprises the following steps:
constructing a discrete space-time network according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation;
taking the minimum linear weighted sum of each operation index as an objective function, and establishing a multi-objective mathematical optimization model based on the discrete space-time network; the operation indexes comprise: train delay time, number of cancelled train number, number of midway turn-back train number and passenger waiting time; the constraint conditions of the multi-objective mathematical optimization model comprise: network flow constraint, underbody turnover constraint, arrival/departure time constraint, service station constraint, stop time constraint, line resource constraint and train running situation constraint;
and solving the multi-objective mathematical optimization model by adopting a large-scale distributed solving method based on data driving to obtain a dynamic train running diagram.
2. The track traffic scheduling command method according to claim 1, wherein the determining of the basic line parameters and the planned operation data of the track traffic system and the obtaining of the comprehensive operation state information of the track traffic system specifically comprises:
determining basic line parameters of the rail transit system according to the actual line conditions of the rail transit system;
according to the operation condition of the rail transit system, determining the plan operation data of the rail transit system;
and acquiring the running state information of an electromechanical equipment monitoring system, an electric power monitoring system, a train running control system, a passenger information system and an environment monitoring system of the rail transit system, and converting unstructured information in the running state information into structured information to obtain comprehensive running state information.
3. The track traffic driving dispatching command method according to claim 1, wherein the identifying of the abnormal event according to the comprehensive operation state information, determining the influence of the abnormal event on driving and the train operation situation, specifically comprises:
identifying an abnormal event based on a neural network algorithm according to the comprehensive operation state information;
according to the comprehensive running state information, a knowledge graph oriented to track traffic driving scheduling is constructed, and the influence of an abnormal event on driving is determined according to the knowledge graph; the influence of the abnormal event on the driving comprises the following steps: the highest running speed of the train, the minimum train tracking interval, available train resources, the number of affected trains and the affected line area;
and determining the train running situation based on a discrete event dynamic system according to the influence of the abnormal event on the running.
4. The track traffic driving dispatching command method according to claim 3, wherein the identifying abnormal events based on the neural network algorithm according to the comprehensive running state information specifically comprises:
determining the type and duration of the abnormal event based on a neural network algorithm according to the comprehensive running state information;
determining the severity of the abnormal event according to the type and duration of the abnormal event;
and classifying and displaying different abnormal events according to the set processing priority and the severity.
5. The track traffic dispatching command method according to claim 1, wherein the multi-objective mathematical optimization model is solved by adopting a large-scale distributed solving method based on data driving, and a dynamic train running diagram is obtained, and the method specifically comprises the following steps:
performing decentralized processing on the objective function and the constraint condition of the multi-objective mathematical optimization model by taking the train number as a unit to obtain a plurality of sub-optimization models;
performing simulation on train operation based on the discrete space-time network to obtain simulation data;
determining a train operation adjustment strategy according to the simulation data by adopting a reinforcement learning method;
and applying the train operation adjustment strategy, and sequentially solving each sub-optimization model according to the morning and evening of the departure time to obtain a dynamic train operation diagram.
6. The track traffic driving dispatching command method according to claim 1, wherein the dispatching command comprises: electromechanical equipment scheduling instructions, power equipment scheduling instructions, driving equipment scheduling instructions, train operation information and passenger flow organization guiding information; the driving equipment scheduling instruction comprises: and (3) adjusting to time division, stop train number, start train number, on-line of a spare vehicle, change train operation intersection, midway turning back and single-line bidirectional operation.
7. A rail transit traffic dispatch command system, comprising:
the information acquisition subsystem is used for determining basic line parameters and planning operation data of the rail transit system and acquiring comprehensive operation state information of the rail transit system;
the information analysis subsystem is used for identifying abnormal events according to the comprehensive running state information and determining the influence of the abnormal events on running and the running situation of the train; the exception event includes: train delay, equipment and facility failure, sudden large passenger flow and abnormal external environment;
the scheduling decision subsystem is used for making a dynamic train operation diagram according to the basic line parameters, the planning operation data, the influence of the abnormal event on driving and the train operation situation;
and the scheduling instruction generation subsystem is used for generating and issuing scheduling instructions according to the dynamic train running diagram.
8. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the rail transit trip scheduling command method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the rail transit traffic scheduling command method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310497726.XA CN116443080B (en) | 2023-05-05 | 2023-05-05 | Rail transit driving dispatching command method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310497726.XA CN116443080B (en) | 2023-05-05 | 2023-05-05 | Rail transit driving dispatching command method, system, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116443080A CN116443080A (en) | 2023-07-18 |
| CN116443080B true CN116443080B (en) | 2023-12-29 |
Family
ID=87135714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310497726.XA Active CN116443080B (en) | 2023-05-05 | 2023-05-05 | Rail transit driving dispatching command method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116443080B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| CN107194497A (en) * | 2017-04-27 | 2017-09-22 | 北京交通大学 | Urban track traffic passenger trip route planing method under a kind of accident |
| CN111369181A (en) * | 2020-06-01 | 2020-07-03 | 北京全路通信信号研究设计院集团有限公司 | Train autonomous scheduling deep reinforcement learning method and module |
| CN111376954A (en) * | 2020-06-01 | 2020-07-07 | 北京全路通信信号研究设计院集团有限公司 | Train autonomous scheduling method and system |
| CN111768074A (en) * | 2020-05-22 | 2020-10-13 | 北京交通大学 | Novel train operation intelligent adjustment method |
| CN112061183A (en) * | 2020-08-28 | 2020-12-11 | 交控科技股份有限公司 | Train operation adjusting method and device |
| AU2021100503A4 (en) * | 2020-12-04 | 2021-04-15 | East China Jiaotong University | Method and system for controlling heavy-haul train based on reinforcement learning |
| CN113085956A (en) * | 2021-04-13 | 2021-07-09 | 河南蓝信科技有限责任公司 | High-speed rail emergency guidance system and method |
| CN114298669A (en) * | 2021-12-22 | 2022-04-08 | 交控科技股份有限公司 | Train operation diagram adjusting method and device and train |
| WO2022099849A1 (en) * | 2020-11-10 | 2022-05-19 | 交控科技股份有限公司 | Rail traffic parallel deduction system and method |
| CN115384586A (en) * | 2022-10-28 | 2022-11-25 | 中国铁道科学研究院集团有限公司通信信号研究所 | Railway parallel scheduling system, method and application thereof |
-
2023
- 2023-05-05 CN CN202310497726.XA patent/CN116443080B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN107194497A (en) * | 2017-04-27 | 2017-09-22 | 北京交通大学 | Urban track traffic passenger trip route planing method under a kind of accident |
| CN111768074A (en) * | 2020-05-22 | 2020-10-13 | 北京交通大学 | Novel train operation intelligent adjustment method |
| CN111369181A (en) * | 2020-06-01 | 2020-07-03 | 北京全路通信信号研究设计院集团有限公司 | Train autonomous scheduling deep reinforcement learning method and module |
| CN111376954A (en) * | 2020-06-01 | 2020-07-07 | 北京全路通信信号研究设计院集团有限公司 | Train autonomous scheduling method and system |
| CN112061183A (en) * | 2020-08-28 | 2020-12-11 | 交控科技股份有限公司 | Train operation adjusting method and device |
| WO2022099849A1 (en) * | 2020-11-10 | 2022-05-19 | 交控科技股份有限公司 | Rail traffic parallel deduction system and method |
| AU2021100503A4 (en) * | 2020-12-04 | 2021-04-15 | East China Jiaotong University | Method and system for controlling heavy-haul train based on reinforcement learning |
| CN113085956A (en) * | 2021-04-13 | 2021-07-09 | 河南蓝信科技有限责任公司 | High-speed rail emergency guidance system and method |
| CN114298669A (en) * | 2021-12-22 | 2022-04-08 | 交控科技股份有限公司 | Train operation diagram adjusting method and device and train |
| CN115384586A (en) * | 2022-10-28 | 2022-11-25 | 中国铁道科学研究院集团有限公司通信信号研究所 | Railway parallel scheduling system, method and application thereof |
Non-Patent Citations (3)
| Title |
|---|
| 一种基于策略梯度强化学习的列车智能控制方法;张淼;张琦;刘文韬;周博渊;;铁道学报(01);全文 * |
| 张嘉敏、张嘉锐.轨道交通系统仿真理论方法与技术应用.2022,(第1版),160-162. * |
| 邱锡鹏.神经网络与深度学习.机械工业出版社,2020,(第1版),151-153. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116443080A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111376954B (en) | Train autonomous scheduling method and system | |
| Liu et al. | Timetable optimization for regenerative energy utilization in subway systems | |
| Dündar et al. | Train re-scheduling with genetic algorithms and artificial neural networks for single-track railways | |
| Corman et al. | A review of online dynamic models and algorithms for railway traffic management | |
| CN111369181A (en) | Train autonomous scheduling deep reinforcement learning method and module | |
| CN111452669B (en) | Intelligent bus charging system and method and medium | |
| CN113415322B (en) | High-speed train operation adjusting method and system based on Q learning | |
| Ning et al. | ACP-based control and management of urban rail transportation systems | |
| CN113177377A (en) | Intelligent urban rail transit network management system based on digital twins | |
| CN115384586B (en) | Railway parallel scheduling system, method and application thereof | |
| CN111784191A (en) | Safety management aid decision-making system based on industrial intelligence | |
| CN112183771A (en) | Intelligent operation and maintenance ecosystem for rail transit and operation method thereof | |
| CN115018148A (en) | Urban rail transit network passenger flow distribution prediction method and system based on digital twin model | |
| CN115796509A (en) | Rail transit emergency scheduling aid decision-making system and method | |
| Li et al. | Model controlled prediction: A reciprocal alternative of model predictive control | |
| Yang et al. | A real‐time timetable rescheduling method for metro system energy optimization under dwell‐time disturbances | |
| Xu et al. | Parallel dispatching: An ACP-based high-speed railway intelligent dispatching system | |
| CN116443080B (en) | Rail transit driving dispatching command method, system, equipment and medium | |
| CN116050669B (en) | Intelligent scheduling method and system for urban rail transit emergency | |
| Ding et al. | Key technologies and applications of intelligent dispatching command for high-speed railway in China | |
| Xiong et al. | Parallel bus rapid transit (BRT) operation management system based on ACP approach | |
| Nüñez et al. | Simulating railway and metropolitan rail networks: From planning to on-line control | |
| CN116011722A (en) | Large power grid-oriented man-machine cooperation regulation and control method, module and device | |
| Bouamrane et al. | Decision making system for regulation of a bimodal urban transportation network, associating a classical and a multi-agent approaches | |
| CN115027535A (en) | Driving command decision-making system and scheduling method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |