CN110843870A - Method for maintaining fixed capacity of high-speed railway network graph under abnormal event - Google Patents
Method for maintaining fixed capacity of high-speed railway network graph under abnormal event Download PDFInfo
- Publication number
- CN110843870A CN110843870A CN201911149049.2A CN201911149049A CN110843870A CN 110843870 A CN110843870 A CN 110843870A CN 201911149049 A CN201911149049 A CN 201911149049A CN 110843870 A CN110843870 A CN 110843870A
- Authority
- CN
- China
- Prior art keywords
- train
- time
- node
- capacity
- network
- 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.)
- Granted
Links
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The embodiment of the invention provides a method for maintaining the fixed capacity of a high-speed rail network graph in an abnormal event, which predicts the delay of a train by using a GBRT model, constructs a train delay operation alternative graph optimization model based on operation adjustment, generates a feasible train operation graph and calculates the capacity of the high-speed rail network in the abnormal event; calculating the capacity of the road sections according to the generated adjusted train running diagram, constructing a high-speed rail network capacity weight network under an abnormal event, and identifying the bottleneck road sections of the high-speed rail network capacity; the method comprises the steps of simulating the running of the high-speed train under different delay conditions by using OPENTRACK simulation software, analyzing the capacities of a high-speed rail section and a station under an abnormal event, feeding back a calculation result serving as capacity constraint to a substitute graph optimization model based on running adjustment, iteratively calculating the capacity of the high-speed rail network under the abnormal event, realizing accurate estimation of the capacity of the high-speed rail network, making a capacity maintenance strategy, and providing a macroscopic reference for high-speed rail scheduling and running graph adjustment.
Description
Technical Field
The invention relates to the technical field of rail transit capacity analysis, in particular to a method for maintaining the fixed capacity of a high-speed rail network graph in an abnormal event.
Background
The occurrence of abnormal events always restricts the improvement of the capacity of a high-speed railway network, different types of abnormal events can cause train delays of different degrees, serious abnormal events are often long in duration, the capacity loss is serious, the transportation capacity and the transportation capacity are unbalanced, and troubles are caused to the running organization and the operation plan of a high-speed train. The abnormal events are mainly divided into natural disasters, accident disasters, public health and social safety. In particular to driving accidents, fire disasters, explosions, geological disasters, meteorological disasters, facility equipment accidents and other events.
In recent years, the construction of high-speed railways in China is rapidly developed and gradually becomes a main channel for passenger transportation in China, and once abnormal events occur, capacity loss or line interruption is caused, so that the whole transportation system is seriously influenced. Therefore, the method for maintaining the fixed capacity of the high-speed railway network graph in the abnormal event is constructed, the change of the capacity of the high-speed railway network in the abnormal event and the bottleneck identification of the capacity of the high-speed railway network are researched, a decision basis is provided for dispatching and commanding from a macroscopic level, the method is beneficial to improving the railway traffic organization efficiency under the high-speed railway network forming condition, and the traffic safety is guaranteed.
Disclosure of Invention
The embodiment of the invention provides a method for maintaining the capacity of a high-speed rail network map under an abnormal event, which is characterized in that a train delay operation alternative map optimization model based on operation adjustment is constructed based on a high-speed rail train late delay prediction and adjustment strategy, the capacity of a section and a station is taken as dynamic constraint of the model, the accurate estimation of the capacity of the high-speed rail network is realized, a capacity maintenance strategy is established, and a macroscopic reference is provided for high-speed rail scheduling and operation map adjustment.
In order to achieve the purpose, the invention adopts the following technical scheme.
A method for maintaining the fixed capacity of a high-speed railway network graph under an abnormal event comprises the following steps:
s1: predicting delay time of a high-speed rail train based on a GBRT model;
s2: station constructed by applying OPENTACT simulation software and method for constructing stationThe topological graph of the high-speed rail network of the interval simulates the running of the high-speed train under different delay times, and the capacity N of the high-speed rail section under abnormal events is calculated according to the simulation resultqAnd station capacity Nw;
s3: using the delay time as model input data, and taking the section capacity NqAnd building a high-speed rail network substitution graph optimization model based on operation adjustment by taking station capacity Nw as model constraint, generating a high-speed rail train operation graph under an abnormal event and calculating network capacity Nz;
S4: constructing a high-speed rail network capacity weight network under an abnormal event based on a high-speed rail train running diagram and the network capacity under the abnormal event, and identifying a high-speed rail network capacity bottleneck road section;
s5: dividing the road network into sections and stations by the bottleneck road section, and calculating to obtain the section capacity of the high-speed rail under the new abnormal event by turning to S2And station capability
S6: it is determined whether the following statement is true,
If the statement is true, stopping iteration and entering S7; otherwise, turning to S3 for loop iteration;
s7: ability to export high-speed rail sections in abnormal eventsStation capacityRoad network capability Nz。
Preferably, the S1 includes:
the method adopts a method of gradient regression tree GBRT ensemble learning to predict the arrival delay of the high-speed rail, takes 7 variables of train number, drawing arrival time, total travel length, station stations, train travel time, travel percentage and late time as independent variables of a prediction model, takes the delay time of each train number arriving at a subsequent station as an output variable, and comprises the following steps based on the GBRT high-speed rail delay prediction:
s11: data input, known training data setWherein xiIs an input variable, yiIs the corresponding output variable, the loss function L (y, f (x)) is a squared error loss function,the iteration number M;
s12: the goal of the model is to find an approximation F towards the function F (x)0(x) And minimizes the expectation of a given loss function on the data set, gamma being a constant term, being the initial value of the model,
s13: the value of the negative gradient of the loss function at the current model is calculated and used as an estimate of the residual, then the negative gradient is defined as,
s14: for residual errors, the model fits it to a regression tree hm(x) Then the step size of the model gradient descent method is calculated as follows,
s15: the model is updated in such a way that,
fm(x)=fm-1(x)+γmhm(x)
s16: finishing M times of iteration to obtain a regression tree,
s17: and outputting the arrival delay time of the train.
Preferably, the S3 includes:
s31: constructing a macro substitution graph model;
s32: and constructing a replacement graph optimization model based on operation adjustment.
Preferably, the S31 includes:
according to train operation basic information and infrastructure data, a substitution graph node set is constructed by taking a block partition as a unit, stations are abstracted into a block partition from a macroscopic level, and the construction process of a concrete substitution graph is as follows, wherein the stations only serve as one node:
s311: acquiring basic information of train operation and infrastructure data;
s312: generating a node set N by the block partition, and generating a substitute arc set F by the connecting arcs of adjacent nodes;
s314: generating a substitution graph G ═ (N, F, a);
in the formula: n is a node set; f is an alternative arc set; a is a set of alternate pairs;the starting time of the train entering the interval, namely the starting moment of the node k, j;the end time of the train leaving interval, namely the end time of the nodes i and h; (k, i), (j, h) are substitutedAn arc, which is a directed edge of adjacent nodes k and i or j and h, and the direction indicates the sequence relation between the train operation; ((i, j), (h, k)) is an alternate pair.
Preferably, the train operation basic information includes: train starting and ending and arrival and departure and passing time information of a station, a train running route and a train;
the infrastructure data includes: interval distance and line allowable speed.
Preferably, said 32 comprises:
the method comprises the following steps of constructing a substitution graph optimization model based on operation adjustment by taking the minimum number of stopped trains and the total delay time of the trains as targets and taking capacity constraint, train departure time windows, train operation time, train forward and backward relation, train interval tracking time and station interval time as constraint conditions, wherein the specific model construction process is as follows:
(1) objective function
The capability of the high-speed railway under the abnormal event is kept with the minimum number of the trains to be stopped and the total time of the trains at the later point as the optimization target,
in the formula: q. q.sc,qdRespectively calculating the outage penalty number and the late penalty number; tau iskPlanning a starting moment for the train at the k node; x is the number ofkFor train shutdown, if the train is shutdown at node k, xk1, otherwise 0;
(2) constraint conditions
① capability constraint
The train runs in a road network and meets the maximum train number which can pass each block subarea in a given time range, namely the train is dynamically limited by the capacity of a section and a station;
in the formula: s represents a set of the block partitions in the interval; v represents a set of which the block subareas are located in a station; τ represents a train set;representing whether the train runs in a block zone S or not, wherein S belongs to S;indicating whether the train runs in a block zone V or not, wherein V belongs to V; n is a radical ofq,sRepresenting the capacity of the q section, and the occlusion partition s is located in the q section; nw, v represents the capacity of w stations, and the block subarea v is positioned at the w stations;
② train departure time window constraint
The occurrence time of the train at the node k is not earlier than the planning time, when the occurrence time is later than the point, the occurrence time of the train at the node k is not later than the planning time of the train plus the maximum time later,
in the formula (I), the compound is shown in the specification,the starting time of the train entering the interval, namely the starting time of the k node; tau iskThe planned starting time of the behavior represented by node k; x is the number ofkFor train shutdown, if the train is shutdown at node k, xk1, otherwise 0; t isDThe maximum late time of the train;
③ train operation time constraints
The starting time of the running behavior of the train at the node i meets the starting time of the direct preceding node k of the node iAnd the running time t of the k nodekThe sum of (a) and (b),
in the formula (I), the compound is shown in the specification,the starting time of the train entering the interval, namely the starting time at the node i;the starting time of the train entering the interval, namely the starting time of the k node; t is tkThe running time of the train on the section, namely the running time of 1 block subarea; f, replacing an arc set;
④ train front-rear relationship constraint
In order to avoid conflict, two trains cannot occupy the same block subarea at the same time,
in the formula (I), the compound is shown in the specification,andthe starting time of the train entering the interval, namely the starting time of the nodes i, k, h and j; t is tkiAnd tjhTo replace the values of the arcs, the nodes are respectively representedThe preparation time from k to node i and the preparation time from node j to node h; f. of(k,i|j,h)The train operation sequence is (k, i | j, h) belongs to A, if the arc (i, j) is selected, f (k, i | j, h) is 1, otherwise, 0 is obtained; m is an arbitrarily large positive number; a replaces the pair set;
⑤ train stopping restriction
If the train stops at the k node, the train stops at all the subsequent nodes of the k node,
xi=xk,k,i∈V,(k,i)∈F
in the formula, xkFor train shutdown, if the train is shutdown at node k, xk1, otherwise 0; x is the number ofiTo stop operation at node i
⑥ tracking train interval time and station interval time constraints
The train tracking interval time of the adjacent 2 trains is more than or equal to the minimum safe interval time t between the 2 trainszminValues of substitute arcs corresponding to substitute mapsShould be greater than or equal to t determined by train speed, interlock and block equipment typezminThe actual departure interval time of 2 trains adjacent in the same direction of the station is more than or equal to the minimum safe interval time tfmin,
In the formula, tzminMinimum safe interval time for train operation; t is tfminThe minimum departure interval time of adjacent trains at the same station;the starting time of the train entering the interval, namely the starting time of the k node;the starting time of the train leaving interval, namely the ending time at the node i; a set of N nodes; p (k) the occurrence position, interval or track of the behavior corresponding to node k; p (i) the occurrence position, interval or track of the behavior corresponding to the node i; hqAn interval set; hgA set of tracks;
(3) model solution
Adopting MATLAB R2018b to program, calling IBM ILOG CPLEX 12.6.0 to realize the proposed method, setting the relevant parameters of CPLEX as default values, solving the mixed integer linear programming model by a built-in branch cutting algorithm combining a branch-and-bound method and a secant plane method, and generating a train running sequence in the solving process according to the following steps:
s321: randomly generating a high-speed train operation sequence by a Fisher-Yates shuffle algorithm;
s322: dynamically sampling to generate all possible train running sequences;
s323: it is determined whether the following statement is true,
if the statement is true, stopping sampling and outputting a generated sequence; otherwise, continuing sampling;
s324: for any line in the road network, excluding trains which do not run on the line in the sequence,
s325: for any station in the road network, all trains passing through the station are included in the sequence according to the front and back running relation,
s326: generating a feasible sequence Sseq,
In the formula:andare respectively N and (N-N)Δ) Sample standard deviation of individual samples;andare respectively N and (N-N)Δ) A sample mean of individual samples; n is the number of sequences generated; n is a radical ofΔIs the number of sequences generated between measurements;is the convergence tolerance of the standard deviation of the samples,is the convergence tolerance of the sample mean; c is a constraint type; c. C-To exclude sequence constraints, c+To contain sequence constraints c+;ecA line corresponding to constraint c; sseqA train sequence generated for a set of trains;is the position of the train in the sequence; erIs a set of lines in path r;is composed ofThe path the train travels.
Preferably, the constructing a high-speed rail network capacity weight network under the abnormal event comprises:
on the basis of a high-speed rail train running diagram under an abnormal event, a road network is decomposed into a combination of sections by combining a locomotive road-crossing system and a riding system, the running direction of the train is not considered, the road network is finally abstracted into a non-directional capacity weight network, and the capacity weight of each section is obtained according to the following formula:
in the formula: n is the number of passing trains in the section; t is the occupied time of the train for m times on the plan operation diagram; t is1And (5) counting the occupied time of the train for the adjusted running chart.
Preferably, the dividing of the road network into sections and stations by the bottleneck road section includes:
s51: calculating the section capacity by the generated adjusted train operation diagram, constructing a non-directional weight traffic network G, and generating an adjacent matrix A of the traffic network GG;
S52: computing a diagonal matrix D of a traffic network GGAnd generates a laplacian matrix LG;
S53: normalized Laplace matrix LG;
S54: calculating the second small eigenvalue λ of the normalized Laplace matrix2And feature vectors
S55: according to the feature vectorAnd a threshold value tau, dividing the traffic network, wherein the cut edge is a traffic bottleneck section.
According to the technical scheme provided by the embodiment of the invention, the embodiment of the invention provides a method for maintaining the capacity of a high-speed railway network graph in an abnormal event, and the method uses the train delay predicted by a GBRT model to construct a train delay operation alternative graph optimization model based on operation adjustment, generate a feasible train operation graph and calculate the capacity of the high-speed railway network in the abnormal event; calculating the capacity of the road sections according to the generated adjusted train running diagram, constructing a high-speed rail network capacity weight network under an abnormal event, and identifying the bottleneck road sections of the high-speed rail network capacity; the method comprises the steps of simulating the running of high-speed trains with different delay times by using OPENTRACK simulation software, analyzing the capacities of high-speed rail sections and stations under abnormal events, feeding back a calculation result serving as capacity constraint to a substitute graph optimization model based on running adjustment, iteratively calculating the capacity of the high-speed rail network under the abnormal events, realizing accurate estimation of the capacity of the high-speed rail network, making a capacity maintenance strategy, and providing a macroscopic reference for high-speed rail scheduling and running graph adjustment.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for maintaining the fixed capacity of a graph of a highway network in an abnormal event;
FIG. 2 is a correlation of train delay to input variables;
FIG. 3 is a comparison of actual delays and predicted delays for three models (training set);
FIG. 4 is a comparison (test set) of actual delays and predicted delays for three models;
fig. 5 illustrates the recognition of the service network capacity bottleneck in the Yangtze delta area.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
The embodiment of the invention provides a method for maintaining the fixed capacity of a high-speed railway network graph in an abnormal event, which comprises the following steps as shown in figure 1:
s1: and predicting delay time of the high-speed rail train based on the GBRT model.
And predicting the high-speed rail arrival delay by adopting a method of integrated learning of a progressive gradient regression tree (GBRT). GBRT generates strong learners in the form of weak learner sets, and performs learning and model prediction of training samples on the basis of the strong learners. Considering that 7 variables such as the arrival time, the travel percentage, the late time and the like of the high-speed rail map are taken as independent variables of a prediction model, the delay time of each train number arriving at a subsequent station is taken as an output variable, and the steps of the high-speed rail delay prediction based on the GBRT are as follows:
s11: data input, known training data setWherein xiIs an input variable, yiIs the corresponding output variable, the loss function L (y, f (x)) is a squared error loss function,the iteration number M;
s12: the goal of the model is to find an approximation F towards the function F (x)0(x) And minimizes the expectation of a given loss function on the data set, gamma being a constant term, being the initial value of the model,
s13: the value of the negative gradient of the loss function at the current model is calculated and used as an estimate of the residual, then the negative gradient is defined as,
s14: for residual errors, the model fits it to a regression tree hm(x) Then the step size of the model gradient descent method is calculated as follows,
s15: the model is updated in such a way that,
fm(x)=fm-1(x)+γmhm(x)
s16: finishing M times of iteration to obtain a regression tree,
s17: and outputting the arrival delay time of the train.
The embodiment of the invention verifies that the selected characteristic variables and the original data are shown in table 1, and before modeling, the modeling data needs to be preprocessed to obtain the correlation between train delay and the characteristic variables, which is shown in fig. 2. As can be seen from the graph, there is a complex relationship between the dependent variable arrival late and the respective variables, which is difficult to determine. Therefore, the machine learning model is considered to solve the complex relationship between the dependent variable and the independent variable to predict the delay of the high-speed train.
TABLE 1 original data Table for modeling
Since the delay time is directly absorbed by the buffer time when the delay time is too small, the delay of a high-speed train of 4min or less is not considered, and the modeling data sample amount is 1306 after data preprocessing such as noise reduction. 80% of the data in the data set was randomly selected as a training set for model training, and the remaining 20% of the data was selected as a test set. The model determines the optimal parameters through a grid search method.
The results of calculating the evaluation indexes of the different models using the training set are shown in table 2. As shown in Table 2, the coefficient of certainty of GBRT is as high as 0.9063, which is superior to that of the RF and SVR models, and MAE, MSE and RMSE are the lowest compared with the RF and SVR models, so the GBRT model has the best fitting effect compared with the RF and SVR models. To verify the validity of each model, test set data was entered into the trained model, and as a result, as shown in table 3, it can be seen that GBRT has slightly lower individual merit values in the test set relative to the training set, but still works best compared to both RF and SVR models. Therefore, the GBRT prediction model has a good effect on the delay prediction of the high-speed rail late.
TABLE 2 comparison of results for three models (training set)
Methods | R2 | MAE | MSE | RMSE |
SVR | 0.8730 | 0.6356 | 2.5791 | 1.6059 |
RF | 0.8866 | 0.9957 | 2.1628 | 1.4706 |
GBRT | 0.9063 | 0.4628 | 1.8845 | 1.3727 |
TABLE 3 comparison of results for three models (test set)
S2: constructing a high-speed rail network topological graph of stations and sections by using OPENTRACK simulation software, simulating the running of high-speed trains at different delay times, and calculating the capacity N of the high-speed rail section under abnormal events according to simulation resultsqAnd station capability Nw (initial value calculated separately).
S3: using delay time as model input data, and using section capacity NqAnd building a high-speed rail network substitution graph optimization model based on operation adjustment by taking station capacity Nw as model constraint, generating a high-speed rail train operation graph under an abnormal event and calculating network capacity Nz。
S31: and (5) constructing a macroscopic substitution graph model.
According to train operation basic information and infrastructure data, a substitution graph node set is constructed by taking a block partition as a unit, stations are abstracted into a block partition from a macroscopic level, and the construction process of a concrete substitution graph is as follows, wherein the stations only serve as one node:
s311: obtaining train operation basic information and infrastructure data, wherein the train operation basic information comprises: information such as train starting and ending to a station, a train running route, train arrival, departure and passing time and the like; the infrastructure data includes section distance, line allowable speed, and the like.
S312: a set of nodes N is generated by the block partition, and a set of substitute arcs F is generated by the connecting arcs of the adjacent nodes.
S314: the alternative graph G ═ (N, F, a) is generated.
In the formula: n is a node set; f is an alternative arc set; a is substitutionA pair set;the starting time of the train entering the interval, namely the starting moment of the node k, j;the end time of the train leaving interval, namely the end time of the nodes i and h; (k, i), (j, h) are substitute arcs, and are directed edges of adjacent nodes k and i or j and h, and the directions indicate the precedence relationship between train operation; ((i, j), (h, k)) is an alternate pair.
S32: and constructing a replacement graph optimization model based on operation adjustment.
The method comprises the following steps of constructing a substitution graph optimization model based on operation adjustment by taking the minimum number of stopped trains and the total delay time of the trains as targets and taking capacity constraint, train departure time windows, train operation time, train forward and backward relation, train interval tracking time, station interval time and the like as constraint conditions, wherein the specific model construction process is as follows:
(1) model symbol
TABLE 4 model parameters
(2) Objective function
The capability of the high-speed railway under the abnormal event is kept with the minimum number of the trains to be stopped and the total time of the trains at the later point as the optimization target,
(3) constraint conditions
① capability constraint
The train running in the road network should satisfy the maximum train number that each block zone can pass in a given time range, namely, the train is limited by the dynamic of the capacity of the section and the station, the capacity of the section and the station is calculated according to the following claim 7,
② train departure time window constraint
The occurrence time of the train at the node k is not earlier than the planning time, when the occurrence time is later than the point, the occurrence time of the train at the node k is not later than the planning time of the train plus the maximum time later,
③ train operation time constraints
The starting time of the running behavior of the train at the node i meets the starting time of the direct preceding node k of the node iAnd the running time t of the k nodekThe sum of (a) and (b),
④ train front-rear relationship constraint
In order to avoid conflict, two trains cannot occupy the same block subarea at the same time,
⑤ train stopping restriction
If the train stops at the k node, the train stops at all the subsequent nodes of the k node,
xi=xk,k,i∈V,(k,i)∈F
⑥ tracking train interval time and station interval time constraints
The train tracking interval time of the adjacent 2 trains is more than or equal to the minimum safe interval time t between the 2 trainszmin. Corresponding to the values of the substitute arcs in the substitute graphShould be greater than or equal to t determined by train running speed, interlock and block equipment type and the likezminThe value of (c). The actual departure interval time of the 2 trains adjacent in the same direction of the station is more than or equal to the minimum safe interval time tfmin,
(4) Model solution
The proposed method was implemented using MATLAB R2018b programming, calling IBM ILOG CPLEX 12.6.0. And setting relevant parameters of the CPLEX as default values, and solving the mixed integer linear programming model by a built-in branch cutting algorithm combining a branch-and-bound method and a cut plane method. Generating a train running sequence in the solving process according to the following steps:
s321, randomly generating a high-speed train operation sequence by a Fisher-Yates shuffle algorithm;
s322, dynamically sampling to generate all possible train operation sequences;
s323, judging whether the following sentence is true,
if the statement is true, stopping sampling and outputting a generated sequence; otherwise, continuing sampling;
s324: for any line in the road network, excluding trains which do not run on the line in the sequence,
s325: for any station in the road network, all trains passing through the station are included in the sequence according to the front and back running relation,
s326: generating a feasible sequence Sseq,
In the formula:andare respectively N and (N-N)Δ) Sample standard deviation of individual samples;andare respectively N and (N-N)Δ) A sample of a sampleMean value; n is the number of sequences generated; n is a radical ofΔIs the number of sequences generated between measurements;is the convergence tolerance of the standard deviation of the samples,is the convergence tolerance of the sample mean; c is a constraint type; c. C-To exclude sequence constraints, c+To contain sequence constraints c+;ecA line corresponding to constraint c; sseqA train sequence generated for a set of trains;is the position of the train in the sequence; erIs a set of lines in path r;is composed ofThe path the train travels.
S4: and constructing a high-speed rail network capacity weight network under the abnormal event based on the high-speed rail train running diagram and the network capacity under the abnormal event, and further identifying the bottleneck road section of the high-speed rail network capacity.
The high-speed train operation diagram under the abnormal event obtained by the step S3 is combined with locomotive traffic and a riding system to decompose the road network into a combination of sections, and the road network is finally abstracted into a non-directional capability weight network without considering the train operation direction. The capacity weight for each segment is given by:
in the formula: n is the number of passing trains in the section; t is the occupied time of the train for m times on the plan operation diagram; t is1And (5) counting the occupied time of the train for the adjusted running chart.
S5: road network is drawn by bottleneck sectionDividing the high-speed rail into sections and stations, and converting S2 to obtain the capacity of the high-speed rail sections under a new abnormal event through calculationAnd station capability
The method for identifying the bottleneck of the road network capacity based on spectral clustering comprises the following steps:
s51: calculating the section capacity by the generated adjusted train operation diagram, constructing a non-directional weight traffic network G, and generating an adjacent matrix A of the traffic network GG;
S52: computing a diagonal matrix D of a traffic network GGAnd generates a laplacian matrix LG;
S53: normalized Laplace matrix LG;
S54: calculating the second small eigenvalue λ of the normalized Laplace matrix2And feature vectors
S55: according to the feature vectorAnd a threshold value tau, dividing the traffic network, wherein the cut edge is a traffic bottleneck section.
Constructing a high-speed railway capacity weight network based on a high-speed railway network in a Yangtze river delta region and a train schedule; the spectral clustering method is adopted to identify the service capacity bottleneck of the high-speed railway, the result is shown in fig. 5(a) and (b), fig. 5(a) shows that the network is divided into two sub-regions, and the boundary of the sub-regions is the capacity bottleneck of the road network; fig. 5(b) shows that the network is divided into three sub-regions, and the boundaries of the sub-regions are the capacity bottlenecks of the road network.
S6: : it is determined whether the following statement is true,
If the statement is true, stopping iteration and entering S7; otherwise, turning to S3 for loop iteration;
s7: ability to export high-speed rail sections in abnormal eventsStation capacityRoad network capability Nz。
In summary, the method for maintaining the mapping capability of the high-speed rail network in the abnormal event provided by the embodiment of the invention predicts the delay of the late point of the high-speed rail based on the GBRT prediction model, and the prediction effect is better than that of the RF model and the SVR model. The method comprises the steps of constructing a train delayed operation substitution graph optimization model based on operation adjustment to calculate the capacity of the high-speed rail network, utilizing OPENTRACK simulation software to simulate the operation of the high-speed train in real time, analyzing the capacity of a high-speed rail section and a station under an abnormal event, feeding back a calculation result serving as capacity constraint to the substitution graph optimization model based on the operation adjustment, iteratively calculating the capacity of the high-speed rail network under the abnormal event, realizing accurate estimation of the capacity of the high-speed rail network, formulating a capacity maintenance strategy and providing a macroscopic reference for high-speed rail scheduling and operation graph adjustment.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method for maintaining the fixed capacity of a high-speed railway network graph under an abnormal event is characterized by comprising the following steps:
s1: predicting delay time of a high-speed rail train based on a GBRT model;
s2: constructing a high-speed rail network topological graph of stations and sections by using OPENTRACK simulation software, simulating the running of high-speed trains at different delay times, and calculating the capacity N of the high-speed rail section under abnormal events according to simulation resultsqAnd station capacity Nw;
s3: using the delay time as model input data, and taking the section capacity NqStation energy Nw as modelConstructing a high-speed rail network alternative graph optimization model based on operation adjustment, generating a high-speed rail train operation graph under an abnormal event, and calculating the network capacity Nz;
S4: constructing a high-speed rail network capacity weight network under an abnormal event based on a high-speed rail train running diagram and the network capacity under the abnormal event, and identifying a high-speed rail network capacity bottleneck road section;
s5: dividing the road network into sections and stations by the bottleneck road section, and calculating to obtain the section capacity of the high-speed rail under the new abnormal event by turning to S2And station capability
S6: it is determined whether the following statement is true,
If the statement is true, stopping iteration and entering S7; otherwise, turning to S3 for loop iteration;
2. The method according to claim 1, wherein the S1 includes:
the method adopts a method of gradient regression tree GBRT ensemble learning to predict the arrival delay of the high-speed rail, takes 7 variables of train number, drawing arrival time, total travel length, station stations, train travel time, travel percentage and late time as independent variables of a prediction model, takes the delay time of each train number arriving at a subsequent station as an output variable, and comprises the following steps based on the GBRT high-speed rail delay prediction:
s11: data input, known training data setWherein xiIs an input variable, yiIs the corresponding output variable, the loss function L (y, f (x)) is a squared error loss function,the iteration number M;
s12: the goal of the model is to find an approximation F towards the function F (x)0(x) And minimizes the expectation of a given loss function on the data set, gamma being a constant term, being the initial value of the model,
s13: the value of the negative gradient of the loss function at the current model is calculated and used as an estimate of the residual, then the negative gradient is defined as,
s14: for residual errors, the model fits it to a regression tree hm(x) Then the step size of the model gradient descent method is calculated as follows,
s15: the model is updated in such a way that,
fm(x)=fm-1(x)+γmhm(x)
s16: finishing M times of iteration to obtain a regression tree,
s17: and outputting the arrival delay time of the train.
3. The method according to claim 1, wherein the S3 includes:
s31: constructing a macro substitution graph model;
s32: and constructing a replacement graph optimization model based on operation adjustment.
4. The method according to claim 3, wherein the S31 includes:
according to train operation basic information and infrastructure data, a substitution graph node set is constructed by taking a block partition as a unit, stations are abstracted into a block partition from a macroscopic level, and the construction process of a concrete substitution graph is as follows, wherein the stations only serve as one node:
s311: acquiring basic information of train operation and infrastructure data;
s312: generating a node set N by the block partition, and generating a substitute arc set F by the connecting arcs of adjacent nodes;
s314: generating a substitution graph G ═ (N, F, a);
in the formula: n is a node set; f is an alternative arc set; a is a set of alternate pairs;the starting time of the train entering the interval, namely the starting moment of the node k, j;for train departureThe end time of the open interval, namely the end time of the nodes i and h; (k, i), (j, h) are substitute arcs, and are directed edges of adjacent nodes k and i or j and h, and the directions indicate the precedence relationship between train operation; ((i, j), (h, k)) is an alternate pair.
5. The method of claim 4, wherein the train operation basic information comprises: train starting and ending and arrival and departure and passing time information of a station, a train running route and a train;
the infrastructure data includes: interval distance and line allowable speed.
6. The method of claim 4 or 5, wherein the 32 comprises:
the method comprises the following steps of constructing a substitution graph optimization model based on operation adjustment by taking the minimum number of stopped trains and the total delay time of the trains as targets and taking capacity constraint, train departure time windows, train operation time, train forward and backward relation, train interval tracking time and station interval time as constraint conditions, wherein the specific model construction process is as follows:
(1) objective function
The capability of the high-speed railway under the abnormal event is kept with the minimum number of the trains to be stopped and the total time of the trains at the later point as the optimization target,
in the formula: q. q.sc,qdRespectively calculating the outage penalty number and the late penalty number; tau iskPlanning a starting moment for the train at the k node; x is the number ofkFor train shutdown, if the train is shutdown at node k, xk1, otherwise 0;
(2) constraint conditions
① capability constraint
The train runs in a road network and meets the maximum train number which can pass each block subarea in a given time range, namely the train is dynamically limited by the capacity of a section and a station;
in the formula: s represents a set of the block partitions in the interval; v represents a set of which the block subareas are located in a station; τ represents a train set; thetat,sRepresenting whether the train runs in a block zone S or not, wherein S belongs to S; thetat,vIndicating whether the train runs in a block zone V or not, wherein V belongs to V; n is a radical ofq,sRepresenting the capacity of the q section, and the occlusion partition s is located in the q section; nw, v represents the capacity of w stations, and the block subarea v is positioned at the w stations;
② train departure time window constraint
The occurrence time of the train at the node k is not earlier than the planning time, when the occurrence time is later than the point, the occurrence time of the train at the node k is not later than the planning time of the train plus the maximum time later,
in the formula (I), the compound is shown in the specification,the starting time of the train entering the interval, namely the starting time of the k node; tau iskThe planned starting time of the behavior represented by node k; x is the number ofkFor train shutdown, if the train is shutdown at node k, xk1, otherwise 0; t isDThe maximum late time of the train;
③ train operation time constraints
The starting time of the running behavior of the train at the node i meets the starting time of the direct preceding node k of the node iAnd the running time t of the k nodekThe sum of (a) and (b),
in the formula (I), the compound is shown in the specification,the starting time of the train entering the interval, namely the starting time at the node i;the starting time of the train entering the interval, namely the starting time of the k node; t is tkThe running time of the train on the section, namely the running time of 1 block subarea; f, replacing an arc set;
④ train front-rear relationship constraint
In order to avoid conflict, two trains cannot occupy the same block subarea at the same time,
in the formula (I), the compound is shown in the specification,andthe starting time of the train entering the interval, namely the starting time of the nodes i, k, h and j; t is tkiAnd tjhRespectively representing the preparation time from the node k to the node i and the preparation time from the node j to the node h for replacing the value of the arc; f. of(k,i|j,h)The train operation sequence is (k, i | j, h) belongs to A, if the arc (i, j) is selected, f (k, i | j, h) is 1, otherwise, 0 is obtained; m is an arbitrarily large positive number; a replaces the pair set;
⑤ train stopping restriction
If the train stops at the k node, the train stops at all the subsequent nodes of the k node,
xi=xk,k,i∈V,(k,i)∈F
in the formula, xkFor train shutdown, if the train is shutdown at node k, xk1, otherwise 0; x is the number ofiTo stop operation at node i
⑥ tracking train interval time and station interval time constraints
The train tracking interval time of the adjacent 2 trains is more than or equal to the minimum safe interval time t between the 2 trainszminValues of substitute arcs corresponding to substitute mapsShould be greater than or equal to t determined by train speed, interlock and block equipment typezminThe actual departure interval time of 2 trains adjacent in the same direction of the station is more than or equal to the minimum safe interval time tfmin,
In the formula, tzminMinimum safe interval time for train operation; t is tfminThe minimum departure interval time of adjacent trains at the same station;the starting time of the train entering the interval, namely the starting time of the k node;the starting time of the train leaving interval, namely the ending time at the node i; a set of N nodes; p (k) the occurrence position, interval or track of the behavior corresponding to node k; p (i) the occurrence position, interval or track of the behavior corresponding to the node i; hqAn interval set; hgA set of tracks;
(3) model solution
Adopting MATLAB R2018b to program, calling IBM ILOG CPLEX 12.6.0 to realize the proposed method, setting the relevant parameters of CPLEX as default values, solving the mixed integer linear programming model by a built-in branch cutting algorithm combining a branch-and-bound method and a secant plane method, and generating a train running sequence in the solving process according to the following steps:
s321: randomly generating a high-speed train operation sequence by a Fisher-Yates shuffle algorithm;
s322: dynamically sampling to generate all possible train running sequences;
s323: it is determined whether the following statement is true,
if the statement is true, stopping sampling and outputting a generated sequence; otherwise, continuing sampling;
s324: for any line in the road network, excluding trains which do not run on the line in the sequence,
s325: for any station in the road network, all trains passing through the station are included in the sequence according to the front and back running relation,
s326: generating a feasible sequence Sseq,
In the formula:andare respectively N and (N-N)Δ) Sample standard deviation of individual samples;andare respectively N and (N-N)Δ) A sample mean of individual samples; n is the number of sequences generated; n is a radical ofΔIs the number of sequences generated between measurements;is the convergence tolerance of the standard deviation of the samples,is the convergence tolerance of the sample mean; c is a constraint type; c. C-To exclude sequence constraints, c+To contain sequence constraints c+;ecA line corresponding to constraint c; sseqA train sequence generated for a set of trains;is the position of the train in the sequence; erIs a set of lines in path r;is composed ofThe path the train travels.
7. The method of claim 6, wherein constructing a highroad network capacity weighting network in the event of an anomaly comprises:
on the basis of a high-speed rail train running diagram under an abnormal event, a road network is decomposed into a combination of sections by combining a locomotive road-crossing system and a riding system, the running direction of the train is not considered, the road network is finally abstracted into a non-directional capacity weight network, and the capacity weight of each section is obtained according to the following formula:
in the formula: n is the number of passing trains in the section; t is the occupied time of the train for m times on the plan operation diagram; t is1And (5) counting the occupied time of the train for the adjusted running chart.
8. The method of claim 7, wherein the dividing of the road network into sections and stations by bottleneck road segments comprises:
s51: calculating the section capacity by the generated adjusted train operation diagram, constructing a non-directional weight traffic network G, and generating an adjacent matrix A of the traffic network GG;
S52: computing a diagonal matrix D of a traffic network GGAnd generates a laplacian matrix LG;
S53: normalized Laplace matrix LG;
S55: according to the feature vectorAnd a threshold value tau, dividing the traffic network, wherein the cut edge is a traffic bottleneck section.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911149049.2A CN110843870B (en) | 2019-11-21 | 2019-11-21 | Method for maintaining fixed capacity of high-speed railway network graph under abnormal event |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911149049.2A CN110843870B (en) | 2019-11-21 | 2019-11-21 | Method for maintaining fixed capacity of high-speed railway network graph under abnormal event |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110843870A true CN110843870A (en) | 2020-02-28 |
CN110843870B CN110843870B (en) | 2021-01-01 |
Family
ID=69603469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911149049.2A Active CN110843870B (en) | 2019-11-21 | 2019-11-21 | Method for maintaining fixed capacity of high-speed railway network graph under abnormal event |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110843870B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112070325A (en) * | 2020-11-12 | 2020-12-11 | 北京交通大学 | Road network train optimization method, device, equipment and storage medium under abnormal event |
CN112249101A (en) * | 2020-11-17 | 2021-01-22 | 中南大学 | High-speed rail network delay propagation quantitative analysis method based on matrix representation |
CN113291356A (en) * | 2021-06-24 | 2021-08-24 | 北京交通大学 | Dynamic train tracking interval calculation method |
CN113536692A (en) * | 2021-08-03 | 2021-10-22 | 东北大学 | Intelligent dispatching method and system for high-speed rail train in uncertain environment |
CN113581261A (en) * | 2021-09-07 | 2021-11-02 | 东北大学 | Comprehensive performance evaluation system for high-speed railway stage adjustment plan |
CN113627694A (en) * | 2021-10-11 | 2021-11-09 | 中国铁道科学研究院集团有限公司通信信号研究所 | Inter-city railway train operation plan adjusting method and system considering outage |
CN114677563A (en) * | 2022-04-08 | 2022-06-28 | 李燕秋 | Neural network online learning method and system based on block chain |
CN114852136A (en) * | 2022-03-18 | 2022-08-05 | 北京交通大学 | Multi-professional collaborative adjustment method, system, equipment and medium for high-speed rail operation |
CN115230777A (en) * | 2022-06-21 | 2022-10-25 | 中国科学院自动化研究所 | Scheduling policy adjustment method and device, electronic equipment and storage medium |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101441680A (en) * | 2008-12-18 | 2009-05-27 | 北京交通大学 | Method for improving high speed rail train operation right time rate by running chart robustness |
CN102129522A (en) * | 2011-03-17 | 2011-07-20 | 北京交通大学 | Method for quickly identifying and eliminating transportation capacity bottleneck of high-speed railway |
JP2013100034A (en) * | 2011-11-09 | 2013-05-23 | Hitachi Ltd | Train arrival time providing device |
KR101299526B1 (en) * | 2013-05-28 | 2013-08-23 | 한국철도공사 | System for train operation planning and method thereof |
CN104239726A (en) * | 2014-09-22 | 2014-12-24 | 北京交通大学 | Passenger flow estimation system under condition of urban rail road network emergency |
CN105608896A (en) * | 2016-03-14 | 2016-05-25 | 西安电子科技大学 | Traffic bottleneck identification method in urban traffic network |
CN105678411A (en) * | 2015-12-30 | 2016-06-15 | 西南交通大学 | Passenger train operation scheme diagram drawing method |
CN107122903A (en) * | 2017-04-27 | 2017-09-01 | 聊城大学 | A kind of measure of railway network structural reliability |
CN108256142A (en) * | 2017-12-13 | 2018-07-06 | 北京交通大学 | A kind of high-speed railway handling capacity calculation and analysis methods and system |
CN108364127A (en) * | 2018-02-01 | 2018-08-03 | 北京市地铁运营有限公司 | A kind of road network passenger flow Collaborative Control optimization system |
CN108491950A (en) * | 2018-01-25 | 2018-09-04 | 北京交通大学 | A kind of high-speed railway handling capacity computational methods considering multiple resources constraint |
CN109359788A (en) * | 2018-12-06 | 2019-02-19 | 西南交通大学 | A kind of initial late method for building up for influencing prediction model of bullet train |
CN109508751A (en) * | 2018-12-06 | 2019-03-22 | 西南交通大学 | The deep neural network model modeling method of the late time prediction of High Speed Railway Trains |
CN109583657A (en) * | 2018-12-06 | 2019-04-05 | 西南交通大学 | The operation figure redundancy time of train operation actual achievement data-driven is laid out acquisition methods |
CN109740839A (en) * | 2018-11-23 | 2019-05-10 | 北京交通大学 | Train Dynamic method of adjustment and system under a kind of emergency event |
CN109733445A (en) * | 2018-12-27 | 2019-05-10 | 中南大学 | The distributed scheduling method based on multi-Agent System Model under emergency event |
CN109754180A (en) * | 2018-12-29 | 2019-05-14 | 中南大学 | Emergency event terminates the high-speed railway train operation adjustment method under time uncertain condition |
CN109840639A (en) * | 2019-03-05 | 2019-06-04 | 东北大学 | A kind of late time forecasting methods of high speed rail train operation |
CN109902864A (en) * | 2019-02-20 | 2019-06-18 | 吉林大学 | A kind of construction area Traffic Organization design method considering network prestowage equilibrium |
CN110341763A (en) * | 2019-07-19 | 2019-10-18 | 东北大学 | A kind of intelligent dispatching system that fast quick-recovery high-speed rail train is run on schedule and method |
-
2019
- 2019-11-21 CN CN201911149049.2A patent/CN110843870B/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101441680A (en) * | 2008-12-18 | 2009-05-27 | 北京交通大学 | Method for improving high speed rail train operation right time rate by running chart robustness |
CN102129522A (en) * | 2011-03-17 | 2011-07-20 | 北京交通大学 | Method for quickly identifying and eliminating transportation capacity bottleneck of high-speed railway |
JP2013100034A (en) * | 2011-11-09 | 2013-05-23 | Hitachi Ltd | Train arrival time providing device |
KR101299526B1 (en) * | 2013-05-28 | 2013-08-23 | 한국철도공사 | System for train operation planning and method thereof |
CN104239726A (en) * | 2014-09-22 | 2014-12-24 | 北京交通大学 | Passenger flow estimation system under condition of urban rail road network emergency |
CN105678411A (en) * | 2015-12-30 | 2016-06-15 | 西南交通大学 | Passenger train operation scheme diagram drawing method |
CN105608896A (en) * | 2016-03-14 | 2016-05-25 | 西安电子科技大学 | Traffic bottleneck identification method in urban traffic network |
CN107122903A (en) * | 2017-04-27 | 2017-09-01 | 聊城大学 | A kind of measure of railway network structural reliability |
CN108256142A (en) * | 2017-12-13 | 2018-07-06 | 北京交通大学 | A kind of high-speed railway handling capacity calculation and analysis methods and system |
CN108491950A (en) * | 2018-01-25 | 2018-09-04 | 北京交通大学 | A kind of high-speed railway handling capacity computational methods considering multiple resources constraint |
CN108364127A (en) * | 2018-02-01 | 2018-08-03 | 北京市地铁运营有限公司 | A kind of road network passenger flow Collaborative Control optimization system |
CN109740839A (en) * | 2018-11-23 | 2019-05-10 | 北京交通大学 | Train Dynamic method of adjustment and system under a kind of emergency event |
CN109359788A (en) * | 2018-12-06 | 2019-02-19 | 西南交通大学 | A kind of initial late method for building up for influencing prediction model of bullet train |
CN109508751A (en) * | 2018-12-06 | 2019-03-22 | 西南交通大学 | The deep neural network model modeling method of the late time prediction of High Speed Railway Trains |
CN109583657A (en) * | 2018-12-06 | 2019-04-05 | 西南交通大学 | The operation figure redundancy time of train operation actual achievement data-driven is laid out acquisition methods |
CN109733445A (en) * | 2018-12-27 | 2019-05-10 | 中南大学 | The distributed scheduling method based on multi-Agent System Model under emergency event |
CN109754180A (en) * | 2018-12-29 | 2019-05-14 | 中南大学 | Emergency event terminates the high-speed railway train operation adjustment method under time uncertain condition |
CN109902864A (en) * | 2019-02-20 | 2019-06-18 | 吉林大学 | A kind of construction area Traffic Organization design method considering network prestowage equilibrium |
CN109840639A (en) * | 2019-03-05 | 2019-06-04 | 东北大学 | A kind of late time forecasting methods of high speed rail train operation |
CN110341763A (en) * | 2019-07-19 | 2019-10-18 | 东北大学 | A kind of intelligent dispatching system that fast quick-recovery high-speed rail train is run on schedule and method |
Non-Patent Citations (2)
Title |
---|
XU XIN-YUE EL.AL.: "An analytical method to calculate station evacuation capacity", 《中南大学学报(英文版)》 * |
黄令海等: "城市轨道交通车站动态瓶颈识别方法研究", 《铁道学报》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112070325B (en) * | 2020-11-12 | 2021-02-26 | 北京交通大学 | Road network train optimization method, device, equipment and storage medium under abnormal event |
CN112070325A (en) * | 2020-11-12 | 2020-12-11 | 北京交通大学 | Road network train optimization method, device, equipment and storage medium under abnormal event |
CN112249101A (en) * | 2020-11-17 | 2021-01-22 | 中南大学 | High-speed rail network delay propagation quantitative analysis method based on matrix representation |
CN112249101B (en) * | 2020-11-17 | 2022-03-11 | 中南大学 | High-speed rail network delay propagation quantitative analysis method based on matrix representation |
CN113291356A (en) * | 2021-06-24 | 2021-08-24 | 北京交通大学 | Dynamic train tracking interval calculation method |
CN113536692A (en) * | 2021-08-03 | 2021-10-22 | 东北大学 | Intelligent dispatching method and system for high-speed rail train in uncertain environment |
CN113536692B (en) * | 2021-08-03 | 2023-10-03 | 东北大学 | Intelligent dispatching method and system for high-speed rail train under uncertain environment |
CN113581261B (en) * | 2021-09-07 | 2022-09-20 | 东北大学 | Comprehensive performance evaluation system for high-speed railway stage adjustment plan |
CN113581261A (en) * | 2021-09-07 | 2021-11-02 | 东北大学 | Comprehensive performance evaluation system for high-speed railway stage adjustment plan |
CN113627694A (en) * | 2021-10-11 | 2021-11-09 | 中国铁道科学研究院集团有限公司通信信号研究所 | Inter-city railway train operation plan adjusting method and system considering outage |
CN114852136A (en) * | 2022-03-18 | 2022-08-05 | 北京交通大学 | Multi-professional collaborative adjustment method, system, equipment and medium for high-speed rail operation |
CN114852136B (en) * | 2022-03-18 | 2023-02-21 | 北京交通大学 | Multi-professional collaborative adjustment method, system, equipment and medium for high-speed rail operation |
CN114677563A (en) * | 2022-04-08 | 2022-06-28 | 李燕秋 | Neural network online learning method and system based on block chain |
CN115230777A (en) * | 2022-06-21 | 2022-10-25 | 中国科学院自动化研究所 | Scheduling policy adjustment method and device, electronic equipment and storage medium |
CN115230777B (en) * | 2022-06-21 | 2024-01-16 | 中国科学院自动化研究所 | Scheduling policy adjustment method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110843870B (en) | 2021-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110843870B (en) | Method for maintaining fixed capacity of high-speed railway network graph under abnormal event | |
Yue et al. | Optimizing train stopping patterns and schedules for high-speed passenger rail corridors | |
Cats et al. | Dynamic vulnerability analysis of public transport networks: mitigation effects of real-time information | |
Salido et al. | Robustness for a single railway line: Analytical and simulation methods | |
CN103984994B (en) | Method for predicting urban rail transit passenger flow peak duration | |
Guo et al. | Efficiency assessment of transit-oriented development by data envelopment analysis: Case study on the Den-en Toshi line in Japan | |
Salido et al. | Robustness in railway transportation scheduling | |
CN109508751B (en) | Deep neural network model modeling method for high-speed railway train late time prediction | |
CN106485359A (en) | A kind of urban track traffic section passenger flow estimation method based on train schedule | |
Wu et al. | Research on the operation safety evaluation of urban rail stations based on the improved TOPSIS method and entropy weight method | |
Li et al. | A dynamic simulation model of passenger flow distribution on schedule-based rail transit networks with train delays | |
Yang et al. | Stochastic process and simulation of traction load for high speed railways | |
Yin et al. | Optimal Bus‐Bridging Service under a Metro Station Disruption | |
CN104050319A (en) | Method for realtime online verification of complex traffic control algorithm | |
RU2662351C1 (en) | Railway section traffic activity operational control system | |
Zheng et al. | Bridging strategy for the disruption of metro considering the reliability of transportation system: Metro and conventional bus network | |
Zhang et al. | Coupling analysis of passenger and train flows for a large-scale urban rail transit system | |
Li et al. | Joint optimization of delay-recovery and energy-saving in a metro system: A case study from China | |
Liu et al. | Prediction algorithms for train arrival time in urban rail transit | |
CN114394135B (en) | Train operation diagram and path selection optimization method based on multi-granularity time-space network | |
Wang et al. | A simulation-based metro train scheduling optimization incorporating multimodal coordination and flexible routing plans | |
Li et al. | Metro train delay-recovery strategy considering passenger waiting time and energy consumption: a real-world case study | |
Sadrani et al. | Designing limited-stop bus services for minimizing operator and user costs under crowding conditions | |
Tiong et al. | Real-time train arrival time prediction at multiple stations and arbitrary times | |
Tian et al. | Identification of critical links in urban road network considering cascading failures |
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 | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200228 Assignee: Beijing Yunxin Networking Technology Co.,Ltd. Assignor: Beijing Jiaotong University Contract record no.: X2021990000808 Denomination of invention: A method for maintaining the fixed capacity of high-speed railway network under abnormal events Granted publication date: 20210101 License type: Common License Record date: 20211222 |
|
EE01 | Entry into force of recordation of patent licensing contract |