CN110427690A - A kind of method and device generating ATO rate curve based on global particle swarm algorithm - Google Patents
A kind of method and device generating ATO rate curve based on global particle swarm algorithm Download PDFInfo
- Publication number
- CN110427690A CN110427690A CN201910690478.4A CN201910690478A CN110427690A CN 110427690 A CN110427690 A CN 110427690A CN 201910690478 A CN201910690478 A CN 201910690478A CN 110427690 A CN110427690 A CN 110427690A
- Authority
- CN
- China
- Prior art keywords
- particle
- train
- target
- swarm algorithm
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002245 particle Substances 0.000 title claims abstract description 304
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000004364 calculation method Methods 0.000 claims abstract description 90
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims description 29
- 238000005457 optimization Methods 0.000 claims description 26
- 230000001133 acceleration Effects 0.000 claims description 15
- 238000005265 energy consumption Methods 0.000 claims description 10
- YTAHJIFKAKIKAV-XNMGPUDCSA-N [(1R)-3-morpholin-4-yl-1-phenylpropyl] N-[(3S)-2-oxo-5-phenyl-1,3-dihydro-1,4-benzodiazepin-3-yl]carbamate Chemical compound O=C1[C@H](N=C(C2=C(N1)C=CC=C2)C1=CC=CC=C1)NC(O[C@H](CCN1CCOCC1)C1=CC=CC=C1)=O YTAHJIFKAKIKAV-XNMGPUDCSA-N 0.000 claims 1
- 230000006870 function Effects 0.000 description 48
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a kind of method and devices that ATO rate curve is generated based on global particle swarm algorithm, after establishing overall fitness function, optimal particle is searched by particle swarm algorithm, ATO rate curve is determined according to the corresponding duty parameter of optimal particle and operating conditions sequence type.Wherein, when being iterated to calculate by particle swarm algorithm, the duty parameter of intended particle when determining this calculating according to the calculated result of the calculated result of either objective particle history and preceding primary each particle of the overall situation in current iteration calculating process, and the overall fitness function is calculated according to the value of each train runing parameters determined by the duty parameter and the operating conditions sequence type, obtain this calculated result of the intended particle.Every time when iterative calculation, the calculated result of single particle history is not only considered, it is also contemplated that the calculated result of global particle also improves convergence speed of the algorithm while improving global search performance and improving search precision.
Description
Technical Field
The invention relates to the technical field of train operation control, in particular to a method and a device for generating an ATO speed curve based on a global particle swarm algorithm.
Background
With the rapid development of urban rail transit in China, higher requirements are put forward on indexes such as safety, parking precision, punctuality, passenger comfort level, energy consumption and the like of automatic operation of urban rail trains. The ATO system is used as an important subsystem of the ATC system, and has the main functions of realizing automatic running, accurate stopping, unmanned turning back, train running adjustment and the like of a train by utilizing ground information, a running control instruction and necessary manual operation. The ATO system can avoid unnecessary acceleration and deceleration operations, so that the train is in the optimal running state, the overall running efficiency of the urban rail transit train and the comfort level of passengers are improved, and meanwhile, the energy consumption of train running is reduced. Therefore, the recommended speed curve of the urban rail transit train is a key strategy for realizing high-quality train automatic driving.
The optimization problem of the recommended speed curve of the urban rail transit train is a high-dimensional, nonlinear and multi-objective constraint optimization problem, so that the solution of the model is very difficult, and the existing solution method mainly comprises a numerical algorithm and an evolutionary algorithm. The numerical algorithm comprises dynamic programming, sequential quadratic programming and methods based on Lagrangian multipliers, has less requirement on an objective function, and can balance optimization performance with calculation time. Evolutionary algorithms, such as Genetic Algorithm (GA), Ant Colony Optimization (ACO), particle swarm algorithm (PSO) and simulated annealing algorithm (SA), have the lowest requirements for models in train speed curve optimization.
The numerical algorithm needs to establish a strict mathematical model, the dimension becomes higher and higher along with the complication of the track line, the strict mathematical model is difficult to define, and the methods are easy to generate dimension disasters and cannot solve the problem that an objective function is not guided. Therefore, the intelligent optimization methods are applied, can solve the irreducible problem and have the advantages of simple principle, strong robustness, high searching speed and the like. However, the original intelligent optimization method has the defects of easy falling into local optimization, low search precision, poor global optimization capability and the like.
In the practical application process, the inventor finds that the existing speed curve calculation method is poor in global optimization capability and low in search accuracy, and cannot search for the optimal speed curve.
Disclosure of Invention
The embodiment of the invention provides a method and a device for generating an ATO speed curve based on a global particle swarm algorithm, which are used for solving the problems that a speed curve calculating method in the prior art is poor in global optimization capability and low in search precision, and an optimal speed curve cannot be searched.
In view of the above technical problems, in a first aspect, an embodiment of the present invention provides a method for generating an ATO speed curve based on a global particle swarm algorithm, including:
acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm;
when iterative computation is carried out through a particle swarm algorithm, determining working condition parameters of target particles during the iterative computation according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and computing the overall fitness function according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the computation results of the target particles at this time;
and after each particle in the particle swarm algorithm meets the calculation termination condition, determining the optimal particle according to the calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating the ATO speed curve of the target train according to the working condition parameters corresponding to the optimal particle and the working condition control sequence type.
In a second aspect, an embodiment of the present invention provides an apparatus for generating an ATO speed curve based on a global particle swarm algorithm, including:
the system comprises an acquisition module, a calculation module and a control module, wherein the acquisition module is used for acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm;
the calculation module is used for determining the working condition parameters of the target particles during current calculation according to the historical calculation results of any target particle and the calculation results of all the particles of the previous time in the current iterative calculation process when iterative calculation is carried out through a particle swarm algorithm, and calculating the overall fitness function according to the values of the train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the current calculation results of the target particles;
and the generating module is used for determining the optimal particles according to the calculation result of each particle during iterative calculation through the particle swarm algorithm each time after each particle in the particle swarm algorithm meets the calculation termination condition, and generating the ATO speed curve of the target train according to the final working condition parameter corresponding to the optimal particles and the working condition control sequence type.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method for generating an ATO speed curve based on a global particle swarm algorithm as described in any one of the above items when executing the program.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for generating an ATO speed profile based on a global particle swarm algorithm as set forth in any of the above.
The embodiment of the invention provides a method and a device for generating an ATO speed curve based on a global particle swarm algorithm. When iterative computation is performed through a particle swarm algorithm, working condition parameters of target particles during the iterative computation are determined according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and the overall fitness function is computed according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types, so that the computation results of the target particles at this time are obtained. In each iterative computation, not only the historical computation results of the single particles are considered, but also the computation results of the global particles are considered, so that the global search performance and the search accuracy are improved, and meanwhile, the convergence rate of the algorithm is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the technical solutions in the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for generating an ATO velocity curve based on a global particle swarm algorithm according to an embodiment of the present invention;
fig. 2 is a sequence U ═ according to another embodiment of the present invention1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]Schematic diagram of the position change of (1);
FIG. 3 is a schematic diagram of a specific flow chart for generating an ATO speed curve based on a global particle swarm algorithm according to another embodiment of the present invention;
FIG. 4 is a convergence curve of the AGPSO algorithm optimization model for solving the overall fitness value according to another embodiment of the present invention;
FIG. 5 is an ATO recommended target speed curve generated for solving a train scheduled autopilot time of 90 seconds according to another embodiment of the present invention;
FIG. 6 is a block diagram of a device for generating an ATO velocity profile based on global particle swarm optimization according to another embodiment of the present invention;
fig. 7 is a block diagram of an electronic device according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for generating an ATO speed curve based on a global particle swarm algorithm provided in this embodiment, and referring to fig. 1, the method includes:
101: acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm;
102: when iterative computation is carried out through a particle swarm algorithm, determining working condition parameters of target particles during the iterative computation according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and computing the overall fitness function according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the computation results of the target particles at this time;
103: and after each particle in the particle swarm algorithm meets the calculation termination condition, determining the optimal particle according to the calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating the ATO speed curve of the target train according to the working condition parameters corresponding to the optimal particle and the working condition control sequence type.
The method provided by the embodiment is executed by a device installed with software for executing the method, and the device may be a server, a computer, or a device for generating an ATO speed curve on a vehicle, which is not particularly limited by the embodiment.
It should be noted that the method provided by the present embodiment is generally used for determining an ATO speed curve of a train running between two stations. The calculation result of each iteration calculation of the target particles is the value of the overall fitness function. After the type of the working condition control sequence is determined, the speed curve can be determined through the working condition parameters, and the value of each train operation parameter of the train which operates according to the determined speed curve can also be obtained.
Specifically, 101 in the above method may include (1) setting relevant parameters and population numbers, initializing the velocity and position of the particles in the search space using a reverse learning strategy, and (2) calculating corresponding fitness values after all particle initializations according to a fitness evaluation formula. The above 102 may include (3) calculating a fitness value for each particle. Updating and storing the individual historical optimal position and the group historical optimal position, and (4) respectively updating the speed and the position of the particle according to a speed updating formula and a position updating formula. 103 may include (5) determining whether an end condition is satisfied, if so, ending the calculation, and generating a recommended speed profile for the train, otherwise, turning to step (2).
The embodiment provides a method for generating an ATO speed curve based on a global particle swarm algorithm, wherein after a total fitness function is established, optimal particles are searched through the particle swarm algorithm, and the ATO speed curve is determined according to working condition parameters and working condition control sequence types corresponding to the optimal particles. When iterative computation is performed through a particle swarm algorithm, working condition parameters of target particles during the iterative computation are determined according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and the overall fitness function is computed according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types, so that the computation results of the target particles at this time are obtained. In each iterative computation, not only the historical computation results of the single particles are considered, but also the computation results of the global particles are considered, so that the global search performance and the search accuracy are improved, and meanwhile, the convergence rate of the algorithm is improved.
Further, on the basis of the above embodiment, the obtaining of the evaluation index to be satisfied by the target train operation and the set operating condition control sequence type of the target train operation, generating the overall fitness function according to the relationship between each evaluation index and the train operation parameter, and setting the algorithm parameter of the particle swarm algorithm includes:
obtaining an evaluation index which is required to enable the target train to run and meet, wherein the obtained evaluation index comprises a safety index, an punctuality index, a parking precision index, a comfort index and an energy consumption index, and the type of the working condition control sequence is set as U ═ U [1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]Wherein U is a type of a working condition control sequence, U1、u2、u3、u4And u5Representing the acceleration and deceleration states of the train under different working conditions;
generating the global fitness function Ktotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeWherein, K isvAs a function of a safety index expressed in terms of train operating parameters, KtAs a function of an on-time index expressed in terms of train operating parameters, KsAs a function of a stopping accuracy index expressed in terms of train operating parameters, KcAs a function of the comfort index expressed in terms of train operating parameters, KeAs a function of an energy consumption index expressed in terms of train operating parameters, ω1、ω2、ω3、ω4And ω5Are each Kv、Kt、Ks、KcAnd KeAt the global fitness function KtotalThe weight in (1);
setting and setting algorithm parameters of a particle swarm algorithm, wherein the algorithm parameters of the particle swarm algorithm comprise the population particle number, the search space dimension and the maximum iteration number of iterative computation that each particle meets the computation termination condition;
the train operation parameters comprise the limit speed of operation, the actual speed of train operation, the set operation time of the train, the actual operation time of the train, the target stop position of the train, the actual stop position of the train, the acceleration of the train, the traction of the train and the braking force of the train.
Further, on the basis of the above-described embodiments, Ktotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeIn, Kv＝∑Kj，Ks＝|xstop-xdestination|，
Wherein,vmaxis the ATP limit speed, K, of the j-th step of the trainjOverspeed judgment index, v, indicating the jth step of the trainjRepresents the actual speed of the jth step train, T represents the running time of the ATS system to the ATO,representing the sum of the running times, x, of the train under various operating conditionsdestinationIndicating a target stopping point, x, of the trainstopIndicating the actual stopping point of the train,representing the running time t of the train under various working conditionsiAnd acceleration aiSum of absolute values of products, fiIndicating magnitude of tractive or braking force, s, in i operating conditionsiThe walking distance in the i working conditions is shown, and i is the type of the working conditions.
Further, fi＝Miai，MiIndicating the quality of the train.
In addition, u is1、u2、u3、u4And u5Indicating the acceleration and deceleration states of the train under different working conditions when u1、u2、u3、u4Or u5The assignment of 0 indicates that the train runs at a constant speed under the corresponding working condition, the assignment of 1 indicates that the train runs at a constant acceleration under the corresponding working condition, and the assignment of-1 indicates that the train runs at a constant deceleration under the corresponding working condition. There are many types of operation condition control sequence types, and in this embodiment, U ═ U is selected1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]This type is the most common type of condition control sequence. The overall fitness function is an ATO speed curve recommended by the urban rail transit trainThe mathematical model of (1).
The embodiment provides a method for generating an ATO speed curve based on a global particle swarm algorithm, wherein when a mathematical model overall fitness function is established, 5 indexes, namely a safety index, a punctuality index, a parking precision index, a comfort index and an energy consumption index, are considered, and the established ATO speed curve can meet the 5 indexes. The algorithm parameters of the initialized particle swarm optimization lay the foundation for subsequent calculation by utilizing the particle swarm optimization.
Specifically, the step (1) includes: in the particle swarm operation process, the inertia weight value range omega in the formula is updatedmax＝0.9，ωmin0.4; the population number Popsize is 40; c1 ═ 2, c2 ═ 2; the maximum iteration number NI is 1000; the search space dimension D is 2.
For the step (2), the fitness evaluation of the recommended ATO speed curve mainly comprises five aspects of safety, punctuality, parking precision, passenger comfort, energy consumption and the like. Under different working conditions, the speed and distance information of the train running in the whole line can be calculated by taking time as an iteration step length, and the adaptability value of each index corresponding to each particle can be further calculated. The ATO computation time iteration step size is chosen to be 100 ms.
For K mentioned abovev、Kt、Ks、KcAnd KeThe above representation can be made by train operating parameters. Omega1、ω2、ω3、ω4And ω5The sum of (1).
In practice, the solution of the ATO speed curve can be regarded as a process of finding a set of condition control sequences and the condition change positions corresponding thereto. In order to achieve the aim of controlling the automatic driving of the train, the automatic driving of the train cannot be realized by depending on a certain working condition, the automatic driving of the train needs to be completed by selecting various working conditions at a plurality of positions in a matching way, and the number of the working conditions is selected by combining the line conditions. In this embodiment, a common operating condition control sequence U ═ U is selected1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]The corresponding working condition change positions are respectively analyzedX＝[x1,x2,x3]And X ═ X1,x2,x3,x4,x5]. Fig. 2 illustrates the operating condition control sequence U ═ U according to this embodiment1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]As shown in fig. 2, the abscissa represents the train running distance; the ordinate represents the train running speed; s1、S2、S3、S4And S5Representing the running distance of the train in each working condition; v. of0、v1、v2、v3、v4And v5Respectively representing the train starting speed and the train running speed of each working condition turning point; v. ofmax_1And vmax_2Is two speed limit levels; l is1And L2Distance range, L, representing two speed limit classes1And L2The sum equals the distance between the two stations. Suppose that the running time of the train under 5 working conditions is t respectively1、t2、t3、t4And t5(ii) a Defining train running time as Tmax(ii) a Acceleration of train traction of ajia＝0.6m/s2Braking deceleration of ajian＝-0.6m/s2. The condition control sequence is used to generate an ATO speed profile from station a to station B for the target train.
Further, on the basis of the foregoing embodiments, generating the overall fitness function includes:
setting the acceleration corresponding to the acceleration of the target train as ajiaAcceleration corresponding to deceleration is ajianThen the operating condition can be controlled by the control sequence under the operating condition u1The distance S for running the target train1And in operating mode u5The distance S for running the target train5Determining a speed curve;
respectively determining the distances S on the assumption that the target train meets the parking precision index and the safety index1And a distance S5In the case of feasible region of (2), the punctuality index is used as a constraint condition for Ktotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeOptimizing to obtain ftotal＝ω1Kc+ω2Ke+λφ(Kt) A 1 is to ftotal＝ω6Kc+ω7Ke+λφ(Kt) As a function of the overall fitness;
wherein, ω is6And ω7Respectively K in the optimized overall fitness functioncAnd KeWeight of phi (K)t)＝max(KtTolerance,0), Tolerance being the Tolerance of the punctuality index constraint, and λ being φ (K) in the overall fitness function after optimizationt) The weight of (c).
Specifically, after the operating condition control sequence type is selected, the overall fitness function can be simplified by using the relationship of the train operating parameters determined by the operating condition control type. For step (2) above, the following relationship (i.e., for K) can be obtained by using the parameters of the type of condition control sequence shown in FIG. 2total＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KePerforming optimization comprises the following steps:
S1+S2≤L1 (1)
the first stage accelerates:
v1 2-v0 2＝2ajiaS1 (2)
v1＝v2 (4)
and a third stage of speed reduction:
vm 2-v2 2＝2ajian(L1-S1-S2) (5)
the fifth stage of speed reduction:
v5 2-v4 2＝2ajianS5 (7)
from the above equations (1) to (8), the following relationships can be obtained:
S4＝L1+L2-S1-S2-S3-S5 (14)
as can be seen from the formulae (9) to (14), S2Upper limit of S1Determination of S3From S1And S5And (4) jointly determining. Therefore, only the S needs to be initialized for establishing the ATO speed curve optimization model1And S5。
To meet the safety index of automatic train operation, the train is at L1Section run speed is not greater than vmax_1(ii) a The train is on L2Section run speed is not greater than vmax_2. Then the security index may be satisfied (i.e., K)vZero) respectively determine the distances S1And distanceS5Feasible field of, distance S1And a distance S5The feasible fields of (1) are:
due to L1And L2The sum of the distances is equal to the distance between the two stations, so that the overall fitness function meets the parking accuracy index (namely K)sIs zero).
Then, the punctuality index is used as a constraint condition, the tolerance of the constraint condition is set to be 0.01s, and when U is equal to [ U ]1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]Under the operating condition control sequence of (1), Kt＝|Tmax-t1-t2-t3-t4-t5|。
Then formula Ktotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeFunction K of the security index of the expression (1)vAnd KsTo zero, the formula can be simplified to ftotal＝ω6Kc+ω7Ke+λφ(Kt). Wherein the weight coefficient (e.g., ω)6、ω7And λ) are assigned following the same order of magnitude principle as the fitness value of the objective function. Omega can be set1＝0.52×106，ω20.48. λ is a constraint penalty coefficient, λ is 1020。φ(Kt) Is a violation quantity, phi (K)t)＝max(KtTolerance,0), Tolerance 0.01 is the Tolerance of the punctuality constraint. The smaller the overall fitness function result, the better.
The embodiment provides a method for generating an ATO speed curve based on a global particle swarm algorithm, which optimizes a total fitness function, simplifies a subsequent calculation process and improves the operation efficiency.
Further, on the basis of the foregoing embodiments, when performing iterative computation by using a particle swarm algorithm, determining the operating condition parameters of the target particles during the current iterative computation according to the historical computation results of any target particle and the computation results of global particles of the previous time in the current iterative computation process includes:
distance S when iteratively calculated by particle swarm optimization1And a distance S5Constructing a search space of the particles as a search space dimension of a particle swarm algorithm;
in the iterative calculation process, acquiring a total fitness function f from the calculation result of the target particle historytotalAt a minimum, the individual best position of the target particle in the search spaceAnd the last position of the target particle at the last iterative computationAnd the last moving speedAnd obtaining a total fitness function f from the calculation result of each global particle of the last iteration calculationtotalGlobal optimum position gbest for the smallest particled；
According to the formulaDetermining the position of the target particle in the current calculation according to a formulaDetermining the moving speed of the time, and determining the distance S in the search space according to the position of the target particles during the calculation of the time1And a distance S5As the working condition parameter of the target particle during the current calculation;
where i denotes the number of the particle, d denotes the search space dimension, ω ═ cos (π. alpha.),NI isThe maximum iteration number of the iterative computation satisfying the computation termination condition in the algorithm parameters, ni is the currently computed iteration number, c1And c2For initialized algorithm parameters, r1、r2And each of alpha and rho is [ 0-1 ]]A uniform random number in between.
Further, on the basis of the foregoing embodiments, the calculating the overall fitness function according to the values of the train operation parameters determined by the operating condition parameters and the operating condition control sequence types to obtain the current calculation result of the target particle includes:
determining the distance S according to the position of the target particle in the current calculation1And a distance S5Determining a speed curve according to the type of the working condition control sequence, acquiring the value of each train operation parameter of the target train operation according to the determined speed curve, and calculating f according to the acquired value of each train operation parametertotalCalculated ftotalThe value of (b) is the calculation result of the target particle this time.
Further, λ is 0.5.
In the iterative calculation process of the particle swarm optimization, the position of each particle in the search space is updated when each particle is calculated next time according to the historical calculation result and the calculation result of the last global particle.
In the method for generating an ATO speed curve based on a global particle swarm algorithm provided by this embodiment, the improvement on the particle swarm algorithm has the following advantages: a. the weight is improved to cosine mapping, so that not only can the population diversity in the searching process be enhanced, but also the global optimum capability of the algorithm can be enhanced; b. the inertia weight can be diversified by adding random influence factors; c. the influence factor delta in the speed updating formula is reduced along with the increase of the iteration times, the influence factor beta is increased along with the increase of the iteration times, and the two influence factors are added, so that the speed updating of the particles tends to be updated according to the individual optimal positions of the particles in the initial stage of the iteration, and particularly, the particles prefer to be updated according to the global optimal values of the particles in the later stage of the iteration; d. by introducing the influence factors, the method changes the particle updating speed mode, expands the search space of the algorithm, can effectively improve the convergence speed of the algorithm, avoids falling into local optimum, and improves the global search performance of the PSO.
Specifically, in each iteration of the step (3), the particle calculates a fitness value through a fitness function, and updates and stores the individual optimal position pbest of the particle through comparisoni＝[pbesti 1,pbesti 2,...,pbesti D]And the optimal position gbest of the whole populationi＝[gbest1,gbest2,...,gbestD]。
For the step (4), the speed and the position of the particles are respectively updated according to a speed updating formula and a position updating formula, and the speed updating formula and the position updating formula of the self-adaptive global particle swarm algorithm are respectively as follows:
wherein ω ═ cos (pi × α);alpha and rho are [ 0-1%]A uniform random number in between; λ is 0.5.
Further, on the basis of the foregoing embodiments, after each particle in the particle swarm algorithm meets the calculation termination condition, determining an optimal particle according to a calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating an ATO speed curve of the target train according to a condition parameter corresponding to the optimal particle and the condition control sequence type, includes:
after the iterative computation times of each particle are greater than or equal to the set maximum iterative times corresponding to the particles, acquiring a total fitness function f from the historical computation result of the target particles for any target particletotalAt a minimum, the individual of the target particle in the search spaceAn optimal position;
obtaining a calculated global fitness function f of each particle at its corresponding individual optimal positiontotalWill be the smallest ftotalThe corresponding particle is taken as the optimal particle, and the distance S corresponding to the optimal particle is determined1And a distance S5And generating an ATO speed curve of the target train.
The selection of the optimal particles takes the calculation results of each particle into consideration, so that the global search is realized, and the generated ATO speed curve is ensured to be the optimal speed curve.
Specifically, the step (5) includes: and (3) judging whether the iteration times of the algorithm reach the set maximum iteration times, if so, finishing the calculation, and generating a recommended speed curve of the train, otherwise, turning to the step (2).
Further, on the basis of the above embodiments, the method further includes:
and sending the ATO speed curve to the ATO of the target train so that the ATO of the target train controls the target train to run according to the ATO speed curve.
Further, on the basis of the above embodiments, before the iterative computation by the particle swarm algorithm, the method further includes:
for any one of the target particles, at a determined distance S1And a distance S5Within the feasible region of (a) obtaining a randomly selected distance S1And a randomly selected distance S5And at a distance S1Within the feasible region of (1) obtaining the distance S1At a maximum value of S5Within the feasible region of (1) obtaining the distance S5Maximum value of (d);
calculating the distance S1Is a maximum value of (d) and a randomly selected distance S1Calculating the distance S from the first difference5Is a maximum value of (d) and a randomly selected distance S5A second difference of (a);
will randomly select a distance S1And the smaller of the first difference is taken as the initial distance S1Will randomly select the distance S5And the smaller of the second difference is taken as the initial distance S5Will be the initial distance S1And an initial distance S5The position in the search space is used as an initialization position of the target particle.
The present embodiment provides a step of initializing each particle in a particle swarm algorithm, that is, the step (1) specifically further includes: initializing group position Pop (ni ═ 0) { x ] in feasible domainij1,2, …, Popsize, j 1,2, …, D; obtaining a reverse initial population position Pop '(ni is 0) { x'ijAnd (e.g., the corresponding positions of the first difference and the second difference in the search space), wherein the inverse population calculation formula is: x'ij＝xmax-xij，XmaxIs the particle position XijMaximum value, x'ijAssigning the boundary value to x 'when the boundary is out of range'ij(ii) a Selecting a smaller population position X from the initial population and the reverse initial populationijAs an initial position of the population, min { Pop (ni ═ 0) uepo' (ni ═ 0) }.
The method for initializing particles provided by the method for generating the ATO speed curve based on the global particle swarm algorithm provided by the embodiment improves the quality of an initial solution, improves the chance of finding a global optimal solution by the algorithm, and accelerates the convergence speed of the algorithm.
Fig. 3 is a schematic diagram of a specific flow of generating an ATO speed curve based on a global particle swarm algorithm provided in this embodiment, and referring to fig. 3, parameters of an AGPSO algorithm (i.e., a population particle algorithm) are initialized, a particle speed and a particle position are initialized according to a line and a speed limit parameter, and then an iterative computation process of the population particle algorithm is performed. In this process, a fitness value (i.e., a value of the overall fitness function) of each particle is calculated, and whether f (x) is satisfied or not is determinedi)＜f(pi) If so, then pi＝xi(i.e., finding the best position of the individual) and determining whether f (p) is satisfiedi) < f (gbest), if so, gbest ═ pi pi＝xiAnd (i.e. searching for a global optimal position), updating the particle speed according to a speed updating formula, updating the particle position according to a particle position formula until a stopping condition is met, ending iterative computation, and generating a train recommended speed curve according to the optimal particle.
In order to verify the effectiveness of the adaptive global particle swarm algorithm and the mathematical model of the recommended speed curve of the train, two stations A and B in the Guangzhou subway No. 1 line are selected as an example, the total length of the line is 1228.40m, the safety margin of the two stations is considered, and the distance between the two stations is 969.22 m. The speed limit between stations is 75km/h at 0-658.4 m, and 55km/h at 658.4-969.22 m. In order to stop accurately, the train needs to pass through the calibration position of the transponder, and the arrangement principle of the transponder is that the stations are dense and the stations are sparse. Platform a to platform B stipulate a train operation time of 90 seconds. Considering the ideal case, the curvature is neglected for the whole line and the slope is zero. The train traction acceleration is assumed to be 0.6m/s2The braking deceleration is-0.6 m/s2. Table 1 is a train operation parameter comparison table.
TABLE 1 train operation parameter comparison table
In the experiment, MATLAB is used as a simulation platform to perform simulation experiment operation for 30 rounds, and the iteration number of each round is 300.
The optimization result comparison data are shown in table 2, and the optimal comfort fitness value, the optimal energy consumption fitness value and the optimal overall fitness value are recorded.
TABLE 2 fitness optimization results comparison data
Fig. 4 is a convergence curve of the AGPSO algorithm optimization model provided in this embodiment for solving the overall fitness value, and the algorithm has a better convergence speed and search accuracy for optimizing the overall fitness value, and from specific data analysis, the result of the AGPSO algorithm can satisfy the constraint tolerance of the punctuality index. Therefore, the experimental result of the AGPSO algorithm achieves the expected effect, and the effectiveness of the AGPSO algorithm in optimizing the generation problem of the recommended speed curve of the urban rail transit train is verified. The data results in Table 3 are the specific operating condition change times and positions obtained by solving the target speed curve. Fig. 5 is a graph for solving the ATO recommended target speed generated for the train specified autopilot time of 90 seconds.
TABLE 3 time(s) and position (m) of operating mode changes
The train recommended target speed curve generated by the method for generating the ATO speed curve based on the global particle swarm optimization provided by the embodiment can simultaneously meet five evaluation standards of safety, punctuality, passenger comfort and energy consumption, and is a high-quality train operation recommended speed curve; the main focus of the generated recommended speed curve of the train lies in the selection area of each working condition conversion point, and the train is easier to track in the actual running process of the train; the weighting standard of the bias of the train recommended speed curve can be adjusted through the inertia weight of each index.
Fig. 6 is a block diagram of a structure of the apparatus for generating an ATO speed curve based on a global particle swarm algorithm provided in this embodiment, referring to fig. 6, the apparatus includes an obtaining module 601, a calculating module 602, and a generating module 603, wherein,
the acquisition module 601 is used for acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relationship between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm;
a calculation module 602, configured to determine, during iterative calculation by a particle swarm algorithm, a working condition parameter of a target particle during the iterative calculation according to a historical calculation result of any target particle and a calculation result of each previous global particle during the iterative calculation, and calculate the overall fitness function according to a value of each train operation parameter determined by the working condition parameter and the working condition control sequence type, so as to obtain a current calculation result of the target particle;
and the generating module 603 is configured to determine an optimal particle according to a calculation result of each particle obtained through iterative calculation of the particle swarm algorithm each time after each particle in the particle swarm algorithm meets a calculation termination condition, and generate an ATO speed curve of the target train according to a final working condition parameter corresponding to the optimal particle and the working condition control sequence type.
The device for generating an ATO speed curve based on the global particle swarm algorithm provided by this embodiment is suitable for the method for generating an ATO speed curve based on the global particle swarm algorithm provided by the above embodiment, and details are not repeated here.
The embodiment provides a device for generating an ATO speed curve based on a global particle swarm algorithm, wherein after a total fitness function is established, optimal particles are searched through the particle swarm algorithm, and the ATO speed curve is determined according to working condition parameters and working condition control sequence types corresponding to the optimal particles. When iterative computation is performed through a particle swarm algorithm, working condition parameters of target particles during the iterative computation are determined according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and the overall fitness function is computed according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types, so that the computation results of the target particles at this time are obtained. In each iterative computation, not only the historical computation results of the single particles are considered, but also the computation results of the global particles are considered, so that the global search performance and the search accuracy are improved, and meanwhile, the convergence rate of the algorithm is improved.
Fig. 7 is a block diagram showing the structure of the electronic apparatus provided in the present embodiment.
Referring to fig. 7, the electronic device includes: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may call logic instructions in memory 730 to perform the following method: acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm; when iterative computation is carried out through a particle swarm algorithm, determining working condition parameters of target particles during the iterative computation according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and computing the overall fitness function according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the computation results of the target particles at this time; and after each particle in the particle swarm algorithm meets the calculation termination condition, determining the optimal particle according to the calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating the ATO speed curve of the target train according to the working condition parameters corresponding to the optimal particle and the working condition control sequence type.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present embodiments provide a non-transitory computer readable storage medium having stored thereon a computer program, the computer program being executable by a processor to perform the method of: acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm; when iterative computation is carried out through a particle swarm algorithm, determining working condition parameters of target particles during the iterative computation according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and computing the overall fitness function according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the computation results of the target particles at this time; and after each particle in the particle swarm algorithm meets the calculation termination condition, determining the optimal particle according to the calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating the ATO speed curve of the target train according to the working condition parameters corresponding to the optimal particle and the working condition control sequence type.
The present embodiments disclose a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments, for example, comprising: acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm; when iterative computation is carried out through a particle swarm algorithm, determining working condition parameters of target particles during the iterative computation according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and computing the overall fitness function according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the computation results of the target particles at this time; and after each particle in the particle swarm algorithm meets the calculation termination condition, determining the optimal particle according to the calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating the ATO speed curve of the target train according to the working condition parameters corresponding to the optimal particle and the working condition control sequence type.
The above-described embodiments of the electronic device and the like are merely illustrative, where 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 also be distributed on multiple 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.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable 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 methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the embodiments of the present invention, and are not limited thereto; although embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for generating an ATO speed curve based on a global particle swarm algorithm is characterized by comprising the following steps:
acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm;
when iterative computation is carried out through a particle swarm algorithm, determining working condition parameters of target particles during the iterative computation according to historical computation results of any target particles and computation results of all particles of the previous time in the iterative computation process, and computing the overall fitness function according to values of train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the computation results of the target particles at this time;
and after each particle in the particle swarm algorithm meets the calculation termination condition, determining the optimal particle according to the calculation result of each particle in each iterative calculation through the particle swarm algorithm, and generating the ATO speed curve of the target train according to the working condition parameters corresponding to the optimal particle and the working condition control sequence type.
2. The method for generating an ATO speed curve based on the global particle swarm algorithm according to claim 1, wherein the obtaining of the evaluation index to be satisfied by the target train operation and the set type of the operating condition control sequence of the target train operation, the generating of the global fitness function according to the relationship between each evaluation index and the train operation parameters, and the setting of the algorithm parameters of the particle swarm algorithm comprise:
obtaining an evaluation index which is required to enable the target train to run and meet, wherein the obtained evaluation index comprises a safety index, an punctuality index, a parking precision index, a comfort index and an energy consumption index, and the type of the working condition control sequence is set as U ═ U [1＝1,u2＝0,u3＝-1,u4＝0,u5＝-1]Wherein U is a type of a working condition control sequence, U1、u2、u3、u4And u5Representing the acceleration and deceleration states of the train under different working conditions;
generating the global fitness function Ktotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeWherein, K isvAs a function of a safety index expressed in terms of train operating parameters, KtAs a function of an on-time index expressed in terms of train operating parameters, KsAs a function of a stopping accuracy index expressed in terms of train operating parameters, KcFor comfort index expressed by train operating parametersFunction of, KeAs a function of an energy consumption index expressed in terms of train operating parameters, ω1、ω2、ω3、ω4And ω5Are each Kv、Kt、Ks、KcAnd KeAt the global fitness function KtotalThe weight in (1);
setting and setting algorithm parameters of a particle swarm algorithm, wherein the algorithm parameters of the particle swarm algorithm comprise the population particle number, the search space dimension and the maximum iteration number of iterative computation that each particle meets the computation termination condition;
the train operation parameters comprise the limit speed of operation, the actual speed of train operation, the set operation time of the train, the actual operation time of the train, the target stop position of the train, the actual stop position of the train, the acceleration of the train, the traction of the train and the braking force of the train.
3. The global particle swarm algorithm based ATO speed curve generation method of claim 2, wherein generating the overall fitness function comprises:
setting the acceleration corresponding to the acceleration of the target train as ajiaAcceleration corresponding to deceleration is ajianThen the operating condition can be controlled by the control sequence under the operating condition u1The distance S for running the target train1And in operating mode u5The distance S for running the target train5Determining a speed curve;
respectively determining the distances S on the assumption that the target train meets the parking precision index and the safety index1And a distance S5In the case of feasible region of (2), the punctuality index is used as a constraint condition for Ktotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeOptimizing to obtain ftotal＝ω1Kc+ω2Ke+λφ(Kt) A 1 is to ftotal＝ω6Kc+ω7Ke+λφ(Kt) As a function of the overall fitness;
wherein, ω is6And ω7Respectively K in the optimized overall fitness functioncAnd KeWeight of phi (K)t)＝max(KtTolerance,0), Tolerance being the Tolerance of the punctuality index constraint, λ being φ) K in the overall fitness function after optimizationt) The weight of (c).
4. The method for generating an ATO speed curve based on the global particle swarm algorithm according to claim 3, wherein when iterative computation is performed through the particle swarm algorithm, the determining of the working condition parameters of the target particles during the current computation according to the historical computation results of any target particle and the previous computation results of global particles during the current iterative computation comprises:
distance S when iteratively calculated by particle swarm optimization1And a distance S5Constructing a search space of the particles as a search space dimension of a particle swarm algorithm;
in the iterative calculation process, acquiring a total fitness function f from the calculation result of the target particle historytotalAt a minimum, the individual best position of the target particle in the search spaceAnd the last position of the target particle at the last iterative computationAnd the last moving speedAnd obtaining a total fitness function f from the calculation result of each global particle of the last iteration calculationtotalGlobal optimum position gbest for the smallest particled；
According to the formulaDetermining the position of the target particle in the current calculation according to a formulaDetermining the moving speed of the time, and determining the distance S in the search space according to the position of the target particles during the calculation of the time1And a distance S5As the working condition parameter of the target particle during the current calculation;
where i denotes the number of the particle, d denotes the search space dimension, ω ═ cos (π. alpha.),NI is the maximum iteration number of the iterative computation which satisfies the computation termination condition in the algorithm parameters, NI is the iteration number of the current computation, c1And c2For initialized algorithm parameters, r1、r2And each of alpha and rho is [ 0-1 ]]A uniform random number in between.
5. The method for generating an ATO speed curve based on a global particle swarm algorithm according to claim 4, wherein the calculating the overall fitness function according to the values of the train operation parameters determined by the operating condition parameters and the operating condition control sequence types to obtain the current calculation result of the target particles comprises:
determining the distance S according to the position of the target particle in the current calculation1And a distance S5Determining a speed curve according to the type of the working condition control sequence, acquiring the value of each train operation parameter of the target train operation according to the determined speed curve, and calculating f according to the acquired value of each train operation parametertotalCalculated ftotalThe value of (b) is the calculation result of the target particle this time.
6. The method for generating an ATO speed curve based on the global particle swarm algorithm according to claim 5, wherein after each particle in the particle swarm algorithm meets the calculation termination condition, the optimal particle is determined according to the calculation result of each particle during each iterative calculation through the particle swarm algorithm, and the ATO speed curve of the target train is generated according to the working condition parameter corresponding to the optimal particle and the working condition control sequence type, comprising:
after the iterative computation times of each particle are greater than or equal to the set maximum iterative times corresponding to the particles, acquiring a total fitness function f from the historical computation result of the target particles for any target particletotalAt a minimum, the individual best position of the target particle in the search space;
obtaining a calculated global fitness function f of each particle at its corresponding individual optimal positiontotalWill be the smallest ftotalThe corresponding particle is taken as the optimal particle, and the distance S corresponding to the optimal particle is determined1And a distance S5And generating an ATO speed curve of the target train.
7. The global particle swarm algorithm based ATO speed profile generating method of claim 1, further comprising:
and sending the ATO speed curve to the ATO of the target train so that the ATO of the target train controls the target train to run according to the ATO speed curve.
8. The method for generating an ATO velocity profile based on global particle swarm algorithm of claim 2, characterized in that K istotal＝ω1Kv+ω2Kt+ω3Ks+ω4Kc+ω5KeIn (1),
wherein,vmaxis the ATP limit speed, K, of the j-th step of the trainjRepresenting trainsOverspeed judgment index of step j, vjRepresents the actual speed of the jth step train, T represents the running time of the ATS system to the ATO,representing the sum of the running times, x, of the train under various operating conditionsdestinationIndicating a target stopping point, x, of the trainstopIndicating the actual stopping point of the train,representing the running time t of the train under various working conditionsiAnd acceleration aiSum of absolute values of products, fiIndicating magnitude of tractive or braking force, s, in i operating conditionsiThe walking distance in the i working conditions is shown, and i is the type of the working conditions.
9. The global particle swarm algorithm based ATO velocity profile generation method of claim 4, further comprising, before iterative computation by particle swarm algorithm:
for any one of the target particles, at a determined distance S1And a distance S5Within the feasible region of (a) obtaining a randomly selected distance S1And a randomly selected distance S5And at a distance S1Within the feasible region of (1) obtaining the distance S1At a maximum value of S5Within the feasible region of (1) obtaining the distance S5Maximum value of (d);
calculating the distance S1Is a maximum value of (d) and a randomly selected distance S1Calculating the distance S from the first difference5Is a maximum value of (d) and a randomly selected distance S5A second difference of (a);
will randomly select a distance S1And the smaller of the first difference is taken as the initial distance S1Will randomly select the distance S5And the smaller of the second difference is taken as the initial distance S5Will be the initial distance S1And an initial distance S5The position in the search space is used as an initialization position of the target particle.
10. A device for generating an ATO speed curve based on a global particle swarm algorithm is characterized by comprising the following steps:
the system comprises an acquisition module, a calculation module and a control module, wherein the acquisition module is used for acquiring evaluation indexes to be met by the target train operation and set working condition control sequence types of the target train operation, generating a total fitness function according to the relation between each evaluation index and train operation parameters, and setting algorithm parameters of a particle swarm algorithm;
the calculation module is used for determining the working condition parameters of the target particles during current calculation according to the historical calculation results of any target particle and the calculation results of all the particles of the previous time in the current iterative calculation process when iterative calculation is carried out through a particle swarm algorithm, and calculating the overall fitness function according to the values of the train operation parameters determined by the working condition parameters and the working condition control sequence types to obtain the current calculation results of the target particles;
and the generating module is used for determining the optimal particles according to the calculation result of each particle during iterative calculation through the particle swarm algorithm each time after each particle in the particle swarm algorithm meets the calculation termination condition, and generating the ATO speed curve of the target train according to the final working condition parameter corresponding to the optimal particles and the working condition control sequence type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910690478.4A CN110427690A (en) | 2019-07-29 | 2019-07-29 | A kind of method and device generating ATO rate curve based on global particle swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910690478.4A CN110427690A (en) | 2019-07-29 | 2019-07-29 | A kind of method and device generating ATO rate curve based on global particle swarm algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110427690A true CN110427690A (en) | 2019-11-08 |
Family
ID=68413020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910690478.4A Pending CN110427690A (en) | 2019-07-29 | 2019-07-29 | A kind of method and device generating ATO rate curve based on global particle swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110427690A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291856A (en) * | 2020-01-21 | 2020-06-16 | 大连海事大学 | Subway train operation and control multi-objective optimization method and system |
| CN111859484A (en) * | 2020-06-24 | 2020-10-30 | 苏州浪潮智能科技有限公司 | Method, device, equipment and storage medium for generating free-form surface part measurement sequence |
| CN113997915A (en) * | 2021-11-26 | 2022-02-01 | 北京大象科技有限公司 | Big data-based automatic train operation ATO (automatic train operation) accurate parking control method |
| CN114460843A (en) * | 2022-01-10 | 2022-05-10 | 西南交通大学 | In-vehicle pressure fluctuation iterative learning control method based on condition and performance matching |
| CN115002897A (en) * | 2021-03-02 | 2022-09-02 | 大唐移动通信设备有限公司 | Terminal positioning method, device, equipment and storage medium |
| CN115542767A (en) * | 2021-06-29 | 2022-12-30 | 中车株洲电力机车研究所有限公司 | Train operation control method, system and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018103704A1 (en) * | 2016-12-09 | 2018-06-14 | 比亚迪股份有限公司 | Train control method, tcms, vobc and train |
| WO2018121691A1 (en) * | 2016-12-29 | 2018-07-05 | 比亚迪股份有限公司 | Train automatic control method and apparatus, and vehicle-mounted automatic train operation system |
| CN109204391A (en) * | 2018-09-29 | 2019-01-15 | 交控科技股份有限公司 | A kind of target velocity curve based on multiobjective decision-making determines method |
-
2019
- 2019-07-29 CN CN201910690478.4A patent/CN110427690A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018103704A1 (en) * | 2016-12-09 | 2018-06-14 | 比亚迪股份有限公司 | Train control method, tcms, vobc and train |
| WO2018121691A1 (en) * | 2016-12-29 | 2018-07-05 | 比亚迪股份有限公司 | Train automatic control method and apparatus, and vehicle-mounted automatic train operation system |
| CN109204391A (en) * | 2018-09-29 | 2019-01-15 | 交控科技股份有限公司 | A kind of target velocity curve based on multiobjective decision-making determines method |
Non-Patent Citations (2)
| Title |
|---|
| 孟建军等: "基于遗传算法的高速列车ATO追溯目标曲线优化", 《计算机工程与应用》 * |
| 胡震等: "R-dPSO算法及其在ATO控制策略中的应用", 《计算机工程与应用》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291856A (en) * | 2020-01-21 | 2020-06-16 | 大连海事大学 | Subway train operation and control multi-objective optimization method and system |
| CN111291856B (en) * | 2020-01-21 | 2023-05-23 | 大连海事大学 | Multi-objective optimization method and system for operation and control of subway train |
| CN111859484A (en) * | 2020-06-24 | 2020-10-30 | 苏州浪潮智能科技有限公司 | Method, device, equipment and storage medium for generating free-form surface part measurement sequence |
| CN111859484B (en) * | 2020-06-24 | 2022-05-31 | 苏州浪潮智能科技有限公司 | Method, device, equipment and storage medium for generating free-form surface part measurement sequence |
| CN115002897A (en) * | 2021-03-02 | 2022-09-02 | 大唐移动通信设备有限公司 | Terminal positioning method, device, equipment and storage medium |
| CN115542767A (en) * | 2021-06-29 | 2022-12-30 | 中车株洲电力机车研究所有限公司 | Train operation control method, system and related device |
| CN113997915A (en) * | 2021-11-26 | 2022-02-01 | 北京大象科技有限公司 | Big data-based automatic train operation ATO (automatic train operation) accurate parking control method |
| CN113997915B (en) * | 2021-11-26 | 2022-06-24 | 北京大象科技有限公司 | Big data-based automatic train operation ATO (automatic train operation) accurate parking control method |
| CN114460843A (en) * | 2022-01-10 | 2022-05-10 | 西南交通大学 | In-vehicle pressure fluctuation iterative learning control method based on condition and performance matching |
| CN114460843B (en) * | 2022-01-10 | 2023-09-01 | 西南交通大学 | Condition and performance matching-based vehicle internal pressure fluctuation iterative learning control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427690A (en) | A kind of method and device generating ATO rate curve based on global particle swarm algorithm | |
| CN110341690B (en) | PHEV energy management method based on deterministic strategy gradient learning | |
| CN111047085B (en) | Hybrid vehicle working condition prediction method based on meta-learning | |
| CN111267831A (en) | Hybrid vehicle intelligent time-domain-variable model prediction energy management method | |
| CN113361777B (en) | Runoff prediction method and system based on VMD decomposition and IHHO optimization LSTM | |
| CN106600059A (en) | Intelligent power grid short-term load predication method based on improved RBF neural network | |
| CN109815523A (en) | Train operation multiple target differential evolution algorithm based on decomposition | |
| CN104900063B (en) | A kind of short distance running time Forecasting Methodology | |
| CN106910337A (en) | A kind of traffic flow forecasting method based on glowworm swarm algorithm Yu RBF neural | |
| CN103879414A (en) | Locomotive optimal manipulation method based on self-adaption A-Star algorithm | |
| CN107644266B (en) | Dynamic adjustment management method for vehicle entering and exiting warehouse | |
| CN112000001A (en) | PID parameter setting optimization method based on improved Bayesian model | |
| CN110471276A (en) | For creating the device of pattern function for physical system | |
| CN112132469B (en) | Reservoir group scheduling method and system based on multiple group cooperation particle swarm algorithm | |
| CN113835443A (en) | Trajectory planning method for quadrotor unmanned aerial vehicle based on non-traditional European distance field | |
| CN115270506B (en) | Method and system for predicting passing time of crowd ascending along stairs | |
| CN108320504B (en) | Dynamic OD matrix estimation method based on monitoring data | |
| CN114721429A (en) | Three-dimensional unmanned aerial vehicle track planning method and device based on improved differential evolution algorithm | |
| CN114355973A (en) | Multi-agent hierarchical reinforcement learning-based unmanned cluster cooperation method under weak observation condition | |
| CN113537580A (en) | Public transport passenger flow prediction method and system based on adaptive graph learning | |
| Tagliaferri et al. | A real-time strategy-decision program for sailing yacht races | |
| CN110110475A (en) | Extended Kalman filter method based on on-line study fading factor | |
| CN113033902A (en) | Automatic driving track-changing planning method based on improved deep learning | |
| Williams et al. | Locally weighted regression pseudo-rehearsal for adaptive model predictive control | |
| CN114648178B (en) | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191108 |