CN116011326A - Train operation optimization method and device, electronic equipment and storage medium - Google Patents
Train operation optimization method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116011326A CN116011326A CN202211699939.2A CN202211699939A CN116011326A CN 116011326 A CN116011326 A CN 116011326A CN 202211699939 A CN202211699939 A CN 202211699939A CN 116011326 A CN116011326 A CN 116011326A
- Authority
- CN
- China
- Prior art keywords
- train
- subinterval
- running
- train operation
- operation optimization
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides a train operation optimization method, a device, electronic equipment and a storage medium, and relates to the technical field of rail transit, wherein the method comprises the following steps: dividing the whole section operation line of the train into a plurality of subintervals; solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solving result; the train operation optimization model comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the minimum. According to the invention, the train operation curve is optimized based on the solving result of the train operation optimization model, and the objective function in the train operation optimization model is constructed by taking the weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the target, so that the noise pollution of the train can be reduced under the condition of lower train operation energy consumption, and the riding experience of passengers can be improved.
Description
Technical Field
The present invention relates to the field of rail transit technologies, and in particular, to a train operation optimization method, a device, an electronic device, and a storage medium.
Background
Along with the promotion of the urban rail transit process, the subway is rapidly developed by the characteristics of large transportation capacity, punctual time, quick arrival, comfort, safety, environmental protection and the like. The subway is used as one of public transportation backbone travel tools in the city, so that although the convenience of people traveling is improved, urban congestion is relieved, the problem of noise pollution in subway trains is gradually highlighted when subway transportation rapidly progresses, and the production and life of people and riding experience of passengers are directly influenced.
The subway train noise source mainly comprises traction noise, wheel track noise and pneumatic noise, and the train running speed is closely related to the main noise component, so that how to optimize the running of the train to reduce the noise pollution of the train and improve the riding experience of passengers becomes a problem to be solved in the industry.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a train operation optimization method, a train operation optimization device, electronic equipment and a storage medium.
In a first aspect, the present invention provides a train operation optimization method, including:
dividing the whole section operation line of the train into a plurality of subintervals;
solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solving result to obtain an operation optimization strategy of the train;
The train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
Optionally, according to the train operation optimization method provided by the invention, the construction process of the objective function includes:
determining the whole-course running energy consumption of the train based on the traction force output by the train in each subinterval and the running distance of the train in each subinterval, and determining the whole-course running noise of the train based on the sound pressure level noise output by the train in each subinterval;
and constructing the objective function based on the whole-course operation energy consumption of the train, the whole-course operation noise of the train and the weighting factor.
Optionally, according to the train operation optimization method provided by the invention, the expression of the objective function is:
wherein p represents a weighting factor, N represents the total number of the subintervals, i represents the index of the subintervals, F i Representing the traction force of the train output in the ith subinterval S i Indicating the cumulative travel distance of the train at the time of entering the ith subinterval, (L) P ) i And represents sound pressure level noise of the train output in the ith subinterval.
Optionally, according to the train operation optimization method provided by the invention, the expression of the time division constraint of the train operation is:
wherein N represents the total number of the subintervals, i represents the index of the subintervals, T i Representing the actual operating time of the train in the ith subinterval, T target Representing the target operating time division of the train, and delta represents the train operating time division threshold.
Optionally, according to the train operation optimization method provided by the invention, the constraint of the train operation start end terminal is as follows:
the running speed of the train at the start point between stations of the whole interval running line is 0, and the running distance of the train at the start point between stations is 0; the running speed of the train at the terminal point between stations of the whole interval running line is 0, and the running distance at the terminal point between stations is the running target distance of the train.
Optionally, according to the train operation optimization method provided by the invention, the expression of the train dynamics constraint is:
Wherein i represents the index of the subinterval, F i Representing the traction force of the train output in the ith subinterval, F max Representing the maximum traction force of the train output, B i Represents the braking force received by the train in the ith subinterval, B max Representing the maximum braking force of the train output, a i Representing the acceleration of the train in the ith subinterval, V i+1 Representing the speed of the train in the (i+1) th subinterval, V i Represents the speed of the train in the ith subinterval, deltaS i Representing the distance travelled by the train in the ith subinterval S i Represents the accumulated running distance of the train when entering the ith subinterval, S i+1 Indicating the accumulated running distance T of the train when entering the (i+1) th subinterval i Representing the actual operating time of the train in the ith subinterval, T i+1 Indicating the actual operating time of the train in the (i+1) th subinterval, w i And G represents the mass of the train.
Optionally, according to the train operation optimization method provided by the invention, the train speed limit constraint is as follows: the running speed of the train in each subinterval is smaller than the target limiting speed.
Optionally, according to the method for optimizing train operation provided by the present invention, the method for optimizing train operation based on the operation process of the train in each subinterval solves a train operation optimization model, optimizes the train operation curve based on the solution result, and obtains the train operation optimization strategy, including:
Determining an expected duration for obtaining an operation optimization strategy of the train;
under the condition that the expected duration is less than the preset duration, solving the train operation optimization model based on a particle swarm algorithm and the operation process of the train in each subinterval to obtain a first optimal solution of the train operation optimization model, and solving the train operation optimization model based on a reinforcement learning algorithm and the operation process of the train in each subinterval to obtain a second optimal solution of the train operation optimization model;
determining a first value of the objective function based on the first optimal solution and a second value of the objective function based on the second optimal solution;
determining a target value of the first value and the second value that is closer to 0;
under the condition that the target value is determined to be the first value, optimizing the running curve of the train based on the first optimal solution to obtain a running optimization strategy of the train;
and under the condition that the target value is determined to be the second value, optimizing the running curve of the train based on the second optimal solution to obtain a running optimization strategy of the train.
Optionally, according to the train operation optimization method provided by the invention, the method further comprises the following steps:
Under the condition that the expected time length is greater than or equal to the preset time length, solving the train operation optimization model based on a dynamic programming algorithm and the running process of the train in each subinterval to obtain a third optimal solution of the train operation optimization model;
and optimizing the running curve of the train based on the third optimal solution to obtain a running optimization strategy of the train.
In a second aspect, the present invention also provides a train operation optimizing apparatus, including:
the dividing module is used for dividing the whole interval running line of the train into a plurality of subintervals;
the solving module is used for solving the train operation optimization model based on the operation process of the train in each subinterval, optimizing the train operation curve based on the solving result and obtaining the train operation optimization strategy;
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
In a third aspect, the present invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the train operation optimization method according to the first aspect when executing the program.
In a fourth aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor implements the train operation optimization method according to the first aspect.
In a fifth aspect, the invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the train operation optimization method according to the first aspect.
According to the train operation optimization method, the device, the electronic equipment and the storage medium, the whole interval operation line of the train is divided into the plurality of subintervals, the train operation optimization model is solved based on the operation process of the train in each subinterval, and the operation curve of the train is optimized based on the solving result, so that the operation optimization strategy of the train is obtained.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of train noise versus speed provided by the related art;
FIG. 2 is one of the flow diagrams of the train operation optimization method provided by the invention;
FIG. 3 is a second flow chart of the train operation optimization method provided by the invention;
FIG. 4 is a schematic diagram of the train operation optimizing device provided by the invention;
fig. 5 is a schematic diagram of the physical structure of the electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to facilitate a clearer understanding of various embodiments of the present invention, some relevant background knowledge is first presented as follows.
The noise source of the subway train mainly comprises traction noise, wheel track noise and pneumatic noise. A great deal of research at home and abroad shows that the running speed of the train is closely related to the main components of noise, and FIG. 1 is a schematic diagram of the relationship between the noise and the speed of the train provided by the related technology, and when the running speed of the train is less than 35km/h, traction noise is dominant, and the contribution quantity to total noise is maximum; when the running speed of the train is 35-250km/h, wheel track noise is the main component; when the train running speed is greater than 250km/h, aerodynamic noise is the main component. At present, the running speed range of the subway train in China is generally 0-120km/h, and the speed interval is mainly traction noise and wheel track noise.
Wheel rail noise is the most important noise source for subway operation, including rolling noise, squeal and impact. The rolling noise is generated by the shortwave irregularity on the surface of the rail of the track structure exciting the vibration of the wheel rail through the air propagation. Howling is a high-pitched noise emitted when a vehicle is traveling on a small radius curve line. Impact noise is generated by localized discontinuities in the wheel or rail surface.
Traction sound pressure level noise L p1 And traction vibration velocity level L v1 Equivalently, the following formula is shown:
wheel track sound pressure level noise L p2 And traction vibration velocity level L v2 Equivalently, the following formula is shown:
pneumatic sound pressure level noise L p3 And traction vibration velocity level L v3 Equivalently, the following formula is shown:
wherein, in the above three expressions, V represents the actual operation of the trainSpeed, V ref Representing the reference speed, the value of which varies with the country acquisition region, V being taken in the United states ref ＝2.54×10 -8 m/s, european get V ref ＝1×10 -8 m/s, or V ref ＝5×10 -8 m/s, or V ref ＝1×10 -9 m/s。
The total noise of the subway is superposition of wheel track noise, traction noise and aerodynamic noise. According to the superposition method of sound pressure level noise, the total synthesized sound pressure level noise L can be calculated p . The conversion formula of the sound pressure level noise and the power level noise is as follows:
wherein P represents power level noise, P 0 Representing the reference power level noise.
The noise superposition and conversion formula of the sound pressure level is as follows:
wherein P is 1 Representing power level noise of wheel track, P 2 Representing traction power level noise, P 3 Representing aerodynamic power level noise.
The train operation optimizing method, the train operation optimizing device, the electronic equipment and the storage medium provided by the invention are exemplarily described below with reference to the accompanying drawings.
Fig. 2 is a schematic flow chart of a train operation optimization method provided by the invention, and as shown in fig. 2, the method includes:
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
It should be noted that, the execution main body of the train operation optimization method provided by the embodiment of the invention may be any electronic device or computer device. The following describes in detail the technical solution of the embodiment of the present invention, taking a train operation optimization system for performing train operation optimization as an execution subject.
Specifically, in order to overcome the defect that noise pollution exists in a subway train so as to influence passenger riding experience, the whole interval running line of the train is divided into a plurality of subintervals, and then a train running optimization model is solved based on the running process of the train in each subinterval, and the running curve of the train is optimized based on a solving result, so that a running optimization strategy of the train is obtained.
Optionally, the train operation optimization model provided by the embodiment of the invention may be pre-stored in the train operation optimization system.
It should be noted that, in the embodiment of the present invention, the basic idea of constructing the train operation optimization model is: and taking line data, train data, basic resistance and other data into consideration, and constructing a train operation optimization model by taking energy conservation and low noise as optimization targets under the constraint conditions of meeting the constraint conditions of time-division operation, start terminal constraint, train dynamics constraint, safety speed limit and the like. According to the constraint condition of the train operation line, the whole operation line of the train is divided into N subintervals (N is a positive integer).
Optionally, the whole interval operation line of the train can be divided into a plurality of subintervals based on the operation line condition or constraint of the train, and then the train operation optimization model is solved based on the operation process of the train in each subinterval.
It can be understood that, because the train operation optimization model in the embodiment of the invention is constructed based on the operation process of the train in a plurality of different subintervals, the requirement of dynamic adjustment of the train operation line can be met.
Optionally, the train operation optimization model provided by the embodiment of the invention comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the weighted sum of the whole-process operation energy consumption and the whole-process operation noise of the train as the minimum target, and the constraint conditions comprise train operation time-division constraint, train operation beginning end constraint, train dynamics constraint and train speed limit constraint.
It can be understood that, in the embodiment of the invention, the objective function in the train operation optimization model is constructed by taking the weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, namely, the optimization objective of the train operation optimization model is to solve the train operation curve with the minimum whole-course operation energy consumption and noise weighting, and the train operation is controlled based on the train operation curve, so that the noise pollution of the train can be reduced under the condition of lower train operation energy consumption.
It can be understood that in the embodiment of the invention, because the constraint conditions in the train operation optimization model comprise the train operation time-division constraint, the train operation start end constraint, the train dynamics constraint and the train speed limit constraint, the influence of factors such as the train operation line condition and the train dynamics characteristic on the train operation process is fully considered when the train operation curve is optimized, and the optimized train operation curve is ensured to be energy-saving and optimal for the operation of the train.
Optionally, the train operation optimization model can be solved based on the operation process of the train in each subinterval, and the operation curve of the train is optimized based on the solving result, so that the operation optimization strategy of the train is obtained, the train can be controlled to operate based on the operation optimization strategy, the train operation energy consumption can be ensured to be lower, and the noise pollution of the train can be reduced.
It will be appreciated that in embodiments of the present invention, the operating strategy of the train may include kinetic parameters of the train in each subinterval, including, for example, the speed and acceleration of the train in each subinterval.
According to the train operation optimization method provided by the invention, the whole interval operation line of the train is divided into a plurality of subintervals, so that the train operation optimization model is solved based on the operation process of the train in each subinterval, and the operation curve of the train is optimized based on the solving result, so that the train operation optimization strategy is obtained, wherein the strategy comprises the operation speed, the acceleration and the like of the train in each subinterval.
Optionally, the construction process of the objective function includes:
determining the whole-course running energy consumption of the train based on the traction force output by the train in each subinterval and the running distance of the train in each subinterval, and determining the whole-course running noise of the train based on the sound pressure level noise output by the train in each subinterval;
And constructing the objective function based on the whole-course operation energy consumption of the train, the whole-course operation noise of the train and the weighting factor.
Specifically, in the embodiment of the invention, when an objective function in a train operation optimization model is constructed, the whole-course operation energy consumption of the train can be determined firstly based on the traction force output by the train in each subinterval and the running distance of the train in each subinterval, and the whole-course operation noise of the train can be determined based on the sound pressure level noise output by the train in each subinterval, so that the objective function is constructed based on the whole-course operation energy consumption of the train, the whole-course operation noise of the train and the weighting factor.
It should be noted that, the train operation energy consumption includes traction energy consumption and auxiliary energy consumption, the train operation auxiliary energy consumption is auxiliary power supply power multiplied by train interval operation time, when the train interval operation time is fixed, the auxiliary energy consumption can be regarded as a constant, and the objective function is equivalent to solving a train operation curve with minimum whole-course traction energy consumption and noise weighting. The whole-process traction energy consumption of the train operation is the sum of the traction energy consumption of all the sub-processes, and the whole-process noise of the train operation is the sum of the noise of all the sub-processes.
Optionally, the expression of the objective function is:
wherein p represents a weighting factor, N represents the total number of the subintervals, i represents the index of the subintervals, F i Representing the traction force of the train output in the ith subinterval S i Indicating the cumulative travel distance of the train at the time of entering the ith subinterval, (L) P ) i And represents sound pressure level noise of the train output in the ith subinterval.
According to the train operation optimization method provided by the invention, the target function in the train operation optimization model is constructed by taking the minimum weighted sum of the traction energy consumption and the noise of the train operation as the target, namely, the optimization target of the train operation optimization model is the train operation curve with the minimum weighted energy consumption and noise of the whole train operation process, and the train operation is controlled based on the train operation strategy corresponding to the train operation curve, so that the noise pollution of the train can be reduced under the condition of lower train operation energy consumption.
Optionally, the expression of the train operation time division constraint is:
wherein N represents the total number of the subintervals, i represents the index of the subintervals, T i Representing the actual operating time of the train in the ith subinterval, T target Representing the target operating time division of the train, and delta represents the train operating time division threshold.
It can be understood that, as can be seen from the expression of the time-division constraint of the train operation, the embodiment of the invention makes the train operation curve with the minimum energy consumption and noise weighting of the whole train operation obtained based on the train operation optimization model by constraining the whole train operation time, and can ensure that the operation time of the train is within the planned operation time, thereby ensuring that the normal riding time or the normal traveling time of passengers is not influenced.
Optionally, the train operation start end constraint is:
the running speed of the train at the start point between stations of the whole interval running line is 0, and the running distance of the train at the start point between stations is 0; the running speed of the train at the terminal point between stations of the whole interval running line is 0, and the running distance at the terminal point between stations is the running target distance of the train.
Optionally, the expression of the train operation start end constraint is:
where v (0) denotes the speed of the start point between stations where the train operates, v (N) denotes the speed of the end point between stations where the train operates, S (0) denotes the travel distance of the train from the start point between stations, S (N) denotes the travel distance of the train to the end point between stations, and S denotes the distance from the start point between stations to the end point between stations.
It can be understood that in the embodiment of the invention, the running speed of the start point between stations, the running distance of the start point between stations, the running speed of the end point between stations and the running distance of the end point between stations are restrained in the running process of the train, so that the train running curve with the minimum whole-course energy consumption and noise weighting obtained based on the train running optimization model can ensure that the train normally starts or stops at the station.
Optionally, the expression of the train dynamics constraint is:
wherein i represents the index of the subinterval, F i Representing the traction force of the train output in the ith subinterval, F max Representing the maximum traction force of the train output, B i Represents the braking force received by the train in the ith subinterval, B max Representing the maximum braking force of the train output, a i Representing the acceleration of the train in the ith subinterval, V i+1 Representing the speed of the train in the (i+1) th subinterval, V i Represents the speed of the train in the ith subinterval, deltaS i Representing the distance travelled by the train in the ith subinterval S i Represents the accumulated running distance of the train when entering the ith subinterval, S i+1 Indicating the accumulated running distance T of the train when entering the (i+1) th subinterval i Representing the actual operating time of the train in the ith subinterval, T i+1 Indicating the actual operating time of the train in the (i+1) th subinterval, w i And G represents the mass of the train.
It should be noted that, during the running process of each subinterval, the state transition of the train is constrained by the maximum traction force and the braking force, so as to satisfy newton's second law of motion.
It can be understood that in the embodiment of the invention, the train running curve with the minimum whole-course energy consumption and noise weighting based on the train running optimization model can be ensured to still meet the dynamics characteristic of the train by restraining the dynamics characteristic of the train, so that the safe running of the train is ensured.
Optionally, the train speed limit constraint is: the running speed of the train in each subinterval is smaller than the target limiting speed.
Specifically, in order to ensure the running safety of the train, the speed during the running of the train cannot exceed a target limiting speed, wherein the target limiting speed comprises a train construction speed, a line speed limit, an outbound speed limit and the like.
Optionally, the expression of the train speed limit constraint is:
V i <V limit
Wherein V is i Representing the speed of the train in the ith subinterval, V limit Indicating the target limiting speed.
It can be understood that in the embodiment of the invention, the speed of the train in each subinterval is constrained, so that the train running curve with the minimum whole train running energy consumption and noise weighting obtained based on the train running optimization model can ensure the safe running of the train.
Optionally, the solving the train operation optimization model based on the operation process of the train in each subinterval, and optimizing the operation curve of the train based on the solving result, to obtain the operation optimization strategy of the train, including:
determining an expected duration for obtaining an operation optimization strategy of the train;
under the condition that the expected duration is less than the preset duration, solving the train operation optimization model based on a particle swarm algorithm and the operation process of the train in each subinterval to obtain a first optimal solution of the train operation optimization model, and solving the train operation optimization model based on a reinforcement learning algorithm and the operation process of the train in each subinterval to obtain a second optimal solution of the train operation optimization model;
Determining a first value of the objective function based on the first optimal solution and a second value of the objective function based on the second optimal solution;
determining a target value of the first value and the second value that is closer to 0;
under the condition that the target value is determined to be the first value, optimizing the running curve of the train based on the first optimal solution to obtain a running optimization strategy of the train;
and under the condition that the target value is determined to be the second value, optimizing the running curve of the train based on the second optimal solution to obtain a running optimization strategy of the train.
Specifically, in the embodiment of the invention, before solving the train operation optimization model, the expected duration of the user for obtaining the train operation optimization strategy can be determined, and then based on the expected duration, the train operation optimization model is solved by utilizing different solving methods.
Optionally, under the condition that the expected duration of the user is less than the preset duration, solving the train operation optimization model based on a particle swarm algorithm and the operation process of the train in each subinterval to obtain a first optimal solution of the train operation optimization model, solving the train operation optimization model based on a reinforcement learning algorithm and the operation process of the train in each subinterval to obtain a second optimal solution of the train operation optimization model, further determining a first value of an objective function in the train operation optimization model based on the first optimal solution, further determining a second value of the objective function in the train operation optimization model based on the second optimal solution, further determining a target value which is closer to 0 in the first value and the second value, and optimizing an operation curve of the train based on the first optimal solution under the condition that the target value is determined to be the first value; if the target value is determined to be the second value, the train operation curve is optimized based on the second optimal solution.
Optionally, the preset time period is not limited specifically, and may be adaptively set based on practical applications, for example, the preset time period may be 2 minutes, 5 minutes, or 10 minutes.
It can be appreciated that when the expected duration of the user is less than the preset duration, it means that the user needs to quickly solve the train operation optimization model to quickly obtain the train operation optimization strategy. In the embodiment of the invention, the train operation optimization strategy can be obtained rapidly by solving the train operation optimization model based on the particle swarm algorithm and the reinforcement learning algorithm because the particle swarm algorithm and the reinforcement learning algorithm have high searching speed, high efficiency and simple algorithm.
Optionally, after the train operation optimization model is solved based on the particle swarm algorithm and the reinforcement learning algorithm, a first optimal solution and a second optimal solution of the train operation optimization model can be obtained, and then the first optimal solution and the second optimal solution can be substituted into the objective function respectively to obtain a first value and a second value of the objective function, a target value which is closer to 0 in the first value and the second value is further determined, and when the target value is determined to be the first value, the operation curve of the train is optimized based on the first optimal solution; if the target value is determined to be the second value, the train operation curve is optimized based on the second optimal solution.
It can be understood that the closer the value of the objective function is to 0, the better the optimizing effect of the train operation curve representing the minimum energy consumption and noise in the whole train operation process is, therefore, in the embodiment of the invention, the better solution in the first optimal solution and the second optimal solution is selected to optimize the train operation curve so as to obtain the train operation optimizing strategy.
According to the train operation optimization method provided by the invention, the train operation optimization model is respectively and rapidly solved based on the particle swarm algorithm and the reinforcement learning algorithm to obtain the first optimal solution and the second optimal solution of the train operation optimization model, and then the better solution in the first optimal solution and the second optimal solution is selected to optimize the train operation curve, so that the train operation optimization strategy can be rapidly obtained, and the optimized train operation curve can be ensured to be optimal.
Optionally, the method further comprises:
under the condition that the expected time length is greater than or equal to the preset time length, solving the train operation optimization model based on a dynamic programming algorithm and the running process of the train in each subinterval to obtain a third optimal solution of the train operation optimization model;
And optimizing the running curve of the train based on the third optimal solution to obtain a running optimization strategy of the train.
Specifically, in the embodiment of the invention, under the condition that the expected time length of the user is greater than or equal to the preset time length, the train operation optimization model can be solved based on a dynamic programming algorithm and the operation process of the train in each subinterval to obtain a third optimal solution of the train operation optimization model, and then the operation curve of the train is optimized based on the third optimal solution to obtain the operation optimization strategy of the train.
It can be appreciated that when the desired time period of the user is greater than or equal to the preset time period, it means that the user does not need to quickly solve the train operation optimization model. Compared with a particle swarm algorithm and a reinforcement learning algorithm, the dynamic programming algorithm has higher calculation complexity and consumes more computer memory, so that the calculation efficiency is lower than that of the particle swarm algorithm and the reinforcement learning algorithm, but the dynamic programming algorithm has better effect of solving the multi-stage decision problem and can obtain a global optimal solution.
According to the train operation optimization method provided by the invention, the train operation optimization model is solved based on the dynamic programming algorithm, so that the optimal solution of the train operation optimization model can be obtained, and the train operation optimization curve obtained based on the optimal solution can be ensured to be optimal.
Fig. 3 is a second flow chart of the train operation optimizing method provided by the invention, as shown in fig. 3, the method includes: firstly, a train operation optimization model is pre-constructed, wherein the model comprises an objective function combined by train energy consumption and noise weighting and constraint conditions, and the constraint conditions can comprise constraint conditions such as operation time division constraint, start end speed and position constraint, train dynamics constraint, safety speed limit constraint and the like; judging whether a train operation optimization model needs to be quickly solved, if so, respectively solving by using a particle swarm algorithm and a reinforcement learning algorithm, and if not, solving by using a dynamic programming algorithm; when a particle swarm algorithm and a reinforcement learning algorithm are selected for solving, finally selecting an optimal solution obtained in the two algorithms for outputting; when the dynamic programming algorithm is selected for solving, the optimal solution obtained based on the algorithm is output.
It can be understood that the train operation optimization method provided by the embodiment of the invention constructs the optimization objective function of the train energy consumption and noise, and constraint conditions such as constraint during operation, start end terminal speed and position constraint, train dynamics constraint and safety speed limit, and the like, so as to solve the problem by using a particle swarm algorithm, a reinforcement learning algorithm or a dynamic programming algorithm, finally obtain the optimal operation strategy of the train, and control the train operation based on the optimal operation strategy, thereby being beneficial to reducing the noise in the train, improving the train environment and improving the riding comfort of passengers.
According to the train operation optimization method provided by the invention, the whole interval operation line of the train is divided into a plurality of subintervals, so that the train operation optimization model is solved based on the operation process of the train in each subinterval, and the operation curve of the train is optimized based on the solving result, so that the train operation optimization strategy is obtained, wherein the strategy comprises the operation speed, the acceleration and the like of the train in each subinterval.
The train operation optimizing device provided by the invention is described below, and the train operation optimizing device described below and the train operation optimizing method described above can be referred to correspondingly.
Fig. 4 is a schematic structural diagram of a train operation optimizing device provided by the present invention, as shown in fig. 4, the device includes: a partitioning module 410 and a solving module 420; wherein:
the dividing module 410 is configured to divide the entire section running line of the train into a plurality of subsections;
the solving module 420 is configured to solve a train operation optimization model based on the operation process of the train in each subinterval, and optimize an operation curve of the train based on a solution result, so as to obtain an operation optimization strategy of the train;
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
According to the train operation optimizing device provided by the invention, the whole interval operation line of the train is divided into the plurality of subintervals, so that the train operation optimizing model is solved based on the operation process of the train in each subinterval, and the operation curve of the train is optimized based on the solving result, so that the train operation optimizing strategy is obtained, wherein the strategy comprises the operation speed, the acceleration and the like of the train in each subinterval.
It should be noted that, the train operation optimizing device provided by the embodiment of the present invention can implement all the method steps implemented by the embodiment of the train operation optimizing method, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those of the embodiment of the method in the embodiment are omitted.
Fig. 5 is a schematic physical structure of an electronic device according to the present invention, as shown in fig. 5, the electronic device may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform the train operation optimization method provided by the methods described above, the method comprising:
dividing the whole section operation line of the train into a plurality of subintervals;
solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solving result to obtain an operation optimization strategy of the train;
The train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform 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, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides 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 method of optimizing train operation provided by the methods described above, the method comprising:
dividing the whole section operation line of the train into a plurality of subintervals;
solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solving result to obtain an operation optimization strategy of the train;
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor is implemented to perform the above provided train operation optimization methods, the method comprising:
Dividing the whole section operation line of the train into a plurality of subintervals;
solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solving result to obtain an operation optimization strategy of the train;
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (13)
1. A train operation optimization method, comprising:
dividing the whole section operation line of the train into a plurality of subintervals;
solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solving result to obtain an operation optimization strategy of the train;
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
2. The train operation optimization method according to claim 1, wherein the construction process of the objective function includes:
determining the whole-course running energy consumption of the train based on the traction force output by the train in each subinterval and the running distance of the train in each subinterval, and determining the whole-course running noise of the train based on the sound pressure level noise output by the train in each subinterval;
And constructing the objective function based on the whole-course operation energy consumption of the train, the whole-course operation noise of the train and the weighting factor.
3. The train operation optimization method according to claim 2, wherein the expression of the objective function is:
wherein p represents a weighting factor, N represents the total number of the subintervals, i represents the index of the subintervals, F i Representing the traction force of the train output in the ith subinterval S i Indicating the cumulative travel distance of the train at the time of entering the ith subinterval, (L) P ) i And represents sound pressure level noise of the train output in the ith subinterval.
4. The train operation optimization method according to claim 1, wherein the expression of the train operation time division constraint is:
wherein N represents the total number of the subintervals, i represents the index of the subintervals, T i Representing the actual operating time of the train in the ith subinterval, T target Representing the target operating time division of the train, and delta represents the train operating time division threshold.
5. The train operation optimization method according to claim 1, wherein the train operation start end constraint is:
the running speed of the train at the start point between stations of the whole interval running line is 0, and the running distance of the train at the start point between stations is 0; the running speed of the train at the terminal point between stations of the whole interval running line is 0, and the running distance at the terminal point between stations is the running target distance of the train.
6. The train operation optimization method according to claim 1, wherein the expression of the train dynamics constraint is:
wherein i represents the index of the subinterval, F i Representing the traction force of the train output in the ith subinterval, F max Representing the maximum traction force of the train output, B i Represents the braking force received by the train in the ith subinterval, B max Representing the maximum braking force of the train output, a i Representing the acceleration of the train in the ith subinterval, V i+1 Representing the speed of the train in the (i+1) th subinterval, V i Represents the speed of the train in the ith subinterval, deltaS i Representing the distance travelled by the train in the ith subinterval S i Represents the accumulated running distance of the train when entering the ith subinterval, S i+1 Indicating the accumulated running distance T of the train when entering the (i+1) th subinterval i Representing the actual operating time of the train in the ith subinterval, T i+1 Indicating the actual operating time of the train in the (i+1) th subinterval, w i And G represents the mass of the train.
7. The train operation optimization method according to claim 1, wherein the train speed limit constraint is: the running speed of the train in each subinterval is smaller than the target limiting speed.
8. The train operation optimization method according to claim 1, wherein the steps of solving a train operation optimization model based on the operation process of the train in each subinterval, and optimizing the train operation curve based on the solution result, and obtaining the train operation optimization strategy include:
determining an expected duration for obtaining an operation optimization strategy of the train;
under the condition that the expected duration is less than the preset duration, solving the train operation optimization model based on a particle swarm algorithm and the operation process of the train in each subinterval to obtain a first optimal solution of the train operation optimization model, and solving the train operation optimization model based on a reinforcement learning algorithm and the operation process of the train in each subinterval to obtain a second optimal solution of the train operation optimization model;
determining a first value of the objective function based on the first optimal solution and a second value of the objective function based on the second optimal solution;
determining a target value of the first value and the second value that is closer to 0;
under the condition that the target value is determined to be the first value, optimizing the running curve of the train based on the first optimal solution to obtain a running optimization strategy of the train;
And under the condition that the target value is determined to be the second value, optimizing the running curve of the train based on the second optimal solution to obtain a running optimization strategy of the train.
9. The train operation optimization method according to claim 8, characterized in that the method further comprises:
under the condition that the expected time length is greater than or equal to the preset time length, solving the train operation optimization model based on a dynamic programming algorithm and the running process of the train in each subinterval to obtain a third optimal solution of the train operation optimization model;
and optimizing the running curve of the train based on the third optimal solution to obtain a running optimization strategy of the train.
10. A train operation optimizing apparatus, comprising:
the dividing module is used for dividing the whole interval running line of the train into a plurality of subintervals;
the solving module is used for solving the train operation optimization model based on the operation process of the train in each subinterval, optimizing the train operation curve based on the solving result and obtaining the train operation optimization strategy;
the train operation optimization model is prestored and comprises an objective function and constraint conditions, wherein the objective function is constructed by taking the minimum weighted sum of the whole-course operation energy consumption and the whole-course operation noise of the train as the objective, and the constraint conditions comprise train operation time division constraint, train operation starting end constraint, train dynamics constraint and train speed limit constraint.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the train operation optimization method of any one of claims 1 to 9 when the program is executed by the processor.
12. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the train operation optimization method according to any one of claims 1 to 9.
13. A computer program product comprising a computer program which, when executed by a processor, implements the train operation optimization method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211699939.2A CN116011326A (en) | 2022-12-28 | 2022-12-28 | Train operation optimization method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211699939.2A CN116011326A (en) | 2022-12-28 | 2022-12-28 | Train operation optimization method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116011326A true CN116011326A (en) | 2023-04-25 |
Family
ID=86024410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211699939.2A Pending CN116011326A (en) | 2022-12-28 | 2022-12-28 | Train operation optimization method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116011326A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117034459A (en) * | 2023-08-18 | 2023-11-10 | 华东交通大学 | Magnetic suspension train operation optimization method and system based on improved dung beetle optimization algorithm |
-
2022
- 2022-12-28 CN CN202211699939.2A patent/CN116011326A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117034459A (en) * | 2023-08-18 | 2023-11-10 | 华东交通大学 | Magnetic suspension train operation optimization method and system based on improved dung beetle optimization algorithm |
| CN117034459B (en) * | 2023-08-18 | 2024-05-31 | 华东交通大学 | Magnetic suspension train operation optimization method and system based on improved dung beetle optimization algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110239600B (en) | Train operation control method and system for regenerative braking energy utilization | |
| US11708098B2 (en) | Method and device for optimizing target operation speed curve in ATO of train | |
| CN108583576B (en) | Economic vehicle speed forward-looking optimization method | |
| Bertoni et al. | An adaptive cruise control for connected energy-saving electric vehicles | |
| CN109062273B (en) | Train speed curve tracking control method and system based on event-triggered PID control | |
| CN107368920B (en) | Energy-saving optimization method for multi-train operation in off-peak hours | |
| CN112633598A (en) | Comprehensive energy-saving optimization method for speed curve and timetable of urban rail transit train | |
| CN105118329A (en) | Method of resolving traffic conflicts of two vehicles at no-signal intersection | |
| CN116011326A (en) | Train operation optimization method and device, electronic equipment and storage medium | |
| US8838304B2 (en) | Method for determining run-curves for vehicles based on travel time | |
| Li et al. | Dynamic trajectory optimization design for railway driver advisory system | |
| CN110188401B (en) | Tramcar operation energy consumption optimization method based on improved PSO | |
| CN106777717A (en) | A kind of ATO speed command energy conservation optimizing methods for considering handling capacity of passengers change | |
| CN112078631B (en) | Train speed control method and system | |
| CN114880770B (en) | Train cooperative operation control method based on reference deep reinforcement learning | |
| CN111680413B (en) | Tramcar timing energy-saving operation optimization method and system based on double-layer algorithm | |
| CN115520188A (en) | Energy-saving vehicle speed planning method, system, electronic device and storage medium | |
| Ding et al. | Simulation algorithm for energy-efficient train control under moving block system | |
| Pu et al. | Multiobjective optimization on the operation speed profile design of an urban railway train with a hybrid running strategy | |
| Wong et al. | Coast control of train movement with genetic algorithm | |
| Yildiz et al. | Traction energy optimization considering comfort parameter: A case study in Istanbul metro line | |
| CN114547774B (en) | Heavy-load train arrival curve optimization method and system | |
| CN116691779A (en) | Method, system and equipment for generating recommended driving curve of virtual marshalling train | |
| Keskin et al. | Energy efficient motion control for a light rail vehicle using the big bang big crunch algorithm | |
| CN116127839A (en) | Bus station service interruption prevention and control method based on reinforcement learning |
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 |