Urban rail train working diagram adjusting method and device based on genetic algorithm

Abstract

The invention provides an urban rail train working diagram adjusting method and device based on a genetic algorithm, and relates to the technical field of urban rail train dispatching.The urban rail train working diagram adjusting method comprises the steps that firstly, historical data including a train operation scheme, station information data, passenger flow data and train operation data are obtained; the train punctuality rate, the stopping time, the passenger flow congestion degree, the train average delay time and the passenger flow satisfaction rate are analyzed, and train operation performance indexes and passenger experience indexes are generated. Then, the two indexes are used for constructing a riding state model and training the riding state model; a historical train operation scheme is used as an initial population, fitness values of individuals in the population are calculated, genetic algorithm iterative optimization is carried out, and finally the individual with the highest fitness value is selected as the optimal operation scheme. And finally, the current train operation scheme is adjusted based on the optimal scheme, and a new train scheduling scheme is formulated to improve the operation efficiency and the passenger experience.

Description

Technical Field

[0001] The present invention relates to the technical field of urban rail train dispatching, and in particular to an urban rail train operation diagram adjustment method and device based on a genetic algorithm. Background Art

[0002] With the acceleration of urbanization, urban rail transit has become an important means to solve urban traffic congestion and improve transportation efficiency. However, the matching problem between the operation and scheduling of urban rail trains and passenger demand has become increasingly prominent, resulting in a series of problems such as low train punctuality, long average passenger waiting time, and passenger congestion. These problems not only affect the travel experience of passengers, but also reduce the overall operation efficiency and service level of urban rail transit. Therefore, how to effectively adjust the operation diagram of urban rail trains to achieve a rapid response to passenger demand has become an important technical challenge in urban rail transit management.

[0003] Among the existing scheduling optimization methods, there are empirical adjustments based on historical data and some traditional optimization algorithms, but it is often difficult to comprehensively consider multiple factors. As an adaptive optimization method, genetic algorithm has a strong global search capability and can find the optimal solution in complex multi-objective optimization problems. Therefore, the urban rail train operation diagram adjustment method based on genetic algorithm can more flexibly respond to dynamically changing passenger flow conditions and achieve a more reasonable train scheduling plan.

[0004] In the prior art, publication number CN113128774B discloses a train operation adjustment optimization method under a fixed train line sequence, which configures an initial train operation plan, basic train operation data and fixed train line data; according to the railway line topology structure, the initial train operation plan, the basic train operation data and the fixed train line data, a train operation adjustment optimization model under a fixed train line sequence is established based on a space-time network; an integer programming algorithm is used to solve the train operation adjustment optimization model under a fixed train line sequence to obtain a train operation adjustment plan with a fixed train line sequence.

[0005] The main problems with the above methods are: insufficient flexibility. When the actual passenger flow or operating status changes, the plan cannot adapt quickly, resulting in the train operation plan not matching the actual demand; and the integer programming algorithm may fall into a local optimal solution when solving the optimization model, affecting the optimization results; when faced with new lines or new operating plans, the model needs to be re-established and complex adjustments need to be made, and the adaptability is relatively weak.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The object of the present invention is to provide a method and device for adjusting an urban rail train operation diagram based on a genetic algorithm to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for adjusting an urban rail train operation diagram based on a genetic algorithm, the specific steps comprising:

[0010] Step 1: Acquire historical data, which includes train operation plans and corresponding status parameters acquired daily, wherein the train operation plans include train stop sequences, driving time sequences and arrival time sequences, and the status parameters include station information data, passenger flow data and train operation data;

[0011] Step 2: Generate train punctuality, train stop time, passenger congestion, average train delay time and passenger satisfaction rate based on the state parameters; generate train operation performance indicators based on train punctuality and average train delay time; generate passenger experience indicators based on average train stop time, passenger congestion and passenger satisfaction rate;

[0012] Step 3: Build a riding status model, using the train operation plan in the historical data as input, and the corresponding train operation performance indicators and passenger experience indicators as labels to train the riding status model;

[0013] Step 4: The train operation scheme in the historical data is used as an individual of the initial population, and the fitness value of the individual is calculated based on the train operation performance index and the passenger experience index. The fitness value maximization is taken as the optimization goal, and the individuals are iteratively optimized based on the genetic algorithm and the passenger status model until the predetermined number of iterations is reached, and the individual with the highest fitness value is selected as the optimal train operation scheme;

[0014] Step 5: Obtain the current train operation plan, and based on the optimal train operation plan, determine a train scheduling plan for adjusting the current train operation plan so that the current train operation plan is close to the optimal train operation plan.

[0015] Furthermore, the station information data includes the maximum allowed passenger flow at each station; the passenger flow data includes the passenger flow at each station and the number of passengers on different trains at the station; the train operation data includes the total number of trains, the number of trains arriving on time, the actual stop time of the train at each station, the remaining passenger capacity and the train delay time.

[0016] Furthermore, the principle for generating the train operation performance index is:

[0017] The formula for generating train punctuality is:

[0018]

[0019] Among them, R represents the train punctuality rate, M time represents the number of trains that arrive on time, and M represents the total number of trains;

[0020] The formula used to generate the average train delay time is:

[0021]

[0022] Where Y represents the average delay time of the train, i represents the index of the train, and i∈[1,M], j represents the index of the station, J represents the total number of stations, and D i,j represents the train delay time of the i-th train arriving at the j-th station;

[0023] The formula for generating train performance indicators is:

[0024]

[0025] Among them, A represents the train operation performance index, α1 and α2 represent the weight coefficients of the train punctuality rate and the average train delay time respectively, and α1+α2=1.

[0026] Furthermore, the principles for generating the passenger experience index are as follows:

[0027] The formula used to generate the average train stop time is:

[0028]

[0029] Where W represents the average stop time of the train, j represents the index of the station, J represents the total number of stations, and W i,j represents the actual stop time of the i-th train at the j-th station;

[0030] The formula for generating passenger flow congestion is:

[0031]

[0032] Among them, C represents the passenger flow congestion, C j,cur represents the passenger flow of the jth station, C j,max represents the maximum allowed passenger flow of the jth station;

[0033] The formula for generating the passenger flow satisfaction rate is:

[0034]

[0035] Among them, Z represents the passenger flow satisfaction rate, E i,jrepresents the remaining passenger capacity of the i-th train at the j-th station, U i,j represents the number of passengers taking the i-th train at the j-th station;

[0036] The principles underlying the generation of passenger experience indicators are:

[0037] B=β1·(1-W)+β2·(1-C)+β3·Z

[0038] Among them, B represents the passenger experience index, β1, β2, and β3 represent the weight coefficients of the average passenger waiting time, passenger congestion, and passenger satisfaction rate, respectively, β1+β2+β3=1, and β2>β3>β1.

[0039] Furthermore, the principle for generating individuals of the initial population is:

[0040] The data elements for each individual in the population are:

[0041] Train stop sequence, S i =[s i,1 ,s i,2 ,…,s i,j ,…,s i,J ];

[0042] Among them, S i represents the stop sequence of the i-th train, i represents the index of the train, j represents the index of the station, and j = 1, 2, ... J, J represents the total number of stations, s i,j represents the jth stop of the i-th train;

[0043] Driving time series, T i =[t i,2 ,t i,3 ,…,t i,j ,…,t i,J ];

[0044] Among them, T i represents the driving time series of the i-th train, t i,j represents the travel time of the i-th train from the j-th station to the j-1-th station;

[0045] Arrival time series, H i =[h i,1 ,h i,2 ,…h i,j …,h i,J ];

[0046] Among them, H i represents the arrival time sequence of the i-th train, h i,jrepresents the arrival time of the i-th train at the j-th station; for each train, the individuals formed are:

[0047] I i =[S i ,T i ,H i ]

[0048] Among them, I i Represents the individual corresponding to the i-th train in the population.

[0049] Furthermore, the formula for generating the fitness value is:

[0050] F=w1·e A +w2·e B

[0051] Among them, F represents the fitness value, A and B represent the train operation performance index and the passenger experience index respectively, w1 and w2 represent the weight coefficients of the train operation performance index and the passenger experience index respectively, w1>w2, and w1+w2=1.

[0052] Furthermore, the principle of iterative optimization of individuals based on genetic algorithms is:

[0053] Based on the tournament selection method, two individuals are randomly selected from the initial population, the fitness values ​​of the selected individuals are compared, and the individual with higher fitness between the two is selected as the parent. The process is repeated until the required number of parent individuals are selected, which is regarded as completing one round of selection. Crossover and mutation are randomly performed among the selected parent individuals to generate new offspring, and the offspring and the parent are combined to form a new population. The individuals in the new population are input into the riding state model, and the train operation performance index and passenger experience index of each individual are calculated. The fitness value of the individual is calculated based on the train operation performance index and the passenger experience index, and the individual with the highest fitness value is recorded as the current optimal solution. The above operation is regarded as one iteration, and the maximum number of iterations is set to 100. When the number of iterations reaches 100, or the improvement of the optimal fitness is less than 5% in 10 consecutive iterations, the iteration is terminated, and the individual with the current optimal solution is selected as the optimal train operation plan.

[0054] The present invention also provides a device for adjusting an urban rail train operation diagram based on a genetic algorithm, and the device is used to implement the above-mentioned method for adjusting an urban rail train operation diagram based on a genetic algorithm, specifically comprising:

[0055] A data acquisition module is used to obtain historical data, the historical data includes the train operation plan and corresponding state parameters obtained daily, the train operation plan includes the train stop sequence, the driving time sequence and the arrival time sequence, and the state parameters include station information data, passenger flow data and train operation data;

[0056] An index generation module is used to generate train punctuality, train stop time, passenger flow congestion, average train delay time and passenger flow satisfaction rate based on state parameters, generate train operation performance indicators based on train punctuality and average train delay time, and generate passenger experience indicators based on average train stop time, passenger flow congestion and passenger flow satisfaction rate;

[0057] The model training module is used to build a passenger status model. It uses the train operation plan in the historical data as input and the corresponding train operation performance indicators and passenger experience indicators as labels to train the passenger status model.

[0058] A scheme optimization module is used to use the train operation scheme in the historical data as individuals of the initial population, calculate the fitness value of the individual based on the train operation performance index and the passenger experience index, take the maximization of the fitness value as the optimization goal, iteratively optimize the individual based on the genetic algorithm and the passenger status model until a predetermined number of iterations is reached, and select the individual with the highest fitness value as the optimal train operation scheme;

[0059] The plan scheduling module is used to obtain the current train operation plan and, based on the optimal train operation plan, determine a train scheduling plan to adjust the current train operation plan so that the current train operation plan is close to the optimal train operation plan.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention uses historical train operation plans and status parameter data to comprehensively reflect all aspects of train operation. The multi-dimensional evaluation method helps to better evaluate the train's operating performance and passenger experience, thereby achieving more targeted optimization. In addition, the historical data obtained daily can timely reflect changes in passenger flow and train operating status, so that the train operation plan can be dynamically adjusted to improve operational efficiency and passenger satisfaction; and based on historical data, the passenger status model is trained to provide accurate suggestions for current decisions and improve the efficiency of train scheduling and operation decisions.

[0062] This statement also calculates the fitness value of individuals through train operation performance indicators and passenger experience indicators, and uses genetic algorithms for optimization, searching for individuals with the largest fitness values, objectively evaluating the pros and cons of each scheduling plan from multiple dimensions, and generating fitness values ​​to make the optimization process clearer and more targeted; in the face of different operating environments and passenger flow changes, genetic algorithms can provide flexible scheduling plans to help operators quickly adapt to changes and avoid falling into local optimal solutions. The results of each optimization can provide feedback for the next round of scheduling decisions, forming a closed loop of continuous improvement, enhancing the adaptability of the plan, and due to rapid iterative optimization, multiple possible operating plans can be provided in a relatively short period of time, helping decision makers quickly evaluate and select the best plan, and improving the efficiency of decision-making and scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a schematic diagram of a method flow of an embodiment of the present invention;

[0064] Figure 2 Schematic diagram of a device module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0066] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0067] Example:

[0068] See also Figure 1 , the present invention provides a technical solution:

[0069] A method for adjusting an urban rail train operation diagram based on a genetic algorithm, the specific steps comprising:

[0070] Step 1: Acquire historical data, which includes train operation plans and corresponding status parameters acquired daily, wherein the train operation plans include train stop sequences, driving time sequences and arrival time sequences, and the status parameters include station information data, passenger flow data and train operation data;

[0071] In this embodiment, the station information data includes the maximum allowed passenger flow at each station; the passenger flow data includes the passenger flow at each station and the number of passengers on different trains at the station; the train operation data includes the total number of trains, the number of trains arriving on time, the actual stop time of the train at each station, the remaining passenger capacity and the train delay time.

[0072] Step 2: Generate train punctuality, train stop time, passenger congestion, average train delay time and passenger satisfaction rate based on the state parameters; generate train operation performance indicators based on train punctuality and average train delay time; generate passenger experience indicators based on average train stop time, passenger congestion and passenger satisfaction rate;

[0073] In this embodiment, the principle for generating the train operation performance index is as follows:

[0074] The formula for generating train punctuality is:

[0075]

[0076] Among them, R represents the train punctuality rate, m time represents the number of trains that arrive on time, and m represents the total number of trains;

[0077] The train punctuality rate directly reflects the train's operating efficiency. The train's stop situation at the station, the train's travel time between stations and the train's actual arrival time at the station will all affect the train punctuality rate. The train punctuality rate is proportional to the number of trains that arrive on time.

[0078] The formula used to generate the average train delay time is:

[0079]

[0080] Where Y represents the average delay time of the train, i represents the index of the train, and i∈[1,M], j represents the index of the station, J represents the total number of stations, and D i,j represents the train delay time of the i-th train arriving at the j-th station;

[0081] The average delay time of a train reflects the average of the total delay time of all trains at all stations. The longer the average delay time, the more congested the overall train operation is.

[0082] The formula for generating train performance indicators is:

[0083]

[0084] Among them, A represents the train operation performance index, α1 and α2 represent the weight coefficients of train punctuality rate and train average delay time respectively.

[0085] The train operation performance index comprehensively considers the train's punctuality and delay, and reflects the quality of the train operation plan. The higher the train operation performance index, the better the train operation plan. The train operation performance index is proportional to the train's punctuality and inversely proportional to the train's average delay time; and α1=α2=0.5.

[0086] The principles underlying the generation of passenger experience indicators are:

[0087] The formula used to generate the average train stop time is:

[0088]

[0089] Where W represents the average stop time of the train, j represents the index of the station, J represents the total number of stations, and W i,j represents the actual stop time of the i-th train at the j-th station;

[0090] The average train stop time refers to the average stop time of all trains at all stations. The shorter the average stop time, the smoother the train operation and the more convenient it is for passengers to get on and off the train; the longer the average stop time, the more congested the train operation.

[0091] The formula for generating passenger flow congestion is:

[0092]

[0093] Among them, C represents the passenger flow congestion, C j,cur represents the passenger flow of the jth station, C j,max represents the maximum allowed passenger flow of the jth station;

[0094] Passenger flow congestion reflects the relationship between the actual passenger flow of a station and its maximum capacity. The higher the actual passenger flow, the higher the passenger flow congestion and the lower the passenger experience.

[0095] The formula for generating the passenger flow satisfaction rate is:

[0096]

[0097] Among them, Z represents the passenger flow satisfaction rate, E i,j represents the remaining passenger capacity of the i-th train at the j-th station, U i,jrepresents the number of passengers taking the i-th train at the j-th station;

[0098] The passenger flow satisfaction rate indicates whether the remaining passenger capacity of the train can meet the needs of passengers at the next stop. A high passenger flow satisfaction rate indicates that the remaining passenger capacity of the train is high, and it is easier to meet the needs of passengers at the next stop.

[0099] The principles underlying the generation of passenger experience indicators are:

[0100] B=β1·(1-W)+β2·(1-C)+β3·Z

[0101] Among them, B represents the passenger experience index, β1, β2, and β3 represent the weight coefficients of the average train stop time, passenger congestion, and passenger satisfaction rate, respectively, β1+β2+β3=1, and β2>β3>β1.

[0102] The passenger experience index comprehensively considers the passengers' boarding and alighting time, station congestion and the train's passenger carrying capacity, and reflects the passengers' riding experience. The higher the passenger experience index, the better the passenger experience and the better the train operation plan. The passenger experience index is inversely proportional to the average train stop time and passenger congestion, and directly proportional to the passenger satisfaction rate, and β1=0.2, β2=0.5, and β3=0.3.

[0103] Step 3: Build a riding status model, using the train operation plan in the historical data as input, and the corresponding train operation performance indicators and passenger experience indicators as labels to train the riding status model.

[0104] In this embodiment, the passenger status model is trained based on a deep learning network, with historical train operation plans as input. The structure of the deep learning network is:

[0105] Input layer: 3 neurons, used to input the train stop sequence, driving time sequence and arrival time sequence in the train operation plan;

[0106] The first fully connected layer has 128 neurons and uses the ReLU activation function.

[0107] The second fully connected layer has 64 neurons and uses the ReLU activation function.

[0108] The third fully connected layer: 32 neurons, using the ReLU activation function;

[0109] Output layer: 2 neurons, outputting train operation performance indicators and passenger experience indicators.

[0110] Step 4: The train operation scheme in the historical data is used as an individual of the initial population, and the fitness value of the individual is calculated based on the train operation performance index and the passenger experience index. The fitness value maximization is taken as the optimization goal, and the individuals are iteratively optimized based on the genetic algorithm and the passenger status model until the predetermined number of iterations is reached, and the individual with the highest fitness value is selected as the optimal train operation scheme;

[0111] In this embodiment, the principle for generating individuals of the initial population is:

[0112] The data elements for each individual in the population are:

[0113] Train stop sequence, S i =[s i,1 ,s i,2 ,…,s i,j ,…,s i,J ];

[0114] Among them, S i represents the stop sequence of the i-th train, i represents the index of the train, j represents the index of the station, and j = 1, 2, ... J, J represents the total number of stations, s i,j represents the jth stop of the i-th train;

[0115] The train stop sequence reflects the running path of the train and is the most basic component of scheduling. According to the changes in passenger flow and demand, the train stops are adjusted to ensure that the train passes through the main stations during peak hours;

[0116] Driving time series, T i =[t i,2 ,t i,3 ,…,t i,j ,…,t i,J ];

[0117] Among them, T i represents the driving time series of the i-th train, t i,j represents the travel time of the i-th train from the j-th station to the j-1-th station;

[0118] The travel time series reflects the travel time of trains between stations and is used to determine whether congestion occurs;

[0119] Arrival time series, H i =[h i,1 ,h i,2 ,…h i,j …,h i,J ];

[0120] Among them, H i represents the arrival time sequence of the i-th train, h i,jrepresents the arrival time of the i-th train at the j-th station;

[0121] The arrival time series reflects the actual time when the train arrives at the station, which is used to determine whether the train is delayed or early and thus determine the congestion situation.

[0122] For each train, the individuals formed are:

[0123] I i =[S i ,T i ,H i ]

[0124] Among them, I i represents the individual corresponding to the i-th train in the population;

[0125] The formula for calculating the fitness value of an individual based on train operation performance indicators and passenger experience indicators is:

[0126] F=w1·e A +w2·e B

[0127] Among them, F represents the fitness value, A and B represent the train operation performance index and the passenger experience index respectively, w1 and w2 represent the weight coefficients of the train operation performance index and the passenger experience index respectively, w1>w2, and w1+w2=1.

[0128] The fitness value comprehensively considers the operation of the train and the passengers' riding and waiting experience. The higher the fitness value, the smoother the train operation, the better the passenger riding experience, and the better the corresponding train operation plan. The fitness value is proportional to the train operation performance index and the passenger experience index. In actual scheduling, the operation quality of the train line is given priority. Therefore, the weight coefficient of the train operation performance index is relatively large, w1=0.7, w2=0.3.

[0129] Based on the tournament selection method, two individuals are randomly selected from the initial population, the fitness values ​​of the selected individuals are compared, and the individual with higher fitness between the two is selected as the parent. The process is repeated until the required number of parent individuals are selected, which is regarded as completing one round of selection. Crossover and mutation are randomly performed among the selected parent individuals to generate new offspring, and the offspring and the parent are combined to form a new population. The individuals in the new population are input into the riding state model, and the train operation performance index and passenger experience index of each individual are calculated. The fitness value of the individual is calculated based on the train operation performance index and the passenger experience index, and the individual with the highest fitness value is recorded as the current optimal solution. The above operation is regarded as one iteration, and the maximum number of iterations is set to 100. When the number of iterations reaches 100, or the improvement of the optimal fitness is less than 5% in 10 consecutive iterations, the iteration is terminated, and the individual with the current optimal solution is selected as the optimal train operation plan.

[0130] Step 5: Obtain the current train operation plan, and based on the optimal train operation plan, determine a train dispatching plan for adjusting the current train operation plan.

[0131] In this embodiment, the scheduling strategy includes:

[0132] Train rush: adjust train travel time and stop time to shorten overall delays;

[0133] Train skipping: some trains are allowed to run past stations with less passenger flow;

[0134] Additional trains: additional trains on key routes based on passenger flow forecast data;

[0135] Empty trains; reduce train running frequency on some lines based on passenger flow forecast data.

[0136] See also Figure 2 The present invention also provides a device for adjusting the urban rail train operation diagram based on a genetic algorithm, and the device is used to implement the above-mentioned method for adjusting the urban rail train operation diagram based on a genetic algorithm, which specifically includes:

[0137] A data acquisition module is used to obtain historical data, the historical data includes the train operation plan and corresponding state parameters obtained daily, the train operation plan includes the train stop sequence, the driving time sequence and the arrival time sequence, and the state parameters include station information data, passenger flow data and train operation data;

[0138] An index generation module is used to generate train punctuality, train stop time, passenger flow congestion, average train delay time and passenger flow satisfaction rate based on state parameters, generate train operation performance indicators based on train punctuality and average train delay time, and generate passenger experience indicators based on average train stop time, passenger flow congestion and passenger flow satisfaction rate;

[0139] The model training module is used to build a passenger status model. It uses the train operation plan in the historical data as input and the corresponding train operation performance indicators and passenger experience indicators as labels to train the passenger status model.

[0140] A scheme optimization module is used to use the train operation scheme in the historical data as individuals of the initial population, calculate the fitness value of the individual based on the train operation performance index and the passenger experience index, take the maximization of the fitness value as the optimization goal, iteratively optimize the individual based on the genetic algorithm and the passenger status model until a predetermined number of iterations is reached, and select the individual with the highest fitness value as the optimal train operation scheme;

[0141] The plan scheduling module is used to obtain the current train operation plan and, based on the optimal train operation plan, determine a train scheduling plan to adjust the current train operation plan so that the current train operation plan is close to the optimal train operation plan.

[0142] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0143] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0144] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for adjusting the urban rail train operation diagram based on genetic algorithm, characterized in that: The specific steps include: Step 1: Acquire historical data, which includes train operation plans and corresponding status parameters acquired daily, wherein the train operation plans include train stop sequences, driving time sequences and arrival time sequences, and the status parameters include station information data, passenger flow data and train operation data; Step 2: Generate train punctuality, train stop time, passenger congestion, average train delay time and passenger satisfaction rate based on the state parameters; generate train operation performance indicators based on train punctuality and average train delay time; generate passenger experience indicators based on average train stop time, passenger congestion and passenger satisfaction rate; Step 3: Build a riding status model, using the train operation plan in the historical data as input, and the corresponding train operation performance indicators and passenger experience indicators as labels to train the riding status model; Step 4: The train operation scheme in the historical data is used as an individual of the initial population, and the fitness value of the individual is calculated based on the train operation performance index and the passenger experience index. The fitness value maximization is taken as the optimization goal, and the individuals are iteratively optimized based on the genetic algorithm and the passenger status model until the predetermined number of iterations is reached, and the individual with the highest fitness value is selected as the optimal train operation scheme; Step 5: Obtain the current train operation plan, and based on the optimal train operation plan, determine a train scheduling plan for adjusting the current train operation plan so that the current train operation plan is close to the optimal train operation plan.

2. The method for adjusting the urban rail train operation diagram based on genetic algorithm according to claim 1, characterized in that: The station information data in step 1 includes the maximum allowed passenger flow of each station; the passenger flow data includes the passenger flow of each station and the number of passengers boarding different trains at the station; The train operation data includes the total number of trains, the number of trains arriving on time, the actual stop time of trains arriving at each station, the remaining passenger capacity and the train delay time.

3. The method for adjusting the urban rail train operation diagram based on genetic algorithm according to claim 1, characterized in that: The principle for generating the train operation performance index in step 2 is: The formula for generating train punctuality is: Among them, R represents the train punctuality rate, M time represents the number of trains that arrive on time, and M represents the total number of trains; The formula used to generate the average train delay time is: Where Y represents the average delay time of the train, i represents the index of the train, and i∈[1,M], j represents the index of the station, J represents the total number of stations, and D i,j represents the train delay time of the i-th train arriving at the j-th station; The formula for generating train performance indicators is: Among them, A represents the train operation performance index, α1 and α2 represent the weight coefficients of the train punctuality rate and the average train delay time respectively, and α1+α2=1.

4. The method for adjusting the urban rail train operation diagram based on genetic algorithm according to claim 1, characterized in that: The principle for generating the passenger experience index in step 2 is: The formula used to generate the average train stop time is: Where W represents the average stop time of the train, j represents the index of the station, J represents the total number of stations, and W i,j represents the actual stop time of the i-th train at the j-th station; The formula for generating passenger flow congestion is: Among them, C represents the passenger flow congestion, C j,cur represents the passenger flow of the jth station, C j,max represents the maximum allowed passenger flow of the jth station; The formula for generating the passenger flow satisfaction rate is: Among them, Z represents the passenger flow satisfaction rate, E i,j represents the remaining passenger capacity of the i-th train at the j-th station, U i,j represents the number of passengers taking the i-th train at the j-th station; The principles underlying the generation of passenger experience indicators are: B=β1·(1-W)+β2·(1-C)+β3·Z Among them, B represents the passenger experience index, β1, β2, and β3 represent the weight coefficients of the average passenger waiting time, passenger congestion, and passenger satisfaction rate, respectively, β1+β2+β3=1, and β2>β3>β1.

5. The method for adjusting the urban rail train operation diagram based on genetic algorithm according to claim 1, characterized in that: The principle for generating individuals of the initial population in step 4 is: The data elements for each individual in the population are: Train stop sequence, S i =[s i,1 ,s i,2 ,…,s i,j ,…,s i,J ]; Among them, S i represents the stop sequence of the i-th train, i represents the index of the train, j represents the index of the station, and j = 1, 2, ... J, J represents the total number of stations, s i,j represents the jth stop of the i-th train; Driving time series, T i =[t i,2 ,t i,3 ,…,t i,j ,…,t i,J ]; Among them, T i represents the driving time series of the i-th train, t i,j represents the travel time of the i-th train from the j-th station to the j-1-th station; Arrival time series, H i =[h i,1 ,h i,2 ,…h i,j …,h i,J ]; Among them, H i represents the arrival time sequence of the i-th train, h i,j represents the arrival time of the i-th train at the j-th station; For each train, the individuals formed are: I i =[S i ,T i ,H i ] Among them, I i Represents the individual corresponding to the i-th train in the population.

6. The method for adjusting the urban rail train operation diagram based on genetic algorithm according to claim 1, characterized in that: The formula for generating the fitness value in step 4 is: F=w1·e A +w2·and B Among them, F represents the fitness value, A and B represent the train operation performance index and the passenger experience index respectively, w1 and w2 represent the weight coefficients of the train operation performance index and the passenger experience index respectively, w1>w2, and w1+w2=1.

7. The method for adjusting the urban rail train operation diagram based on genetic algorithm according to claim 1, characterized in that: The principle for iterative optimization of individuals based on genetic algorithm in step 4 is: Based on the tournament selection method, two individuals are randomly selected from the initial population, the fitness values ​​of the selected individuals are compared, and the individual with higher fitness between the two is selected as the parent. The process is repeated until the required number of parent individuals are selected, which is regarded as completing one round of selection. Crossover and mutation are randomly performed among the selected parent individuals to generate new offspring, and the offspring and the parent are combined to form a new population. The individuals in the new population are input into the riding state model, and the train operation performance index and passenger experience index of each individual are calculated. The fitness value of the individual is calculated based on the train operation performance index and the passenger experience index, and the individual with the highest fitness value is recorded as the current optimal solution. The above operation is regarded as one iteration, and the maximum number of iterations is set to 100. When the number of iterations reaches 100, or the improvement of the optimal fitness is less than 5% in 10 consecutive iterations, the iteration is terminated, and the individual with the current optimal solution is selected as the optimal train operation plan.

8. A device for adjusting the operation diagram of urban rail trains based on genetic algorithm, characterized in that: The device is used to implement the urban rail train operation diagram adjustment method based on genetic algorithm according to any one of claims 1 to 7, specifically comprising: A data acquisition module is used to obtain historical data, the historical data includes the train operation plan and corresponding state parameters obtained daily, the train operation plan includes the train stop sequence, the driving time sequence and the arrival time sequence, and the state parameters include station information data, passenger flow data and train operation data; An index generation module is used to generate train punctuality, train stop time, passenger flow congestion, average train delay time and passenger flow satisfaction rate based on state parameters, generate train operation performance indicators based on train punctuality and average train delay time, and generate passenger experience indicators based on average train stop time, passenger flow congestion and passenger flow satisfaction rate; The model training module is used to build a passenger status model. It uses the train operation plan in the historical data as input and the corresponding train operation performance indicators and passenger experience indicators as labels to train the passenger status model. A scheme optimization module is used to use the train operation scheme in the historical data as individuals of the initial population, calculate the fitness value of the individual based on the train operation performance index and the passenger experience index, take the maximization of the fitness value as the optimization goal, iteratively optimize the individual based on the genetic algorithm and the passenger status model until a predetermined number of iterations is reached, and select the individual with the highest fitness value as the optimal train operation scheme; The plan scheduling module is used to obtain the current train operation plan and, based on the optimal train operation plan, determine a train scheduling plan to adjust the current train operation plan so that the current train operation plan is close to the optimal train operation plan.

Images