WO2023134093A1 - Virtual subway train operation big data generation method based on interval speed limit and expert experience - Google Patents

Abstract

Disclosed in the present invention is a virtual subway train operation big data generation method based on an interval speed limit and expert experience. Limited parameters of virtual data, such as a traction interval, a speed interval, a station spacing interval and a speed change interval, are obtained by investigating actual data of subway operation and consulting related experts, such that the generated virtual data is in a small range and has high reliability. Then, a five-section operation mode of a subway train is assumed according to dynamic knowledge, so as to generate a virtual speed-distance image of the train. Afterwards, programming implementation and data visualization are performed by using Python, so as to obtain a large amount of required virtual subway train operation data. Conditional screening is performed on a large amount of generated virtual data, so as to obtain some dotted lines required by a researcher. In addition, a selected single curve is tracked in real time, so as to obtain an operation state of the subway train on the single curve every 0.1 second, such that the real-time operation state of the subway train is learned, thereby facilitating the researcher in further researching the subway train.

Description

Big data generation method for virtual subway train operation based on section speed limit and expert experience technical field

The invention relates to the technical field of data processing, in particular to a method for generating big data of virtual subway train operation based on section speed limit and expert experience.

Background technique

In recent years, the operation data acquisition methods of subway trains can be divided into two types: single operation curve generated by tracking simulation and manual driving data sampling. Among them, the simulation to generate a single running curve has the following research: through the four steps of reading data, data preprocessing, setting the calculation interval, calculating and outputting the results, the reference running curve is simulated and generated; the genetic algorithm is used to find out the position and location of the key points of the subway train. Acceleration of subway trains, and then use the knowledge of subway train kinematics to obtain the speed curve; use non-parametric iterative learning method to optimize the speed curve of a single subway train; use PSO-CS algorithm to provide the optimal control target curve for subway trains. However, the generation process of this method of obtaining subway train operation data is relatively complicated, the optimization time is long, and the generated curve can only adapt to one type of operation time.

In addition, some studies have obtained data mining from the operating curves of human driving experts, and sampled the state of subway trains every 0.5s to obtain the speed-displacement curves of subway trains. This method is time-consuming, laborious and inefficient, and the obtained data It can only be applied to this section of the running interval and the set running time, and the versatility is not strong.

Contents of the invention

The purpose of the present invention is to provide a virtual subway train operation big data generation method based on interval speed limit and expert experience, generate a large amount of virtual data based on reality, and screen according to the needs of researchers to obtain curves that meet the requirements, and perform Isochronous sampling is used to obtain the tracking data set of the curve, which is convenient for the study of train operation.

The technical scheme adopted in the present invention is:

A method for generating big data of virtual subway train operation based on section speed limit and expert experience, which includes the following steps:

Step 1, set the parameter interval of the virtual subway train according to expert experience and data, the parameter interval includes acceleration interval, speed interval, station distance interval and speed change distance interval;

Step 2, using the five-stage operation method to segment the operation curve of the virtual subway train, and set the operation parameters for each stage respectively;

Step 3, using the operating parameters of each stage of the set five-stage operating method to calculate the operating data of several groups of virtual subway trains, and using drawing tools to generate corresponding operating curves;

Step 4, set screening conditions according to research requirements to obtain corresponding operating curves;

Step 5: Sampling curve data at equal time intervals for each selected curve, and outputting the state of the train at each time point.

Further, the setting of the parameter interval in step 1 specifically includes the following steps:

Step 1-1, calculate and obtain the actual subway train acceleration interval based on the actual subway train data, configure the acceleration interval of the virtual subway train to include the actual subway train acceleration interval; that is, the actual subway train acceleration interval is a subset of the acceleration interval of the virtual subway train;

Step 1-2, calculate the speed interval of the actual subway train operation based on the actual subway train data, configure the speed interval of the virtual subway train to include the speed interval of the actual subway train operation; that is, the speed interval of the actual subway train operation is the speed interval of the virtual subway train operation a subset of velocity intervals;

Step 1-3, based on the interval between two adjacent stations of the actual subway train line, configure the interval between two adjacent stations of the virtual subway train line to include the interval between two adjacent stations of the actual subway train line; that is, the actual subway train The interval between two adjacent stations of the line is a subset of the interval between two adjacent stations of the virtual subway train line;

In steps 1-4, the running process of the virtual subway train is divided into four stages of speed change and one stage of constant speed. The speed change distance is set to 100-600m, and the step length is 50m to form a speed change distance interval.

Further, the five-stage operation method in step 2 divides the operation curve of the virtual subway train into four stages of variable speed process and one stage of constant speed process, and the operating parameters of each stage are as follows:

First shift stage:

First, the acceleration time _t1 of the first shifting phase is calculated from the first acceleration limit speed v _max1 and the first shifting acceleration a _max1 , as shown in formula (1):

The constant-speed travel time _t1 of the first shift stage is calculated from the remaining preset shift distance Lef ₁ of the first shift and the first acceleration speed limit v _max1 , as shown in formula (2):

The remaining preset shift distance Lef ₁ of the first shift is calculated from the preset shift distance dis and the first acceleration distance s ₁ , as shown in formula (3):

Lef ₁ = dis-s ₁ (3)

The first acceleration distance s ₁ is calculated from the acceleration time t ₁ of the first shift stage and the first acceleration speed limit v _max1 , as shown in formula (4):

Then the total running time _T1 of the first stage is calculated from the acceleration time _t1 and the constant speed running time _t1 , as shown in formula (5):

T ₁ =t ₁ +t ₁ (5)

The second shift stage:

The calculation of the running time of the second shifting stage is the same as the first stage, which can be calculated by formula (6) ~ formula (10). The calculation variables involved are the acceleration time t ₂ of the first shifting stage, the first acceleration speed limit v _max1 , the second acceleration speed limit v _max2 , the second shifting acceleration a _max2 , the second shifting speed The constant speed travel time t ₂ , the remaining preset shift distance Lef ₂ for the second shift, the preset shift distance dis, and the second acceleration distance s ₂ .

Lef ₂ = dis-s ₂ (8)

T ₂ =t ₂ +t ₂ (10)

Uniform speed driving stage:

The running time runtime of the subway train at the stage of constant speed running is calculated by the second acceleration speed limit _vmax2 of the subway train and the runtance of the constant speed running distance, as shown in formula (11):

The third shift stage:

The running time of the third shifting stage can be calculated by formula (12) ~ formula (16). The calculation variables involved are the deceleration time t ₃ of the third shifting stage, the third deceleration speed limit v _max3 , the second acceleration speed limit v _max2 , the third shifting acceleration a _max3 , the third shifting speed limit The constant speed travel time th ₃ , the remaining preset shift distance Lef ₃ for the third shift, the preset shift distance dis, and the third acceleration distance s ₃ .

Lef ₃ = dis-s ₃ (14)

T ₃ =t ₃ +t ₃ (16)

fourth shift stage

The running time of the fourth shifting stage can be calculated by formula (17) ~ formula (21). The calculation variables involved are the deceleration time t ₄ of the fourth shift stage, the third deceleration speed limit v _max3 , the fourth shift acceleration a _max4 , the constant speed travel time th ₄ of the fourth shift stage, and the fourth The remaining preset shifting distance Lef ₄ , the preset shifting distance dis , and the fourth acceleration distance s ₄ .

Lef ₄ = dis-s ₄ (19)

T ₄ =t ₄ +t ₄ (21)

Calculation of running time in the fastest running state:

The running time alltime in the fastest running state is calculated from the running time T ₁ , T ₂ , T ₃ , T ₄ of the four shifting stages and the running time runtime at a constant speed, as shown in formula (22).

alltime＝T ₁ +T ₂ +T ₃ +T ₄ +runtime (22).

Further, in step 3, the operating curve is drawn and formed with the curve corresponding to the fastest operating state as the upper bound and the curve corresponding to the slowest operating state as the lower bound.

Further, the data sampling interval in step 5 is 0.1 second.

Further, the state of the train at each time point in step 5 includes current position acceleration m/s ² , current position elapsed running time s, current position running speed m/s, current position running distance m, current position speed limit m/s s, the time to maintain the current driving state s, the remaining shifting distance at the current position m, the remaining shifting range at the current position m/s, the remaining time at the current position at the station s, and the remaining distance at the current position at the station m.

The present invention adopts the above technical scheme, based on human-machine hybrid intelligence, learns the advanced idea of AlphaZero, abandons the traditional method of collecting subway train operation data, generates a large amount of data according to expert experience and curve generation algorithm, and then performs screening and drawing. That is to say, the subway train driving is regarded as playing Go in one-dimensional space, and the required parameters are proposed according to the subway train speed curve generation algorithm, and the parameter range is set in combination with expert experience, so as to greatly reduce the order of magnitude of the subway train driving data and meet various running times. and interval requirements. The various running times covered by the virtual data can be observed by drawing the frequency distribution map of the running time of subway trains, which can meet the data requirements of different situations, and is more conducive to the research of intelligent driving algorithms for subway trains than traditional data.

Description of drawings

The present invention will be described in further detail below in conjunction with accompanying drawing and specific embodiment;

Fig. 1 is the schematic flow sheet of the present invention's virtual subway train operation big data generation method based on section speed limit and expert experience;

Fig. 2 is five section schematic diagrams of virtual subway train operation;

Fig. 3 is the fastest running state and the slowest running state schematic diagram of virtual subway train operation;

Fig. 4 is the relation schematic diagram of subway train speed-distance;

Fig. 5 is a schematic diagram of frequency distribution of subway train running time;

Figure 6 is a schematic diagram of the operating curve under the condition of a speed limit of 80km/h;

Figure 7 is a schematic diagram of the running time under the condition of a speed limit of 80km/h;

Figure 8 is a schematic diagram of the operating curve under the condition of a speed limit of 100km/h;

Figure 9 is a schematic diagram of the fastest running time under the condition of a speed limit of 100km/h;

Figure 10 is a schematic diagram of the operation curve under the condition of a station distance of 2800m;

Figure 11 is a schematic diagram of the running time under the condition of a station distance of 2800m and a speed limit of 100km/h;

Figure 12 Schematic diagram of the operation curve under the condition of a station distance of 700m;

Figure 13 Schematic diagram of the running time with a station distance of 700m and a speed limit of 100km/h;

Figure 14 Schematic diagram of positioning a single curve.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

The most critical idea of the present invention is to set the parameter range according to expert experience and data, then generate virtual data through the train operation method set in the present invention, and then filter the data set according to the researcher's requirements to obtain a small number of curves. Perform isochronous tracking on a small number of curves obtained, and export the running state data set of the curves.

As shown in one of Figures 1 to 14, the present invention discloses a virtual subway train operation big data generation method based on section speed limit and expert experience, which includes the following steps:

Step 1, set the parameter interval of the virtual subway train according to expert experience and data, the parameter interval includes the acceleration interval, the speed interval, the station distance interval and the speed change distance interval; further, the setting of the parameter interval in step 1 specifically includes the following steps:

Step 1-1, calculate and obtain the actual subway train acceleration interval based on the actual subway train data, configure the acceleration interval of the virtual subway train to include the actual subway train acceleration interval; that is, the actual subway train acceleration interval is a subset of the acceleration interval of the virtual subway train;

Specifically, in order to make the data set produced by the research include various traction and braking conditions, the present invention has inquired about the operation data of Fuzhou subway and obtained the following data: when the running speed of Fuzhou subway is 0-40km/h, the average acceleration is greater than 0.83m/h s2, when the running speed is 0-80km/h, the average acceleration is greater than 0.5m/s2. Therefore, the acceleration interval of the subway train speed curve data set generation algorithm should be greater than the actual subway train acceleration interval, that is, greater than the maximum acceleration and less than the minimum acceleration. The specific data is set to 0.3-1.3m/s2, and the step size is set to 0.1m/s2.

Step 1-2, calculate the speed interval of the actual subway train operation based on the actual subway train data, configure the speed interval of the virtual subway train to include the speed interval of the actual subway train operation; that is, the speed interval of the actual subway train operation is the speed interval of the virtual subway train operation a subset of velocity intervals;

Specifically, after data review, the following information was obtained: As of December 2020, the total length of Fuzhou Metro Line 1 is 29.582km, all of which are underground; a total of 25 stations are set up, all of which are underground; 6-section B-type The maximum operating speed of subway trains is 80km/h[13]. Fuzhou Metro Line 2 is initially equipped with 31 subway vehicles from Quanzhou CRRC Tangche Company. The subway trains are composed of 4 trains, 2 trains and 6 trains, with a maximum passenger capacity of 1 880 people , with a maximum operating speed of 80km/h[14]. In order to make the virtual data set summarize all the running conditions, the speed range of the virtual data is set to be greater than the actual running speed range, that is, the virtual fastest running speed should be greater than the actual fastest running speed of 100km/h. In order to consider the riding experience of the passengers, the slowest running speed can not be too low, which can be set to 20km/h as an embodiment of the present invention. Thus, the operating speed range is set to 20-100km/h, and the step size is set to 5km/h.

Step 1-3, based on the interval between two adjacent stations of the actual subway train line, configure the interval between two adjacent stations of the virtual subway train line to include the interval between two adjacent stations of the actual subway train line; that is, the actual subway train The interval between two adjacent stations of the line is a subset of the interval between two adjacent stations of the virtual subway train line;

Specifically, according to the data, after the adjustment, the starting point of Fuzhou Metro Line 1 Project (Phase I) is Xiangfeng Station, and the terminal station is Fuzhou South Railway Station. The spacing is 1.202km; as of April 2019, Fuzhou Metro Line 2 has a total of 22 stations, all of which are underground stations. The maximum station spacing is 2.827km (from Houting Station to Juyuanzhou Station), and the minimum station spacing is 0.745km (Juyuanzhou Station to Hongwan Station), the average station distance is 1.392km. Therefore, the distance between stations is set to 700-3 000m, which is smaller than the minimum station distance and greater than the maximum station distance to include the possibility of all station distances, and the step length is set to 100m; because the subway train speed generation algorithm includes four stages of variable speed process and one stage of constant speed process , so set the speed change distance as 100-600m, and set the step length as 50m.

In steps 1-4, the running process of the virtual subway train is divided into four stages of speed change and one stage of constant speed. The speed change distance is set to 100-600m, and the step length is 50m to form a speed change distance interval.

Step 2, using the five-stage operation method to segment the operation curve of the virtual subway train, and set the operation parameters for each stage respectively;

Specifically, in the ideal operating state, the subway train is regarded as a rigid body, assuming that it has no friction, no air resistance, and no force on the carriage, and a five-stage subway train operation method is proposed. The specific implementation method is shown in Figure 2. The bold black dotted line in the figure is the speed limit curve of the subway train; the vertical dotted line is the division line of the operation phase; the gray point is the turning point of the operation phase.

First, the curve is divided into 5 segments (divided by vertical dotted lines in Figure 1). In the first shifting stage, the subway train accelerates to the preset first acceleration limit speed vmax1 with the preset first shifting acceleration amax1, and then travels at a constant speed to complete the first shifting remaining preset acceleration distance Lef1; the second shifting stage , the subway train accelerates with the preset second acceleration amax2 to the preset second acceleration limit speed vmax2 of the subway train, and then moves at a constant speed, and the remaining preset acceleration distance Lef2 is left after the second speed change; The preset second acceleration limit speed vmax2 of the preset subway train runs at a constant speed and finishes the preset running distance runtance at a constant speed; the last two sections are decelerated running, and in the third shifting stage, the subway train first runs through the third shifting and the remaining preset shifting distance Lef3, Then decelerate with the preset third speed change acceleration amax3, so that the speed of the subway train is reduced to the preset first deceleration limit speed vmax3 of the subway train; The remaining preset shifting distance Lef4 of shifting is then decelerated at the preset fourth shifting acceleration amax4, so that the speed of the subway train is reduced to 0, that is, the subway train arrives at the station.

Further, the five-stage operation method in step 2 divides the operation curve of the virtual subway train into the first shifting stage, the second shifting stage, the uniform speed running stage, the third shifting stage, and the fourth shifting stage, each The stage operation parameters are as follows:

First shift stage:

First, the acceleration time _t1 of the first shifting phase is calculated from the first acceleration limit speed v _max1 and the first shifting acceleration a _max1 , as shown in formula (1):

The constant-speed travel time _th1 of the first shift stage is calculated from the remaining preset shift distance Lef ₁ of the first shift and the first acceleration speed limit v _max1 , as shown in formula (2):

The remaining preset shift distance Lef ₁ of the first shift is calculated from the preset shift distance dis and the first acceleration distance s ₁ , as shown in formula (3):

Lef ₁ = dis-s ₁ (3)

The first acceleration distance s ₁ is calculated from the acceleration time t ₁ of the first shift stage and the first acceleration speed limit v _max1 , as shown in formula (4):

Then the total running time T ₁ of the first stage is calculated from the acceleration time t ₁ and the constant speed travel time th ₁ , as shown in formula (5):

T ₁ =t ₁ +th ₁ (5)

The second shift stage:

The calculation of the running time of the second shifting stage is the same as the first stage, which can be calculated by formula (6) ~ formula (10). The calculation variables involved are the acceleration time t ₂ of the first shifting stage, the first acceleration speed limit v _max1 , the second acceleration speed limit v _max2 , the second shifting acceleration a _max2 , the second shifting speed The constant speed travel time th ₂ , the remaining preset shift distance Lef ₂ for the second shift, the preset shift distance dis, and the second acceleration distance s ₂ .

Lef ₂ = dis-s ₂ (8)

T ₂ =t ₂ +th ₂ (10)

Uniform speed driving stage:

The running time runtime of the subway train at the stage of constant speed running is calculated by the second acceleration speed limit _vmax2 of the subway train and the runtance of the constant speed running distance, as shown in formula (11):

The third shift stage:

The running time of the third shifting stage can be calculated by formula (12) ~ formula (16). The calculation variables involved are the deceleration time t ₃ of the third shifting stage, the third deceleration speed limit v _max3 , the second acceleration speed limit v _max2 , the third shifting acceleration a _max3 , the third shifting speed limit The constant speed travel time th ₃ , the remaining preset shift distance Lef ₃ for the third shift, the preset shift distance dis, and the third acceleration distance s ₃ .

Lef ₃ = dis-s ₃ (14)

T ₃ =t ₃ +th ₃ (16)

fourth shift stage

The running time of the fourth shifting stage can be calculated by formula (17) ~ formula (21). The calculation variables involved are the deceleration time t ₄ of the fourth shift stage, the third deceleration speed limit v _max3 , the fourth shift acceleration a _max4 , the constant speed travel time th ₄ of the fourth shift stage, and the fourth The remaining preset shifting distance Lef ₄ , the preset shifting distance dis , and the fourth acceleration distance s ₄ .

Lef ₄ = dis-s ₄ (19)

T ₄ =t ₄ +th ₄ (21)

Calculation of running time in the fastest running state:

The running time alltime in the fastest running state is calculated from the running time T ₁ , T ₂ , T ₃ , T ₄ of the four shifting stages and the running time runtime at a constant speed, as shown in formula (22).

alltime=T ₁ +T ₂ +T ₃ +T ₄ +runtime (22).

Step 3, using the operating parameters of each stage of the set five-stage operating method to calculate the operating data of several groups of virtual subway trains, and using drawing tools to generate corresponding operating curves;

Specifically, taking the fastest running state and the slowest running state of the subway train as an example, the five-stage running mode is analyzed, as shown in Figure 3: the first running state is the fastest running close to the speed limit curve of the subway train state, in this state, the first acceleration limit speed vmax1 and the first deceleration limit speed vmax3 of the subway train are set as the minimum speed limit Emin of the subway train, and the second acceleration limit speed vmax2 of the subway train is set as the minimum speed limit Emax of the subway train; the speed change stage The accelerations amax1, amax2, amax3, and amax4 are all the fastest accelerations; the second running state is to set the first acceleration limit speed vmax1 of the preset subway train and the first deceleration limit speed vmax3 to half of the preset minimum speed limit Emin of the subway train. The second deceleration limit speed vmax2 of the preset subway train is set to the minimum speed limit Emin of the preset subway train; the accelerations amax1, amax2, amax3, and amax4 of the speed change stage are all the slowest accelerations, and the slowest running state is obtained. These two operating states are the upper boundary and lower boundary of the generated curve, and other generated curves are in between, as shown in Figure 4.

According to the above assumptions, the data is classified, and the subway train operation data set can be obtained, with a total of 312 800 0 data, which can be realized by Python programming and exported as a CSV file. The column variables include the minimum speed limit, maximum speed limit, acceleration, preset acceleration Distance, two-station distance, four-segment acceleration distance, running time and other parameters. In the generated data set, 209 005 0 pieces of data were obtained after eliminating the curves that did not conform to the actual situation (such as running time greater than 600s, not conforming to the preset running model). The frequency distribution of running time of these data is shown in Figure 5.

Step 4, set screening conditions according to research requirements to obtain corresponding operating curves;

Specifically, in order to verify the usability of the data set, the present invention set the fastest running speed of Fuzhou Metro to 80km/h, the fastest running speed of the data set to 100km/h, the maximum station distance of Fuzhou Metro Line 2 to 2800m, and the shortest distance between the two stations of the data set. Taking the spacing of 700m as an example to screen, the following results can be obtained.

(4.1) Use the running speed as the filter condition:

Set the maximum speed limit to the actual operating speed of Fuzhou Metro at 80km/h, and set the other parameters to the minimum speed limit of 30km/h, the distance between two stations to 1600m, and the acceleration distance to 300m, and obtain 2450 pieces of data, which can be obtained through matplotlib drawing such as 6 As shown in the running curve, and get its running time as shown in Figure 7.

Set the maximum speed limit to 100km/h, the minimum speed limit to 50km/h, the distance between two stations to 1600m, and the acceleration distance to 300m, and obtain 5510 pieces of data. After matplotlib drawing, the running curve shown in Figure 8 can be obtained, and it can be obtained as shown in Figure 9 running time.

(4.2) Take the distance between two stations as the filter condition

Set the distance between two stations as the maximum station distance of Fuzhou Metro Line 2 to 2800m, and set the other parameters as the minimum speed limit of 30km/h, the maximum speed limit of 50km/h, and the acceleration distance of 500m to obtain 350 pieces of data, which can be obtained through matplotlib drawing such as 10 The running curve shown, and get its running time as shown in Figure 11.

Set the distance between the two stations to 700m, and set the other parameters to the minimum speed limit of 30km/h, the maximum speed limit of 50km/h, and the acceleration distance of 100m, and obtain 350 pieces of data. After drawing with matplotlib, the running curve shown in Figure 12 can be obtained, and Its running time is shown in Figure 13.

Step 5: Sampling curve data at equal time intervals for each selected curve, and outputting the state of the train at each time point.

Specifically, as shown in Figure 14, for the screened curves, data sampling is performed at an interval of 0.1s for each curve, and the state of the train at each time point is output,

Further, the state of the train at each time point in step 5 includes current position acceleration m/s ² , current position elapsed running time s, current position running speed m/s, current position running distance m, current position speed limit m/s s, the time to maintain the current driving state s, the remaining shifting distance at the current position m, the remaining shifting range at the current position m/s, the remaining time at the current position at the station s, and the remaining distance at the current position at the station m.

The invention makes a breakthrough in replacing the traditional method of obtaining subway train operation data by artificially generating a large number of subway operation curves. Specifically, by investigating the actual data of subway operation and consulting relevant experts to obtain the limited parameters of the virtual data such as the traction interval, speed interval, station distance interval, and speed change interval, so that the generated virtual data has a small range and high reliability; and then according to the dynamics knowledge Assume the five-stage running mode of the subway train, so as to generate the virtual speed-distance image of the train; then use python to carry out programming and data visualization to obtain a large amount of virtual subway train running data required by the present invention. For the generated large amount of virtual data, the present invention screens them according to the conditions, and obtains the partial dotted lines required by the researcher. In addition, for the selected single curve, the present invention tracks it in real time, and obtains the running state of the single curve subway train every 0.1s, specifically including: current position acceleration, current position elapsed running time, current position running speed, current The running distance at the current location, the speed limit at the current location, the time to maintain the current driving state, the remaining shifting distance at the current location, the remaining shifting range at the current location, the remaining time at the current location to the station, and the remaining distance at the current location to the station. According to these data, the present invention can understand the The real-time running status of the train is convenient for researchers to further study the subway train.

Apparently, the described embodiments are some of the embodiments of the present application, but not all of them. In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The components of the embodiments of the application generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Therefore, the detailed description of the embodiments of the present application is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

Claims (7)

The big data generation method of virtual subway train operation based on interval speed limit and expert experience is characterized in that: it comprises the following steps: Step 1, set the parameter interval of the virtual subway train according to expert experience and data, the parameter interval includes acceleration interval, speed interval, station distance interval and speed change distance interval; Step 2, use the five-stage operation method to segment the operation curve of the virtual subway train, and set the operation preset parameters for each stage respectively; Step 3, using the operating parameters of each stage of the set five-stage operating method to calculate the operating data of several groups of virtual subway trains, and using drawing tools to generate corresponding operating curves; Step 4, set screening conditions according to research requirements to obtain corresponding operating curves; Step 5: Sampling curve data at equal time intervals for each selected curve, and outputting the state of the train at each time point. The virtual subway train operation big data generation method based on interval speed limit and expert experience according to claim 1, is characterized in that: the setting of the parameter interval of step 1 specifically comprises the following steps: Step 1-1, calculate and obtain the actual subway train acceleration interval based on the actual subway train data, configure the acceleration interval of the virtual subway train to include the actual subway train acceleration interval; that is, the actual subway train acceleration interval is a subset of the acceleration interval of the virtual subway train; Step 1-2, calculate the speed interval of the actual subway train operation based on the actual subway train data, configure the speed interval of the virtual subway train to include the speed interval of the actual subway train operation; that is, the speed interval of the actual subway train operation is the speed interval of the virtual subway train operation a subset of velocity intervals; Step 1-3, based on the interval between two adjacent stations of the actual subway train line, configure the interval between two adjacent stations of the virtual subway train line to include the interval between two adjacent stations of the actual subway train line; that is, the actual subway train The interval between two adjacent stations of the line is a subset of the interval between two adjacent stations of the virtual subway train line; In steps 1-4, the running process of the virtual subway train is divided into four stages of speed change and one stage of constant speed. The speed change distance is set to 100-600m, and the step length is 50m to form a speed change distance interval. According to claim 1, the virtual subway train operation big data generation method based on interval speed limit and expert experience is characterized in that: in step 2, the five-stage operation method divides the operation curve of the virtual subway train into the first speed change successively stage, the second speed change stage, the constant speed driving stage, the third speed change stage and the fourth speed change stage, the preset parameters of the four-stage speed change process and the one-stage constant speed process include the preset speed change distance dis, the first acceleration speed limit v _{max 1} means the second speed change acceleration a _{max 2} and the first time speed change acceleration a _{max 1} ; the running distance runtance at a constant speed. According to claim 3, based on section speed limit and expert experience virtual subway train operation big data generation method, it is characterized in that: in step 2, the calculation of each stage operation parameter is as follows: First shift stage: The acceleration time _t1 of the first shift stage is calculated from the first acceleration limit speed v _{max 1} and the first shift acceleration a _{max 1} , as shown in formula (1):

The constant-speed travel time _th1 of the first shift stage is calculated from the remaining preset shift distance Lef ₁ of the first shift and the first acceleration speed limit v _{max 1} , as shown in formula (2):

The remaining preset shift distance Lef ₁ of the first shift is calculated from the preset shift distance dis and the first acceleration distance s ₁ , as shown in formula (3): Lef ₁ = dis-s ₁ (3) The first acceleration distance s ₁ is calculated from the acceleration time t ₁ of the first shift stage and the first acceleration speed limit v _{max 1} , as shown in formula (4):

The total running time T ₁ of the first stage is calculated from the acceleration time t ₁ and the constant speed travel time th ₁ , as shown in formula (5): T ₁ =t ₁ +th ₁ (5) The second shift stage: The calculation formulas for each variable are

Lef ₂ = dis-s ₂ (8)

T ₂ =t ₂ +th ₂ (10) Among them, t ₂ represents the acceleration time of the first shift stage, v _{max 1} represents the first acceleration speed limit, v _{max 2} represents the second acceleration speed limit, a _{max 2} represents the second speed change acceleration, and th ₂ represents the first speed limit The constant-speed driving time in the second shift stage, Lef ₂ represents the remaining preset shift distance for the second shift, dis represents the preset shift distance, and s ₂ represents the second acceleration distance; Uniform speed driving stage: The running time runtime of the subway train at the stage of constant speed running is calculated by the second acceleration speed limit v _{max 2} of the subway train and the runtance of the constant speed running distance, as shown in formula (11):

The third shift stage: The calculation formulas for each calculation variable are

Lef ₃ = dis-s ₃ (14)

T ₃ =t ₃ +th ₃ (16) Among them, the calculation variables involved are the deceleration time t ₃ of the third shift stage, the third deceleration speed limit v _{max 3} , the second acceleration speed limit v _{max 2} , the third speed change acceleration a _{max 3} , the third speed limit The constant speed travel time th ₃ of the secondary shifting stage, the remaining preset shifting distance Lef ₃ of the third shifting, the preset shifting distance dis, and the third acceleration distance s ₃ ; The fourth shift stage: The calculation formulas for each calculation variable are

Lef ₄ = dis-s ₄ (19)

T ₄ =t ₄ +th ₄ (21) Among them, the calculation variables involved are the deceleration time t ₄ of the fourth shift stage, the third deceleration speed limit v _{max 3} , the fourth shift acceleration a _{max 4} , the constant speed travel time th ₄ of the fourth shift stage, The remaining preset shift distance Lef ₄ for the fourth shift, the preset shift distance dis, and the fourth acceleration distance s ₄ ; Calculation of running time in the fastest running state: The running time alltime in the fastest running state is calculated from the running time T ₁ , T ₂ , T ₃ , T ₄ of the four shifting stages and the running time runtime at a constant speed, as shown in formula (22): alltime=T ₁ +T ₂ +T ₃ +T ₄ +runtime (22). According to claim 1, the virtual subway train operation big data generation method based on interval speed limit and expert experience, is characterized in that: in step 3, draw and form the operation curve with the fastest operation state corresponding curve as the upper bound and the slowest operation The state-corresponding curve is used as the lower bound. The method for generating big data of virtual subway train operation based on section speed limit and expert experience according to claim 1, characterized in that: the interval of data sampling in step 5 is 0.1 second. According to claim 1, based on section speed limit and expert experience virtual subway train running big data generation method, it is characterized in that: in step 5, the state of train at each time point includes current position acceleration m/s ² , current position Elapsed running time s, current position running speed m/s, current position running distance m, current position speed limit m/s, current driving state time s, current position remaining shifting distance m, current position remaining shifting range m/s, The remaining time to the station at the current position s and the remaining distance to the station at the current position m.

Images