CN114368417A - Intelligent train route arrangement method and system based on machine learning - Google Patents
Intelligent train route arrangement method and system based on machine learning Download PDFInfo
- Publication number
- CN114368417A CN114368417A CN202210056795.2A CN202210056795A CN114368417A CN 114368417 A CN114368417 A CN 114368417A CN 202210056795 A CN202210056795 A CN 202210056795A CN 114368417 A CN114368417 A CN 114368417A
- Authority
- CN
- China
- Prior art keywords
- train
- data
- station
- module
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000010801 machine learning Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000013480 data collection Methods 0.000 claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 238000007405 data analysis Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 231100000279 safety data Toxicity 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000012806 monitoring device Methods 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a machine learning-based train route intelligent arrangement method and a machine learning-based train route intelligent arrangement system, which are characterized by comprising a data collection module, a central processing module, a scheduling module and a safety monitoring module; the processor adjusts the balance and economy of the train task arrangement; the processor in the scheduling module can analyze the safety monitoring data and transmit the influence analysis data to the data analysis unit of the central processing module, and the data analysis unit can update the data quickly. Compared with the prior art, the invention adopts the safety monitoring module, can constantly monitor the train and track running data and timely transmit the abnormal state to the dispatching module, the processor in the dispatching module is preset with a large number of abnormal analysis subprograms which can actually analyze the abnormal data and timely transmit the abnormal processing data to the data analysis unit in the central processing module, and the train arrangement unit can timely adjust the train arrangement unit, thereby greatly improving the train arrangement efficiency and the train running safety.
Description
Technical Field
The invention belongs to the field of train transportation, and particularly relates to a train route intelligent arrangement method and system based on machine learning.
Background
In the process of operating domestic trains, the arrangement of train schedules is one of the most basic plans before the trains run. Usually, before a train normally starts, a dispatcher needs to adjust a pre-programmed basic schedule as a train running plan according to experience, so that the train runs according to the existing plan. In actual operation, the train is often subjected to changes of passenger flow and transportation organization methods to adjust the schedule so as to meet actual operation requirements. Therefore, how to efficiently and reliably adjust the schedule plan is beneficial to improving the management level of urban rail transit operation and the quality of transportation service.
The current schedule still stays in the degree of manual compilation and computer-aided compilation, but the automatic compilation of the train schedule is not realized, so that the schedule arrangement needs a dispatcher to spend a large amount of time for compilation, even because of insufficient experience of the dispatcher, the imbalance of the train schedule arrangement is caused, and the train receiving and dispatching are easily caused to be too little or too much at the same time. Along with the push of the accurate management of the urban rail system and the opening of a new line, the updating frequency of the schedule arrangement of the line is higher, and the labor intensity of the compiling personnel is greatly increased.
Disclosure of Invention
The invention aims to provide a machine learning-based train route intelligent arrangement method and system, which can greatly reduce the labor of a compiler and improve the updating speed and the balance of a train schedule at the same time. Aiming at the problems, the train schedule intelligent system is designed originality.
In order to achieve the purpose, the technical scheme adopted by the invention for solving the technical problems is as follows: a running method of an intelligent train route arranging method based on machine learning is characterized in that: the method comprises the following steps of 1) obtaining constant data, wherein the constant data comprises passenger demand data, train basic data and station basic data;
2) comprehensively analyzing the types and the number of the required trains through the constant data, and analyzing the whole time length of each type of train from entering the station to leaving the station;
3) inputting the analysis data into a preset train scheduling model for solving, evaluating and adjusting a solving result, obtaining an adjustment quantity of model parameters through evaluation and adjustment, and storing the adjustment quantity;
4) feeding back the adjustment quantity of the model parameters to a train scheduling model, and adjusting original parameters in the train scheduling model;
5) inputting the constant data into the adjusted train scheduling model again, and solving;
6) acquiring safety data in real time, wherein the safety data comprises train operation data, track safety data and electric equipment working data; when the safety data are abnormal, the abnormal safety data are processed through a preset abnormal processing subprogram, the variable influence degree of the train scheduling model is obtained, the train scheduling model is updated, and the updated train scheduling model is input through the constant data to obtain the updated train scheduling.
In the above scheme, the passenger demand data includes an origin, a destination and a number of passengers; the train basic data includes the type and the number of trains; the station basic data comprises the number of station stop track lines, the throat part of a station stop platform and the length of a stop part.
In the above scheme, the evaluation adjustment includes a safety adjustment and an economic adjustment, and the safety adjustment is constrained by: 1) t isi+td+ti<Ti+1，tf>(ti+ti')/2 wherein TiIs the moment when the ith train is just arriving at the station, tdThe time length of the ith train arriving at the station late, tiThe time length of the i-th train when unloading passengers, Ti+1The departure time of the ith +1 th train is the right point; t is tfThe maximum delay time which is not influenced by trains is delayed;
2) the constraints of the economic adjustment are:
u is the controllable energy consumption budget of the station, ti is the time length of the ith train arriving at the station late point, ti' is the time length of the ith +1 train departure at the station late point, and V is the proportion of extra energy consumption loss when the train arrives at the station late point or arrives at the train late point.
In the scheme, the system further comprises additional safety constraint conditions, and at least one station stop track can be used for train stopping in an emergency at the same time.
The passenger demand data collects passenger ticketing information and historical passenger flow information of each station through the Internet and the Internet of things; the train basic data comprises collected train types, train quantity of each type and maintenance history information of each type of train; and the station basic data collects station passenger flow capacity, the length of a train parking track of a station and the average time of a station waiting hall leading to a station waiting place.
Preferably, the train operation data comprises the position, speed and energy consumption data of each collected train; the method comprises the steps that track data collection comprises track wear data monitored by a plurality of monitoring devices arranged beside a track and image data of whether obstacles exist on the track or not; and the electrical equipment data collects whether the trackside signal equipment is normal or not.
Preferably, the system also comprises a data collecting module, a central processing module, a scheduling module and a safety monitoring module; the data collection module comprises a passenger riding data unit, a train basic data collection unit and a station basic data collection unit; the central processing module comprises a data receiving unit, a data analyzing unit, a model editing and simulating unit and a train arranging unit; the scheduling module comprises a processor and a task scheduling unit; the safety monitoring module comprises a train operation data collecting unit, a track data collecting unit and an electrical equipment data collecting unit;
preferably, the data collection module is connected with a data receiving unit of the central processing module, a train arrangement unit of the central processing module transmits data to a processor of the scheduling module, the processor performs balance and economic adjustment on train task arrangement, and a large number of abnormal data processing subroutines are preset in the processor; the safety monitoring module transmits safety monitoring data to the dispatching module, a processor in the dispatching module analyzes the safety monitoring data and transmits analysis influence data to a data analysis unit of the central processing module, and the data analysis unit updates data analysis and updates a train arrangement unit; the model editing and simulating unit is provided with a safety constraint condition, an economic constraint condition and a balance constraint condition.
Preferably, the exception handling subprogram is preset in the processor in the scheduling module, the preset subprogram is an editable subprogram, and the exception subprogram can be processed manually under the condition that the corresponding exception handling self-call is not stored, and the manual processing method is added into the exception handling subprogram, namely the exception subprogram is a real-time updating system, and along with the running time of the system, the exception handling subprogram can automatically handle most of exception monitoring data monitored by the safety monitoring unit, so that the intelligence and the scientificity of train arrangement are greatly improved.
The central processing module train scheduling unit transmits data to a scheduling module, which schedules the work schedule of each train and trainee.
Preferably, the simulation editing and simulating unit is preset with a solving evaluation adjustment program, and the evaluation adjustment program is provided with a constraint editing input port, where the constraints include safety constraints, economic constraints, and balance constraints. On one hand, the model editing and simulating unit presets constraint conditions constructed by various models, such as running time between train stations, passenger unloading time, train interval time before and after, station track information, traffic information and the like, and a dispatcher can reasonably edit the models according to the actual conditions of the stations to make the models most close to the actual conditions.
In the above scheme, the model editing and simulating unit further includes an additional safety constraint condition that at least one station stop track can be used for train stop of an emergency at the same time. Namely, at least in the same time, one track is stopped without arranging trains, namely, the trains can be arranged on the idle train track at any time under the emergency conditions of weather or train faults and the like, thereby greatly improving the safety of train operation.
Preferably, the passenger riding data unit collects passenger ticketing information and historical passenger flow information of each station through the internet and the internet of things; the train basic data collection unit collects train types, train quantity of each type and maintenance history information of each type of train; the station basic data collection unit collects station passenger flow capacity, station train parking track length and average station waiting time of a station waiting hall leading to a station waiting place. The trains are generally respectively a common train, a motor train and a high-speed train, the time of passing through and stopping the station is different, and meanwhile, the design lengths of the station access channel and the station access channel of different stations are different, which affects the arrangement of the train at any time; further, it is considered that the time of unloading passengers from different stations and the delay time of the train, and the time arrangement of trains before and after the same station needs to consider the time of unloading passengers and the delay time of the train.
In the above scheme, the monitoring device generally includes a speed sensor, a high-definition camera, a network transmission device, and the like; the system can shoot the running speed of the train, the operation working conditions of train components, the abrasion state of a track and the like; the data are transmitted to the scheduling module, the scheduling module can adjust the train arrangement plan in time, and meanwhile, the scheduling module can also issue tasks to maintenance personnel to maintain related equipment in time.
The working method of the intelligent system comprises the following steps of 1), collecting passenger demand data and station train type data through big data, comprehensively analyzing the number and the number of trains of various types, and analyzing the whole time length of each type of train from entering a station to leaving the station through station basic data;
2) the model editing and simulating module inputs the analysis data into a preset train scheduling model for solving, and inputs the result into a scheduling model, and a processor in the scheduling model adjusts the balance, economy and safety of the train scheduling data;
3) the scheduling module issues the adjusted vertical train scheduling task to a dispatcher and a trainee;
4) the safety monitoring module constantly monitors train operation data, track safety data and electrical equipment working data and sends abnormal data to a processor in the scheduling module, the processor is preset with a corresponding abnormal processing logic operation subprogram, the processor transmits the data after abnormal data processing to a data analysis module in the central processing module, the data analysis module updates data of a train arrangement unit, the train arrangement unit sends the updated data to the scheduling module, and a task arrangement unit in the scheduling module updates task release.
The invention adopts big data collection, and the data collection is more efficient and comprehensive. The method has the following advantages: 1. compared with the prior art, the invention adopts the safety monitoring module, can constantly monitor the train and track running data and timely transmit the abnormal state to the dispatching module, the processor in the dispatching module is preset with a large number of abnormal analysis subprograms which can actually analyze the abnormal data and timely transmit the abnormal processing data to the data analysis unit in the central processing module, and simultaneously, the abnormal processing subprograms can be updated in real time, so that the processing means can gradually cope with the abnormal problems of different conditions, and the train arrangement unit can timely adjust the train arrangement unit, thereby greatly improving the train arrangement efficiency and the train running safety.
2. A large number of abnormal problem processing subprograms are preset in the scheduling module, and after the abnormal data of the safety monitoring module are received, the related abnormal data subprograms can be called rapidly.
3. Whether this application has the barrier through monitoring facilities monitoring track wearing and tearing and on the track, can discover the potential safety hazard problem in advance to turn into analog data with data, and in time update the train arrangement plan, improved the security of train operation.
4. The application monitors the working state data of the electrical equipment, can avoid the problem that abnormal data caused by the problem of network or circuit data transmission cannot be transmitted in time, and further provides guarantee for safe operation of the train.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is an overall flow chart of the intelligent scheduling method of the present invention.
Fig. 2 is an overall structural view of the intelligent arrangement system of the present invention.
FIG. 3 is a block diagram of the data collection module according to the present invention.
FIG. 4 is an overall structure diagram of the CPU module of the present invention.
Fig. 5 is an overall structural diagram of a scheduling module of the present invention.
Fig. 6 is an overall structural view of the safety monitoring module of the present invention.
In the figure: 1. the system comprises a data collection module 2, a central processing module 3, a scheduling module 4, a safety monitoring module 5, a passenger riding data collection unit 6, a train basic data collection unit 7, a station basic data collection unit 8, a data receiving unit 9, a data analysis unit 10, a model editing and simulation unit 11, a train arrangement unit 12, a processor 13, a task arrangement unit 14, a train operation data collection unit 15, a track data collection unit 16 and an electrical equipment data collection unit
Detailed Description
Embodiments of the present application will be described in detail with reference to the drawings and examples, so that how to implement technical means to solve technical problems and achieve technical effects of the present application can be fully understood and implemented.
Referring to fig. 1, the present invention provides a technical solution: a running method of an intelligent train route arranging method based on machine learning is characterized in that: the method comprises the following steps of 1) obtaining constant data, wherein the constant data comprises passenger demand data, train basic data and station basic data;
2) comprehensively analyzing the types and the number of the required trains through the constant data, and analyzing the whole time length of each type of train from entering the station to leaving the station;
3) inputting the analysis data into a preset train scheduling model for solving, evaluating and adjusting a solving result, obtaining an adjustment quantity of model parameters through evaluation and adjustment, and storing the adjustment quantity;
4) feeding back the adjustment quantity of the model parameters to a train scheduling model, and adjusting original parameters in the train scheduling model;
5) inputting the constant data into the adjusted train scheduling model again, and solving;
6) acquiring safety data in real time, wherein the safety data comprises train operation data, track safety data and electric equipment working data; when the safety data are abnormal, the abnormal safety data are processed through a preset abnormal processing subprogram, the variable influence degree of the train scheduling model is obtained, the train scheduling model is updated, and the updated train scheduling model is input through the constant data to obtain the updated train scheduling.
The passenger demand data comprises the origin, destination and number of passengers for taking the passengers; the train basic data includes the type and the number of trains; the station basic data comprises the number of station stop track lines, the throat part of a station stop platform and the length of a stop part.
The evaluation adjustment comprises safety adjustment and economy adjustment, and the constraint of the safety adjustment is as follows: 1) t isi+td+ti<Ti+1，tf>(ti+ti')/2 wherein TiIs the moment when the ith train is just arriving at the station, tdThe time length of the ith train arriving at the station late, tiThe time length of the i-th train when unloading passengers, Ti+1The departure time of the ith +1 th train is the right point; t is tfThe maximum delay time which is not influenced by trains is delayed;
2) the constraints of the economic adjustment are:
u is the controllable energy consumption budget of the station, ti is the time length of the ith train arriving at the station late point, ti' is the time length of the ith +1 train departure at the station late point, and V is the proportion of extra energy consumption loss when the train arrives at the station late point or arrives at the train late point.
The system also comprises an additional safety constraint condition, so that at least one station stop track can be used for train stop of an emergency at the same time.
The passenger demand data collects passenger ticketing information and historical passenger flow information of each station through the Internet and the Internet of things; the train basic data comprises collected train types, train quantity of each type and maintenance history information of each type of train; and the station basic data collects station passenger flow capacity, the length of a train parking track of a station and the average time of a station waiting hall leading to a station waiting place.
The train operation data comprises the position, speed and energy consumption data of each train; the method comprises the steps that track data collection comprises track wear data monitored by a plurality of monitoring devices arranged beside a track and image data of whether obstacles exist on the track or not; and the electrical equipment data collects whether the trackside signal equipment is normal or not.
As shown in fig. 2, the system further comprises a data collecting module, a central processing module, a scheduling module and a safety monitoring module;
as shown in fig. 3, the data collection module includes a passenger riding data unit, a train basic data collection unit, and a station basic data collection unit;
as shown in fig. 4, the central processing module includes a data receiving unit, a data analyzing unit, a model editing and simulating unit, and a train arranging unit;
as shown in FIG. 5, the scheduling module includes a processor and a task scheduling unit;
as shown in fig. 6, the safety monitoring module includes a train operation data collecting unit, a track data collecting unit, and an electrical equipment data collecting unit;
in the scheme, the data collection module is connected with a data receiving unit of the central processing module, a train arrangement unit of the central processing module transmits data to a processor of the scheduling module, the processor performs balance and economic adjustment on train task arrangement, and a large number of abnormal data processing subprograms are preset in the processor; the safety monitoring module transmits safety monitoring data to the dispatching module, a processor in the dispatching module analyzes the safety monitoring data and transmits analysis influence data to a data analysis unit of the central processing module, and the data analysis unit updates data analysis and updates a train arrangement unit; the model editing and simulating unit is provided with a safety constraint condition, an economic constraint condition and a balance constraint condition.
The central processing module train scheduling unit transmits data to a scheduling module, which schedules the work schedule of each train and trainee.
The simulation editing and simulating unit is preset with an evaluation adjusting program, a constraint editing input port is arranged in the evaluation adjusting program, the constraints comprise safety constraints, economic constraints and balance constraints, a dispatcher can add reasonable type constraints according to actual working conditions, and a train arrangement scheme is obtained through model adjustment.
And an exception handling subprogram is preset in a processor in the dispatching module, the train arranging unit transmits data to the dispatching module, and the dispatching module arranges the working plans of each train and trainees.
In the above scheme, the model editing and simulating unit further includes an additional safety constraint condition that at least one station stop track can be used for train stop of an emergency at the same time. Namely, at least in the same time, one track is stopped without arranging trains, namely, the trains can be arranged on the idle train track at any time under the emergency conditions of weather or train faults and the like, thereby greatly improving the safety of train operation.
Preferably, the passenger riding data unit collects passenger ticketing information and historical passenger flow information of each station through the internet and the internet of things; the train basic data collection unit collects train types, train quantity of each type and maintenance history information of each type of train; the station basic data collection unit collects station passenger flow capacity, station train parking track length and average station waiting time of a station waiting hall leading to a station waiting place. The trains are generally respectively a common train, a motor train and a high-speed train, the time of passing through and stopping the station is different, and meanwhile, the design lengths of the station access channel and the station access channel of different stations are different, which affects the arrangement of the train at any time; further, it is considered that the time of unloading passengers from different stations and the delay time of the train, and the time arrangement of trains before and after the same station needs to consider the time of unloading passengers and the delay time of the train.
In the above scheme, the monitoring device generally includes a speed sensor, a high-definition camera, a network transmission device, and the like; the system can shoot the running speed of the train, the operation working conditions of train components, the abrasion state of a track and the like; the data are transmitted to the scheduling module, the scheduling module can adjust the train arrangement plan in time, and meanwhile, the scheduling module can also issue tasks to maintenance personnel to maintain related equipment in time.
The foregoing description shows and describes several preferred embodiments of the invention, but as aforementioned, it is to be understood that the invention is not limited to the forms disclosed herein, but is not to be construed as excluding other embodiments and is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A running method of an intelligent train route arranging method based on machine learning is characterized in that: the method comprises the following steps of 1) obtaining constant data, wherein the constant data comprises passenger demand data, train basic data and station basic data;
2) comprehensively analyzing the types and the number of the required trains through the constant data, and analyzing the whole time length of each type of train from entering the station to leaving the station;
3) inputting the analysis data into a preset train scheduling model for solving, evaluating and adjusting a solving result, obtaining an adjustment quantity of model parameters through evaluation and adjustment, and storing the adjustment quantity;
4) feeding back the adjustment quantity of the model parameters to a train scheduling model, and adjusting original parameters in the train scheduling model;
5) inputting the constant data into the adjusted train scheduling model again, and solving;
6) acquiring safety data in real time, wherein the safety data comprises train operation data, track safety data and electric equipment working data; when the safety data are abnormal, the abnormal safety data are processed through a preset abnormal processing subprogram, the variable influence degree of the train scheduling model is obtained, the train scheduling model is updated, and the updated train scheduling model is input through the constant data to obtain the updated train scheduling.
2. The machine learning-based train route intelligent arrangement method as claimed in claim 1, wherein the passenger demand data includes an origin, a destination and a number of passengers; the train basic data includes the type and the number of trains; the station basic data comprises the number of station stop track lines, the throat part of a station stop platform and the length of a stop part.
3. The machine learning-based train route intelligent arrangement method as claimed in claim 1, wherein the evaluation adjustment includes a safety adjustment and an economic adjustment, and the constraint of the safety adjustment is as follows:
1)Ti+td+ti<Ti+1，tf>(ti+ti')/2 wherein TiIs the moment when the ith train is just arriving at the station, tdThe time length of the ith train arriving at the station late, tiThe time length of the i-th train when unloading passengers, Ti+1The departure time of the ith +1 th train is the right point; t is tfThe maximum delay time which is not influenced by trains is delayed;
2) the constraints of the economic adjustment are:
u is the controllable energy consumption budget of the station, ti is the time length of the ith train arriving at the station late point, ti' is the time length of the ith +1 train departure at the station late point, and V is the proportion of extra energy consumption loss when the train arrives at the station late point or arrives at the train late point.
4. The machine learning-based train route intelligent arrangement method as claimed in claim 1, further comprising additional safety constraints, wherein at least one station stop track is available for train stop of an emergency at the same time.
5. The machine learning-based train route intelligent arrangement method as claimed in claim 2, wherein the passenger demand data is used for collecting passenger ticketing information and historical passenger flow information at each station through the internet and the internet of things; the train basic data comprises collected train types, train quantity of each type and maintenance history information of each type of train; and the station basic data collects station passenger flow capacity, the length of a train parking track of a station and the average time of a station waiting hall leading to a station waiting place.
6. The machine learning-based train route intelligent arrangement method as claimed in claim 1, wherein the train operation data includes collecting position, speed and energy consumption data of each train; the method comprises the steps that track data collection comprises track wear data monitored by a plurality of monitoring devices arranged beside a track and image data of whether obstacles exist on the track or not; and the electrical equipment data collects whether the trackside signal equipment is normal or not.
7. A system applying the machine learning-based train route intelligent arrangement method according to claim 1, which is characterized by comprising a data collection module, a central processing module, a scheduling module and a safety monitoring module; the data collection module comprises a passenger riding data unit, a train basic data collection unit and a station basic data collection unit; the central processing module comprises a data receiving unit, a data analyzing unit, a model editing and simulating unit and a train arranging unit; the scheduling module comprises a processor and a task scheduling unit; the safety monitoring module comprises a train operation data collecting unit, a track data collecting unit and an electrical equipment data collecting unit;
the data collection module is connected with the data receiving unit of the central processing module, the train arrangement unit of the central processing module transmits data to the processor of the scheduling module, the processor performs balance and economic adjustment on train task arrangement, and a large number of abnormal data processing subprograms are preset in the processor; the safety monitoring module transmits safety monitoring data to the dispatching module, a processor in the dispatching module analyzes the safety monitoring data and transmits analysis influence data to a data analysis unit of the central processing module, and the data analysis unit updates data analysis and updates a train arrangement unit; the model editing and simulating unit is provided with a safety constraint condition, an economic constraint condition and a balance constraint condition.
8. The machine learning-based train routing intelligence arrangement system of claim 7, wherein the central processing module train routing unit transmits data to a scheduling module that schedules trains and trainees.
9. The train route intelligent arrangement system based on machine learning as claimed in claim 7, wherein the simulation editing and simulating unit is preset with a solution evaluation adjustment program, and the evaluation adjustment program is provided with a constraint editing input port, and the constraints include safety constraints, economic constraints and balance constraints.
10. The machine learning-based train routing intelligent arrangement system of claim 7, wherein the processor in the scheduling module is pre-programmed with an exception handling subroutine having editable entries.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210056795.2A CN114368417B (en) | 2022-01-18 | 2022-01-18 | Intelligent train route arrangement method and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210056795.2A CN114368417B (en) | 2022-01-18 | 2022-01-18 | Intelligent train route arrangement method and system based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114368417A true CN114368417A (en) | 2022-04-19 |
| CN114368417B CN114368417B (en) | 2022-07-19 |
Family
ID=81143735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210056795.2A Active CN114368417B (en) | 2022-01-18 | 2022-01-18 | Intelligent train route arrangement method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114368417B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2928783A1 (en) * | 2015-05-07 | 2016-11-07 | Morr Transportation Consulting | A system to provide real-time railroad grade crossing information to support traffic management decision-making |
| CN106828544A (en) * | 2016-12-09 | 2017-06-13 | 交控科技股份有限公司 | A kind of movement across lines route triggering method and device |
| CN109649453A (en) * | 2018-12-07 | 2019-04-19 | 天津津航计算技术研究所 | A kind of train route handles method automatically |
| CN110341763A (en) * | 2019-07-19 | 2019-10-18 | 东北大学 | A kind of intelligent dispatching system that fast quick-recovery high-speed rail train is run on schedule and method |
| CN112977553A (en) * | 2021-03-05 | 2021-06-18 | 北京交通大学 | Automatic train operation adjusting method |
| CN113415322A (en) * | 2021-08-03 | 2021-09-21 | 东北大学 | High-speed train operation adjusting method and system based on Q learning |
-
2022
- 2022-01-18 CN CN202210056795.2A patent/CN114368417B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2928783A1 (en) * | 2015-05-07 | 2016-11-07 | Morr Transportation Consulting | A system to provide real-time railroad grade crossing information to support traffic management decision-making |
| CN106828544A (en) * | 2016-12-09 | 2017-06-13 | 交控科技股份有限公司 | A kind of movement across lines route triggering method and device |
| CN109649453A (en) * | 2018-12-07 | 2019-04-19 | 天津津航计算技术研究所 | A kind of train route handles method automatically |
| CN110341763A (en) * | 2019-07-19 | 2019-10-18 | 东北大学 | A kind of intelligent dispatching system that fast quick-recovery high-speed rail train is run on schedule and method |
| CN112977553A (en) * | 2021-03-05 | 2021-06-18 | 北京交通大学 | Automatic train operation adjusting method |
| CN113415322A (en) * | 2021-08-03 | 2021-09-21 | 东北大学 | High-speed train operation adjusting method and system based on Q learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114368417B (en) | 2022-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111376954B (en) | Train autonomous scheduling method and system | |
| CN110568829B (en) | Mine full production chain intelligence management and control system | |
| CN104773191B (en) | Automatic centralized enterprise railway control method and system thereof | |
| CN110329319B (en) | Full-automatic operation system for smart city rail | |
| CN113415322B (en) | High-speed train operation adjusting method and system based on Q learning | |
| CN105050881B (en) | Track traffic informationization central control system and its control method | |
| CN112883640B (en) | Digital twin station system, job scheduling method based on system and application | |
| RU2500563C1 (en) | System for train operating control in railway network course | |
| CN111232024A (en) | Intelligent running scheduling system and method for high-speed railway | |
| CN113177377A (en) | Intelligent urban rail transit network management system based on digital twins | |
| AU2015264896B2 (en) | Railroad control system having onboard management | |
| CN110803204B (en) | On-line control method for keeping running stability of high-speed train | |
| CN114611726A (en) | Urban rail transit data fusion control system based on cloud platform | |
| CN112948457A (en) | Passenger transport cableway detection monitoring and health diagnosis system, method, medium and equipment | |
| CA3106015A1 (en) | System and transport for optimizing operations of trains travelling along a railway line | |
| CN110949459B (en) | Railway wagon vehicle section shunting operation system | |
| CN106022582A (en) | Work order control system service automatic analyzing and processing method and system | |
| CN114368417B (en) | Intelligent train route arrangement method and system based on machine learning | |
| CN104504454A (en) | Integrated electric multiple unit (EMU) operation and maintenance plan making method based on the degree of model-route matching | |
| CN110794837A (en) | Intelligent inspection equipment system based on robot | |
| Kurbanov et al. | Improving the control method of the decelerator mechanism on the sorting hill in railway transport | |
| CN112614038A (en) | Intelligent operation and maintenance management system for passenger train | |
| RU2738778C1 (en) | Railroad network direction control system based on cars virtual sorting | |
| Liu | Optimization of Computer-aided Decision-making System for Railroad Traffic Dispatching Command | |
| CN111127886A (en) | Intelligent traffic management system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221026 Address after: 222002 No. 2, Chenguang Road, Haizhou District, Lianyungang City, Jiangsu Province Patentee after: LIANYUNGANG TECHNICAL College Patentee after: Lianyungang Tianshi Electronic Engineering Co.,Ltd. Address before: 222002 No. 2, Chenguang Road, Haizhou District, Lianyungang City, Jiangsu Province Patentee before: LIANYUNGANG TECHNICAL College |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240203 Address after: 222002 No. 2, Chenguang Road, Haizhou District, Lianyungang City, Jiangsu Province Patentee after: LIANYUNGANG TECHNICAL College Country or region after: China Address before: 222002 No. 2, Chenguang Road, Haizhou District, Lianyungang City, Jiangsu Province Patentee before: LIANYUNGANG TECHNICAL College Country or region before: China Patentee before: Lianyungang Tianshi Electronic Engineering Co.,Ltd. |
|
| TR01 | Transfer of patent right |