CN109017884B - Train automatic operation control method based on learning - Google Patents
Train automatic operation control method based on learning Download PDFInfo
- Publication number
- CN109017884B CN109017884B CN201810789988.2A CN201810789988A CN109017884B CN 109017884 B CN109017884 B CN 109017884B CN 201810789988 A CN201810789988 A CN 201810789988A CN 109017884 B CN109017884 B CN 109017884B
- Authority
- CN
- China
- Prior art keywords
- train
- traction
- threshold value
- running time
- time
- 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.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/04—Automatic systems, e.g. controlled by train; Change-over to manual control
Abstract
The invention provides a train automatic operation control method based on learning. The method comprises the following steps: setting an initial traction excision threshold value and a traction establishment threshold value of the train, and establishing a mapping matrix between train operation time and the traction excision threshold value and between the train operation time and the traction establishment threshold value through an iterative learning and linear interpolation method based on the initial traction excision threshold value and the traction establishment threshold value; acquiring the planned operation time of the train according to the line segmentation and the distributed initial operation time of the train, and performing operation control on the train according to the planned operation time of the train and the mapping matrix; and updating and managing the mapping matrix according to the actual inter-station running time and the planned running time of the train. The method of the invention can select proper traction cutting and threshold value establishment according to the planned running time of the issued train, so that the train can run on time between the current stations under the ATO condition.
Description
Technical Field
The invention relates to the technical field of train operation control, in particular to a train automatic operation control method based on learning.
Background
At present, in a control algorithm of an ATO (Automatic Train Operation), a control process is divided into a cruise phase and an accurate stop phase. In the cruising stage, the EBI (Emergency brake intervention Curve) is reduced by a fixed value to be used as a target speed, and PID (proportional, integral, derivative) control or maximum traction-coasting mode tracking is adopted. In the accurate parking stage, starting from a parking point, a brake curve is generated at a common brake rate and used as a target speed curve, and PID control tracking is adopted. Different inter-station operating times are obtained by repeatedly adjusting the reduced fixed value in the cruise phase.
An effective train automatic operation control method based on learning does not exist in the prior art.
Disclosure of Invention
The embodiment of the invention provides a train automatic operation control method based on learning, which aims to overcome the defects of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme.
A train automatic operation control method based on learning is characterized by comprising the following steps:
setting an initial traction excision threshold value and a traction establishment threshold value of the train, and establishing a mapping matrix between train operation time and the traction excision threshold value and between the train operation time and the traction establishment threshold value through a learning iteration and linear interpolation method based on the initial traction excision threshold value and the traction establishment threshold value;
acquiring the planned operation time of the train according to the line segmentation and the distributed initial operation time of the train, and performing operation control on the train according to the planned operation time of the train and the mapping matrix;
and updating and managing the mapping matrix according to the actual inter-station running time and the planned running time of the train.
Further, the setting of the initial traction cut threshold value and the traction establishment threshold value of the train, and the establishment of a mapping matrix between the train operation time and the traction cut threshold value and the traction establishment threshold value by a learning iterative method based on the initial traction cut threshold value and the traction establishment threshold value includes:
step 1: giving initial traction cutting threshold values and traction establishing threshold values of two groups of trains, wherein one group of initial traction cutting threshold values and traction establishing threshold values correspond to the shortest running time of the trains;
step 2: the train operates according to the two groups of initial traction cutting threshold values and traction establishing threshold values respectively to obtain corresponding train operation time under the conditions of the two groups of initial traction cutting threshold values and traction establishing threshold values;
and step 3: giving a certain train planning running time which is not recorded yet, and calculating a traction cutting threshold value and a traction establishing threshold value corresponding to the train planning running time by a linear interpolation method when the train planning running time is between the recorded train planning running times;
when the train planning running time is greater than or less than all recorded train planning running times, calculating a traction removal threshold value and a traction establishment threshold value corresponding to the train planning running time by adopting an iterative learning method;
and 4, step 4: aiming at the planned running time of the train, the train runs according to the traction cutting threshold value and the traction establishing threshold value determined in the step 3;
and 5: when the train runs to a terminal, acquiring the actual train running time of the train in different line sections, and storing the actual train running time, the corresponding traction cutting threshold value and the corresponding traction establishing threshold value in a mapping matrix in an associated manner;
step 6: and (5) repeatedly executing the step 3, the step 4 and the step 5 until the train scheduled operation time in the mapping matrix meets the set time resolution, and stopping executing the processing flow from the step 1 to the step 6.
Further, the calculation formula of the linear interpolation is as follows:
wherein t isl，tnRepresenting the recorded closest train operation time before and after the train planning operation time, t being the train planning operation time, c (t) establishing a traction cut threshold or traction threshold corresponding to said train planning operation time, cnA traction cut-off threshold value or a traction creation threshold value corresponding to the recorded train operation time which is closest after the train planning operation time, clAnd establishing a threshold value for the recorded traction cutting threshold value or traction corresponding to the closest train running time before the train planning running time.
Further, the formula of the iterative learning is as follows:
c1＝c2+q*(Ts-Tm)
wherein c1 is the traction cut-off threshold or traction establishment threshold corresponding to the train planning operation time, c2 is the recorded traction cut-off threshold or traction establishment threshold corresponding to the maximum or minimum train planning operation time, q is the learning step length, TsPlanning run time for a given train, TmPlanning operation for recorded maximum trainAnd (3) removing the solvent.
Further, the acquiring the planned operation time of the train according to the route section and the allocated initial operation time of the train includes:
segmenting the running line of the train according to the turning point of the fixed speed limit of the line, and setting a train state check point at the initial position of each line segment; and distributing the initial running time of each section of the line according to the shortest running time between stations and the issued planned running time between stations to obtain the planned running time of the initial train on the section.
Further, when the ratio of the length of the different line segments to the total length of the line segments is used as the weight, the allocation rule of the initial running time of each line segment is as follows:
wherein
Is the shortest running time, x, of the jth allocation zonejIs the assigned weight of the jth section, T is the inter-station scheduled run time, TminIs the shortest running time between stations,
is the planned run time for the jth zone.
Further, the controlling the operation of the train according to the planned operation time of the train and the mapping matrix includes:
inquiring the mapping matrix according to the train plan operation time to obtain a traction cutting threshold value and a traction establishing threshold value corresponding to the train plan operation time; if the train plan operation time is in the gap of the mapping matrix, obtaining approximate values of a traction excision threshold value and a traction establishment threshold value corresponding to the gap of the mapping matrix through a linear interpolation method, and taking the approximate values as the traction excision threshold value and the traction establishment threshold value corresponding to the train plan operation time;
the calculation formula of the linear interpolation is as follows:
wherein t isu，tvRepresenting the recorded closest train operation time before and after the train planning operation time, t being the train planning operation time, D (t) being a traction cut threshold or a traction set threshold corresponding to said train planning operation time, DvEstablishing a threshold value for the recorded traction cut-off threshold value or traction corresponding to the closest train operation time after the train planning operation time, DuEstablishing a threshold value for the recorded traction cutting threshold value or traction corresponding to the closest train running time before the train planning running time;
controlling the train to run according to the obtained traction cut-off threshold value and the traction establishment threshold value, and when the train runs in an accelerated mode and the traction reaches the traction cut-off threshold value, the train starts to coast; when the train is coasting and the tractive effort reaches the traction establishment threshold, the train is re-accelerated until the tractive effort reaches the traction cut-off threshold.
Further, the updating and managing the mapping matrix according to the actual inter-station running time and the planned running time of the train includes:
when the train runs to the initial position of each section of line, the train state is checked;
if the train state meets the checking condition, redistributing the running time of the remaining line section according to the current running time of the train;
if the train state does not meet the inspection condition, selecting a traction removal threshold value and a traction establishment threshold value which enable the train to run at the highest speed;
when the train does not run to finish the last section of line, repeatedly executing the processing process of controlling the train running and checking the train state according to the planned running time and the mapping matrix of the train; and when the train finishes the last section of line, recording the actual train running time of the train between the whole stations, and replacing the train running time corresponding to the current traction cutting threshold value and the traction establishing threshold value in the mapping matrix by using the actual train running time when the difference between the planned train running time and the actual train running time is within a set time threshold value.
Further, when the ratio of the length of the different remaining line segments to the total length of the remaining line segments is used as a weight, the formula for redistributing the current running time of the train is as follows:
where N is the number of allocation sections, j is the index of the past previous allocation section, left
Is the planned runtime of the updated j + m-th section, right side
Is the planned runtime, y, of the j + m th section that is not updatedj+mIs the assigned weight on the j + m-th section,
is the planned allocation time on the jth sector, tacIs the actual running time of the last session.
According to the technical scheme provided by the embodiment of the invention, the method provided by the embodiment of the invention establishes the mapping matrix between the train operation time and the traction cutting and threshold value through learning iteration, and can select the proper traction cutting and threshold value according to the delivered train plan operation time, so that the train can operate on time between the current stations under the condition of AT 0.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a processing flow chart of a learning-based train automatic operation control method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a processing procedure for updating a mapping matrix during online operation of a train according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a circuit segment according to an embodiment of the present invention;
fig. 4 is a schematic diagram of initial runtime allocation according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
Example one
The embodiment of the invention provides a train automatic operation control method based on learning, which can construct a mapping matrix stage of a traction removal threshold value, a traction establishment threshold value and train operation time, and update a mapping matrix during the online operation of a train.
The processing flow of the learning-based train automatic operation control method provided by the embodiment of the invention is shown in fig. 1, and the processing flow is used for constructing a mapping matrix between train operation time of a train and a traction cutting threshold value and a traction establishing threshold value, and comprises the following processing steps:
step S110: and giving initial traction removal threshold values and traction establishment threshold values of the two groups of trains, wherein one group of traction removal threshold values and traction establishment threshold values correspond to the shortest running time of the trains.
And the train operates according to the two groups of initial traction cutting threshold values and traction establishing threshold values respectively to obtain corresponding operating time under two different threshold conditions.
Step S120: giving a certain train planning running time which is not recorded yet, and calculating a traction cutting threshold value and a traction establishing threshold value corresponding to the train planning running time by a linear interpolation method when the train planning running time is between the recorded train planning running times;
the calculation formula of the linear interpolation is as follows:
wherein t isl，tnRepresenting the recorded closest train operation time before and after the train planning operation time, t being the train planning operation time, c (t) establishing a traction cut threshold or traction threshold corresponding to the train planning operation time, cnA traction cut-off threshold value or a traction creation threshold value corresponding to the recorded train operation time which is closest after the train planning operation time, clAnd establishing a threshold value for the recorded traction cutting threshold value or traction corresponding to the closest train running time before the train planning running time.
And when the train planning running time is greater than or less than all the recorded train planning running times, calculating a traction cutting threshold value and a traction establishing threshold value corresponding to the train planning running time by adopting an iterative learning method.
The iterative learning formula is as follows:
c1＝c2+q*(Ts-Tm)
wherein c1 is the traction cut-off threshold or traction establishment threshold corresponding to the train planning operation time, c2 is the recorded traction cut-off threshold or traction establishment threshold corresponding to the maximum or minimum train planning operation time, q is the learning step length, TsPlanning run time for a given train, TmAnd planning the running time for the recorded maximum train.
Step S130: the train operates according to the traction cut-off threshold and the traction established threshold determined in step S120.
When the train runs to the terminal, the actual train running time of the train in different line sections is obtained (the planned running time of the train is replaced), and the actual train running time, the corresponding traction cutting threshold value and the corresponding traction establishing threshold value are stored in a mapping matrix in an associated mode.
Step S140: steps S120 and S130 are repeatedly performed. And stopping the processing flow of the method until the train planning running time in the mapping matrix meets the set time resolution.
Example two
Fig. 2 is a schematic diagram of a processing procedure for updating a mapping matrix during online operation of a train according to an embodiment of the present invention, which specifically includes the following steps:
step 1: fig. 3 is a schematic diagram of a line segment according to an embodiment of the present invention, in which a line is segmented according to a turning point of a fixed speed limit of the line, and a train state check point is set at an initial position of each line segment;
step 2: fig. 4 is a schematic diagram of initial runtime allocation according to an embodiment of the present invention. And performing initial operation time distribution on each section of the circuit according to the shortest operation time between stations and the issued planned operation time between stations. When the ratio of the length of the different line sections to the total length of the line is taken as the weight, the allocation formula of the initial running time of each line section is as follows:
wherein
Is the shortest running time, x, of the jth allocation zonejIs the assigned weight of the jth section, T is the inter-station scheduled run time, TminIs the shortest running time between stations,
is the planned run time for the jth zone.
And step 3: and acquiring the planned running time of the train according to the initial running time distributed by each section of the line. Then, inquiring the mapping matrix according to the train plan operation time to obtain a traction removal threshold value and a traction establishment threshold value corresponding to the train plan operation time;
and if the train plan operation time is in the gap of the mapping matrix, obtaining an approximate value of a traction excision threshold value and a traction establishment threshold value corresponding to the gap of the mapping matrix by a linear interpolation method, and taking the approximate value as the traction excision threshold value and the traction establishment threshold value corresponding to the train plan operation time.
The calculation formula of the linear interpolation is as follows:
wherein t isu，tvRepresenting the recorded closest train operation time before and after the train planning operation time, t being the train planning operation time, D (t) being a traction cut threshold or a traction set threshold corresponding to said train planning operation time, DvEstablishing a threshold value for the recorded traction cut-off threshold value or traction corresponding to the closest train operation time after the train planning operation time, DuAnd establishing a threshold value for the recorded traction cutting threshold value or traction corresponding to the closest train running time before the train planning running time.
And 4, step 4: controlling the train to run according to the obtained traction cut-off threshold value and the traction establishment threshold value, and when the train runs in an accelerated mode and the traction reaches the traction cut-off threshold value, the train starts to coast; when the train is coasting and the tractive effort reaches the traction establishment threshold, the train is re-accelerated until the tractive effort reaches the traction cut-off threshold.
And 5: when the train runs to the initial position of each section of line, the train state is checked. And if the checking condition is met, redistributing the running time of the rest line section according to the current running time of the train. Otherwise, selecting a traction cutting threshold value and a traction establishing threshold value which enable the train to run at the highest speed. When the ratio of the length of the different remaining line sections to the total length of the remaining line sections is used as the weight, the formula for redistributing the current running time of the train is as follows:
where N is the number of allocation sections, j is the index of the past previous allocation section, left
Is the planned runtime of the updated j + m-th section, right side
Is the planned runtime, y, of the j + m th section that is not updatedj+mIs the assigned weight on the j + m-th section,
is the planned allocation time on the jth sector, tacIs the actual running time of the last session.
Step 6: and when the train does not run to the last section of the line, repeating the steps 3, 4 and 5.
When the train runs to the last section of line, recording the actual running time of the train between the whole stations, comparing the actual running time with the planned running time, and updating a mapping matrix between the train running time and a traction cutting threshold value and between the train running time and a traction establishing threshold value by adopting a learning method, namely when the difference between the train planned running time and the train actual running time is within a set time threshold value (such as 10 seconds), replacing the train running time corresponding to the current traction cutting threshold value and the traction establishing threshold value in the mapping matrix by using the actual train running time.
In summary, the method of the embodiment of the invention establishes a mapping matrix between train operation time and traction cutting threshold value through learning iteration, adjusts an operation curve between train stations by controlling changes of the traction cutting threshold value and the traction establishing threshold value, and updates the mapping matrix between the train operation time and the traction cutting threshold value and between the train operation time and the traction establishing threshold value through actual tests in combination with the actual operation time between the train stations and the train planning operation time. Through multiple tests, the invention can select a proper traction cutting threshold value and a traction establishing threshold value according to the planned running time of the issued train, so that the train can run between the current stations on time under the ATO condition.
The learning-based Train Automatic operation control method provided by the embodiment of the invention can adjust the inter-station operation time of the Train in real time, the inter-station operation time is issued to the Train before the Train is dispatched by an Automatic Train monitoring system (ATS), the Train arrives at the station on time according to the inter-station operation time after the Train is dispatched, the deviation is not more than +/-2%, the parking precision and the comfort (unbalanced centrifugal acceleration and impact rate on a curve) are ensured, and the energy consumption is properly reduced.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A train automatic operation control method based on learning is characterized by comprising the following steps:
setting an initial traction excision threshold value and a traction establishment threshold value of the train, and establishing a mapping matrix between train operation time and the traction excision threshold value and between the train operation time and the traction establishment threshold value through a learning iteration and linear interpolation method based on the initial traction excision threshold value and the traction establishment threshold value;
acquiring the planned operation time of the train according to the line segmentation and the distributed initial operation time of the train, and performing operation control on the train according to the planned operation time of the train and the mapping matrix;
updating and managing the mapping matrix according to the actual inter-station running time and the planned running time of the train;
the method comprises the following steps of setting an initial traction cutting threshold value and a traction establishing threshold value of a train, and establishing a mapping matrix between train operation time and the traction cutting threshold value and the traction establishing threshold value through a learning iteration method based on the initial traction cutting threshold value and the traction establishing threshold value, wherein the mapping matrix comprises the following steps:
step 1: giving initial traction cutting threshold values and traction establishing threshold values of two groups of trains, wherein one group of initial traction cutting threshold values and traction establishing threshold values correspond to the shortest running time of the trains;
step 2: the train runs according to the two groups of initial traction cutting threshold values and traction building threshold values respectively to obtain corresponding train running time under the conditions of the two groups of initial traction cutting threshold values and traction building threshold values;
and step 3: giving a certain train planning running time which is not recorded yet, and calculating a traction cutting threshold value and a traction establishing threshold value corresponding to the train planning running time by a linear interpolation method when the train planning running time is between the recorded train planning running times;
when the train planning running time is greater than or less than all recorded train planning running times, calculating a traction removal threshold value and a traction establishment threshold value corresponding to the train planning running time by adopting an iterative learning method;
and 4, step 4: aiming at the planned running time of the train, the train runs according to the traction cutting threshold value and the traction establishing threshold value determined in the step 3;
and 5: when the train runs to a terminal, acquiring the actual train running time of the train in different line sections, and storing the actual train running time, the corresponding traction cutting threshold value and the corresponding traction establishing threshold value in a mapping matrix in an associated manner;
step 6: and (5) repeatedly executing the step 3, the step 4 and the step 5 until the train scheduled operation time in the mapping matrix meets the set time resolution, and stopping executing the processing flow from the step 1 to the step 6.
2. The method of claim 1, wherein the linear interpolation is calculated as follows:
wherein t isl，tnIndicating that the recorded position is before the scheduled operation time of the trainAnd thereafter the closest train operation time, t being the train planning operation time, c (t) establishing a traction cut-off threshold or traction threshold corresponding to said train planning operation time, cnA traction cut-off threshold value or a traction creation threshold value corresponding to the recorded train operation time which is closest after the train planning operation time, clAnd establishing a threshold value for the recorded traction cutting threshold value or traction corresponding to the closest train running time before the train planning running time.
3. The method of claim 2, wherein the iteratively learned formula is as follows:
c1＝c2+q*(Ts-Tm)
wherein c1 is the traction cut-off threshold or traction establishment threshold corresponding to the train planning operation time, c2 is the recorded traction cut-off threshold or traction establishment threshold corresponding to the maximum or minimum train planning operation time, q is the learning step length, TsPlanning run time for a given train, TmAnd planning the running time for the recorded maximum train.
4. A method according to any one of claims 1 to 3, wherein said obtaining planned operational time of the train based on the route segments and the assigned initial operational time of the train comprises:
segmenting the running line of the train according to the turning point of the fixed speed limit of the line, and setting a train state check point at the initial position of each line segment; and distributing the initial running time of each section of the line according to the shortest running time between stations and the issued planned running time between stations to obtain the planned running time of the initial train on the section.
5. The method of claim 4, wherein when the ratios of the lengths of the different line segments to the total length of the line are used as weights, the allocation rule of the initial running time of each line segment is as follows:
wherein
Is the shortest running time, x, of the jth allocation zonejIs the assigned weight of the jth section, T is the inter-station scheduled run time, TminIs the shortest running time between stations,
is the planned runtime for the jth zone, and N is the number of zones allocated.
6. The method of claim 5, wherein said controlling the operation of the train according to the planned operation time of the train and the mapping matrix comprises:
inquiring the mapping matrix according to the train plan operation time to obtain a traction cutting threshold value and a traction establishing threshold value corresponding to the train plan operation time; if the train plan operation time is in the gap of the mapping matrix, obtaining an approximate value of a traction excision threshold value and a traction establishment threshold value corresponding to the gap of the mapping matrix through a linear interpolation method, and taking the approximate value as the traction excision threshold value and the traction establishment threshold value corresponding to the train plan operation time;
the calculation formula of the linear interpolation is as follows:
wherein t isu，tvRepresenting the recorded closest train operation time before and after the train planning operation time, t being the train planning operation time, D (t) being a traction cut threshold or a traction set threshold corresponding to said train planning operation time, DvFor recorded location in a trainA traction cut-off threshold or a traction build threshold corresponding to the closest train operation time after the planned operation time, DuEstablishing a threshold value for the recorded traction cutting threshold value or traction corresponding to the closest train running time before the train planning running time;
controlling the train to run according to the obtained traction cut-off threshold value and the traction establishment threshold value, and when the train runs in an accelerated mode and the traction reaches the traction cut-off threshold value, the train starts to coast; when the train is coasting and the tractive effort reaches the traction establishment threshold, the train is re-accelerated until the tractive effort reaches the traction cut-off threshold.
7. The method according to claim 6, wherein the updating and managing the mapping matrix according to the actual inter-station running time and the planned running time of the train comprises:
when the train runs to the initial position of each section of line, the train state is checked;
if the train state meets the checking condition, redistributing the running time of the remaining line section according to the current running time of the train;
if the train state does not meet the inspection condition, selecting a traction cutting threshold value and a traction establishing threshold value which enable the train to run at the highest speed;
when the train does not run to finish the last section of line, repeatedly executing the processing process of controlling the train running and checking the train state according to the planned running time and the mapping matrix of the train; and when the train finishes the last section of line, recording the actual train running time of the train between the whole stations, and replacing the train running time corresponding to the current traction cutting threshold value and the traction establishing threshold value in the mapping matrix by using the actual train running time when the difference between the planned train running time and the actual train running time is within a set time threshold value.
8. The method of claim 7, wherein when the ratios of the different remaining track segment lengths to the remaining track segment total lengths are used as weights, the formula for the redistribution of the current train operation time is as follows:
where N is the number of allocation sections, j is the index of the past previous allocation section, left
Is the planned runtime of the updated j + m-th section, right side
Is the planned runtime, y, of the j + m th section that is not updatedj+mIs the assigned weight on the j + m-th section,
is the planned allocation time on the jth sector, tacIs the actual running time of the last session.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810789988.2A CN109017884B (en) | 2018-07-18 | 2018-07-18 | Train automatic operation control method based on learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810789988.2A CN109017884B (en) | 2018-07-18 | 2018-07-18 | Train automatic operation control method based on learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109017884A CN109017884A (en) | 2018-12-18 |
| CN109017884B true CN109017884B (en) | 2020-03-31 |
Family
ID=64643305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810789988.2A Active CN109017884B (en) | 2018-07-18 | 2018-07-18 | Train automatic operation control method based on learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109017884B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109649418A (en) | 2019-01-29 | 2019-04-19 | 中车长春轨道客车股份有限公司 | A kind of railroad train progress control method and system |
| CN110794711A (en) * | 2019-11-26 | 2020-02-14 | 交控科技股份有限公司 | Train energy-saving operation control method based on energy-saving slope, electronic device and medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04133601A (en) * | 1990-09-21 | 1992-05-07 | Toshiba Corp | Automatic operation controller having protective function |
| TWI277549B (en) * | 2002-01-31 | 2007-04-01 | Toshiba Corp | Automatic fixed-position stop control device for train |
| CN106274994B (en) * | 2016-08-30 | 2018-11-13 | 湖南中车时代通信信号有限公司 | A kind of train all fronts arrival time prediction technique and system |
| CN107640183B (en) * | 2017-07-31 | 2020-08-25 | 北京石油化工学院 | Train operation control method based on iterative learning control |
-
2018
- 2018-07-18 CN CN201810789988.2A patent/CN109017884B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109017884A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109649441B (en) | Automatic train driving energy-saving control method | |
| EP3088240B1 (en) | Driving curve creation device, driving assistance device, driving control device, and driving curve creation method | |
| CN111267913B (en) | Energy-saving running method for urban rail transit train | |
| CN109017884B (en) | Train automatic operation control method based on learning | |
| CN109476330B (en) | Automation system and method for optimizing control of a train | |
| CN103213677B (en) | For the method and apparatus assisting the driving of aircraft during landing period | |
| CN109703606B (en) | High-speed train intelligent driving control method based on historical operation data | |
| CN103818392A (en) | Method for adjusting train operation curve | |
| CN108734361B (en) | Car pooling order processing method and device | |
| CN107198884B (en) | Method for efficiently loading game scenes | |
| JP2016000573A (en) | Information processor and operation curve creation method | |
| US9097433B2 (en) | Apparatus and a method for controlling facility devices, and a non-transitory computer readable medium thereof | |
| CN111797473A (en) | Subway train main line operation simulation calculation method and device | |
| CN111582919B (en) | Flight passenger rate prediction method and system | |
| CN111783357A (en) | Transfer route optimization method and system based on passenger delay reduction | |
| CN112896244A (en) | Method and device for controlling operation between train stations based on target speed curve tracking | |
| JP2016019411A (en) | Automatic train operation device and automatic train operation method | |
| CN112744270B (en) | Rapid and accurate train stopping method based on state identification | |
| CN112172878B (en) | Train speed limit curve calculation method and system | |
| JP2020029211A (en) | Operation curve creation device | |
| JP6045388B2 (en) | Operation management device, operation management method, and program | |
| WO2023087717A1 (en) | Method for determining transition altitude elements in flight climbing stage on basis of constant-value segment identification | |
| JP2018007497A (en) | Traveling pattern creation device and traveling pattern creation method | |
| CN113935581A (en) | Freight train scheduling method and system based on rolling time domain event influence analysis | |
| WO2017184114A1 (en) | Speed profiling for locomotive display and event recorder |
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 |