Railway skylight scheme optimization method, device and equipment and readable storage medium

Abstract

The invention provides a railway skylight scheme optimization method, device and equipment and a readable storage medium, and relates to the technical field of ordinary-speed railway transportation organizations, and the method comprises the steps: obtaining railway equipment information and train operation information, and determining a plurality of basic data; obtaining a plurality of dynamic skylights; constructing a collaborative optimization model based on the plurality of dynamic skylights and the plurality of basic data to obtain a multi-objective planning model; adjusting the basic data to obtain target data; and performing corresponding adjustment on the dynamic skylight based on the target data. According to the method, a train operation plan and dynamic skylight scheme collaborative optimization model is established by combining dynamically changing transportation requirements and equipment maintenance information, considering mutual influence between traffic flows and skylights and aiming at minimizing the total travel time and maintenance operation cost of a freight train, and solving is performed based on a Lagrange algorithm, so that the dynamic skylight scheme is optimized. Therefore, matching between the skylight and the line trafficability is ensured, reasonable application of track resources is achieved, and the skylight utilization rate is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of conventional railway transport organization, and in particular to a railway skylight scheme optimization method, device, equipment and readable storage medium. Background Art

[0002] The opening of windows and train operation have a mutually restrictive and mutually influential relationship. Most of the existing studies currently use the remaining capacity to arrange windows after the train timetable is compiled. This compilation method makes the window plan unable to meet the maintenance operation needs when the line capacity is tight, and the window realization rate is low; although a small number of literature focuses on the study of the coordinated optimization of train operation plans and window plans, they usually rely on manual experience to fix the window opening time and window segmentation, and lack a more flexible method for coordinating the window plan with the train operation plan, resulting in a greater impact of windows on train operation, making it impossible for the compiled train operation diagram to take into account both transportation efficiency and train operation safety. Therefore, there is a lack of research on the maintenance demand determination method that combines the advantages of the above two methods to ensure targeted maintenance operations while avoiding train operation safety problems caused by inaccurate equipment status prediction. Summary of the invention

[0003] The purpose of the present invention is to provide a railway skylight solution optimization method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0004] In a first aspect, the present application provides a railway skylight solution optimization method, comprising:

[0005] Acquire railway equipment information and train operation information and determine a plurality of basic data, wherein the railway equipment information includes railway equipment status prediction data and equipment fixed maintenance cycle, and the train operation information includes transportation plan and maintenance plan;

[0006] Divide the preset railway maintenance time into multiple skylights to obtain multiple dynamic skylights;

[0007] Building a collaborative optimization model based on multiple dynamic skylights and multiple basic data to obtain a multi-objective planning model, wherein the multi-objective planning model includes multiple objective functions;

[0008] Based on the constraint functions preset in the multi-objective programming model, the basic data is adjusted to obtain target data, where the target data is data that satisfies each constraint function in the multi-objective programming model;

[0009] The dynamic sunroof is adjusted accordingly based on the target data.

[0010] In a second aspect, the present application also provides a railway skylight solution optimization device, comprising:

[0011] An acquisition unit, used to acquire railway equipment information and train operation information and determine a plurality of basic data, wherein the railway equipment information includes railway equipment status prediction data and equipment fixed maintenance cycle, and the train operation information includes a transportation plan and a maintenance plan;

[0012] A division unit, used for dividing the preset railway maintenance time into a plurality of skylights to obtain a plurality of dynamic skylights;

[0013] A first construction unit is used to construct a collaborative optimization model based on multiple dynamic skylights and multiple basic data to obtain a multi-objective planning model, wherein the multi-objective planning model includes multiple objective functions;

[0014] A first adjustment unit, configured to adjust the basic data based on a constraint function preset in the multi-objective programming model to obtain target data, wherein the target data is data satisfying each constraint function in the multi-objective programming model;

[0015] The second adjustment unit is used to make corresponding adjustments to the dynamic sunroof based on the target data.

[0016] In a third aspect, the present application also provides a railway skylight solution optimization device, including:

[0017] Memory for storing computer programs;

[0018] A processor is used to implement the steps of the railway skylight solution optimization method when executing the computer program.

[0019] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned railway skylight solution optimization method are implemented.

[0020] The beneficial effects of the present invention are:

[0021] The present invention combines dynamically changing transportation demand and equipment maintenance information, considers the mutual influence between vehicle flow and skylight, takes minimizing the total travel time and maintenance operation cost of freight trains as the goal, establishes a collaborative optimization model of train operation plan and dynamic skylight scheme, and solves it based on the Lagrangian algorithm, thereby ensuring the matching of skylight and line capacity, realizing the rational use of track resources, and improving the utilization rate of skylight.

[0022] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a schematic diagram of the flow chart of the railway skylight solution optimization method described in an embodiment of the present invention;

[0025] Figure 2 It is a schematic diagram of the structure of the railway skylight solution optimization device described in an embodiment of the present invention;

[0026] Figure 3 It is a schematic diagram of the structure of the railway skylight solution optimization device described in an embodiment of the present invention.

[0027] Markings in the figure:

[0028] 10. Acquisition unit; 20. Division unit; 30. First construction unit; 40. First adjustment unit; 50. Second adjustment unit; 800. Railway skylight solution optimization device; 801. Processor; 802. Memory; 803. Multimedia component; 804. I / O interface; 805. Communication component. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0030] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0031] Embodiment 1:

[0032] This embodiment provides a railway skylight solution optimization method.

[0033] See also Figure 1 , the figure shows that the method includes step S10, step S20, step S30, step S40 and step S50.

[0034] Step S10. Obtain railway equipment information and train operation information and determine multiple basic data, the railway equipment information includes railway equipment status prediction data and equipment fixed maintenance cycle, and the train operation information includes transportation plan and maintenance plan;

[0035] Step S20. Divide the preset railway maintenance time into multiple skylights to obtain multiple dynamic skylights;

[0036] Specifically, the maintenance time range of the railway equipment can be determined based on the railway equipment information, and the railway maintenance time can be divided into multiple windows.

[0037] The maintenance time range of railway equipment is usually related to the predicted value of the railway equipment status or the fixed maintenance cycle of the equipment. The calculation formula for the maintenance time range of railway equipment is as follows:

[0038]

[0039]

[0040] in, is the maximum time allowed for the next execution of maintenance job p in the interval (i, j); is the minimum time allowed for the next execution of maintenance job p in the interval (i, j); t p (i, j) is the time when the maintenance operation p in the interval (i, j) was last executed; EC p is the fixed maintenance cycle of maintenance operation p; α u is the upper limit factor; α l is the lower limit factor; β is the adjustment parameter; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; p is the maintenance operation index; P is the set of major maintenance operations for the railway line.

[0041] The upper and lower limit factors of some equipment are shown in Table 1:

[0042] Table 1

[0043]

[0044] There are usually two ways to determine the maintenance time of railway equipment: the first way is that within the planning time period, the predicted value of the equipment status reaches the status management standard of the equipment; the second way is that if the intersection of the equipment maintenance time range based on the flexible maintenance cycle and the planning time period is not empty, the equipment maintenance operation will be included in the maintenance demand of the dynamic skylight scheme within the planning period, and the unique calculation formula for the maintenance time determination method is constructed as follows (3):

[0045]

[0046] in, Whether the maintenance operation p in the interval (i, j) is scheduled for equipment maintenance according to the predicted value of the equipment status; Whether the maintenance operation p in the interval (i, j) is scheduled for equipment maintenance according to the flexible maintenance cycle; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; p is the maintenance operation index; P is the set of major maintenance operations on the railway line;

[0047] It is a 0-1 variable. If the maintenance operation p arranges equipment maintenance according to the predicted value of the equipment status, the value is 1, otherwise it is 0; is a 0-1 variable. If the maintenance task p is scheduled for equipment maintenance according to the flexible maintenance cycle, the value is 1, otherwise it is 0. If the maintenance time of maintenance task p is determined according to the equipment status prediction value, then maintenance task p is included in the maintenance task set based on the equipment status prediction value. Otherwise, it is included in the maintenance work set based on the flexible maintenance cycle

[0048] Step S30. Constructing a collaborative optimization model based on multiple dynamic skylights and multiple basic data to obtain a multi-objective planning model, where the multi-objective planning model includes multiple objective functions;

[0049] Specifically, considering that the transportation demand of trains and the maintenance demand of railway equipment are both dynamically changing, there is a mutual influence between train traffic and skylights. Therefore, with the goal of minimizing the total travel time and maintenance operation cost of freight trains, a collaborative optimization model of train operation plan and dynamic skylight scheme is established, and it is solved to maximize the skylight utilization.

[0050] Specifically, step S30 specifically includes step S31, step S32, step S33 and step S34:

[0051] Step S31. Based on the time cost of equipment maintenance and the penalty cost of equipment maintenance, a first objective function is constructed, wherein the penalty cost of equipment maintenance is used to characterize the additional cost of untimely equipment maintenance operations;

[0052] Specifically, the cost of maintenance work is mainly composed of actual maintenance time and penalty time.

[0053] Specifically, step S31 specifically includes step S311, step S312, step S313, step S314, step S315, step S316, step S317, step S318 and step S319:

[0054] Step S311. Calculate the maintenance operation duration of each railway line within the planned time period to obtain multiple first values;

[0055] Step S312. Sum all the first values ​​to construct a time cost function for equipment maintenance;

[0056] Specifically, the cost function of equipment maintenance is as follows:

[0057]

[0058] Among them, C t (i, j, s) is the cost function of equipment maintenance; d p (i,j,s) is the start time of maintenance operation p on day s within the interval (i,j); a p (i,j,s) is the end time of maintenance operation p on the sth day within the interval (i,j); (i,j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period; p is the maintenance operation index.

[0059] Step S313. Calculate the product of the number of times the upper limit of the maintenance time of each railway line in the planning time period exceeds the preset first unit penalty cost to obtain multiple second values;

[0060] Step S314. Sum all the second values ​​to construct a penalty cost function for exceeding the upper limit of the overhaul time;

[0061] Specifically, the penalty cost function for exceeding the upper limit of maintenance time is as follows:

[0062]

[0063] in, is the penalty cost of the maintenance operation p in the interval (i, j) that is executed within the planning period but exceeds the upper limit of the predicted maintenance time; pen represents the unit penalty cost of the maintenance operation p that exceeds the upper limit of the predicted maintenance time; is the maximum time allowed for the next execution of maintenance job p in the interval (i, j); is the minimum time allowed for the next execution of maintenance job p in the interval (i, j); s is the time index; p is the maintenance job index.

[0064] Step S315. Calculate the product of the number of superelastic maintenance cycles of each railway line within the planning time period and the preset second unit penalty cost to obtain multiple third values;

[0065] Step S316. Sum all third values ​​to construct a penalty cost function for a superelastic maintenance cycle;

[0066] Specifically, the penalty cost function of the super-elastic maintenance cycle is as follows:

[0067]

[0068] in, is the penalty cost of the maintenance operation p in the interval (i, j) executed within the planning period but in a super-elastic maintenance cycle; pen' is the unit penalty cost of the maintenance operation p executed in a super-elastic maintenance cycle; MV p (i, j) is the upper limit of the execution time of maintenance operation p based on the equipment status prediction value in the interval (i, j); s is the time index; p is the maintenance operation index.

[0069] Step S317. Calculate the product of the number of unmaintained times within the planned time period for each railway line within the planned time period and the preset third unit penalty cost to obtain a plurality of fourth values;

[0070] Step S318. Sum all the fourth values ​​to construct a penalty cost function for not implementing maintenance within the planned time;

[0071] Specifically, the penalty cost function for not implementing maintenance within the planned time is as follows:

[0072]

[0073] Among them, C p '(i,j) is the penalty cost of maintenance operation p in interval (i,j) not being scheduled within the planning period; pen"

[0074] is the penalty cost of maintenance operation p not being scheduled within the planned period; x p (i,j,s) is whether maintenance operation p is scheduled to be performed within the interval (i,j) on the sth day; s is the time index; p is the maintenance operation index.

[0075] x p (i,j,s) is a 0-1 variable, which takes the value of 1 if the maintenance operation p is scheduled to be performed within the interval (i,j) on the sth day, and 0 otherwise.

[0076] Step S319. Construct a first objective function based on the time cost function of equipment maintenance, the penalty cost function for exceeding the upper limit of maintenance time, the penalty cost function for super-elastic maintenance cycle, and the penalty cost function for not implementing maintenance within the planned time;

[0077] Specifically, the penalty function for untimely job scheduling is as follows:

[0078]

[0079] in, is the penalty cost of executing the maintenance operation p in the interval (i, j) within the planning period but exceeding the upper limit of the predicted maintenance time; is the penalty cost of the maintenance operation p in the interval (i, j) being executed within the planning period but with a super-elastic maintenance cycle; C p '(i,j) represents the penalty cost of maintenance operation p in interval (i,j) not being scheduled in the planning period; x p (i,j,s) is whether the maintenance operation p is scheduled to be carried out within the interval (i,j) on the sth day; is a set of maintenance operations based on the predicted value of equipment status; is the maintenance operation set based on the flexible maintenance cycle; 1 For the corresponding equipment construction and maintenance work determined by the flexible maintenance cycle; 2 is the corresponding equipment construction and maintenance work determined by the equipment status prediction value; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line;

[0080] s is the time index; T is the planned time period; p is the maintenance operation index;

[0081] x p (i,j,s) is a 0-1 variable, which takes the value of 1 if the maintenance operation p is scheduled to be performed within the interval (i,j) on the sth day, and 0 otherwise.

[0082] The first objective function is formula (9):

[0083] minZ1=C p (i,j,s)+C t (i,j,s) (9)

[0084] Among them, Z1 is the first objective function; C t (i, j, s) is the cost function of equipment maintenance; C p (i,j,s) is the penalty function for untimely job scheduling.

[0085] Step S32. constructing a second objective function based on the departure time of the freight train and the arrival time of the freight train;

[0086] Specifically, according to the information such as the number, type, stop plan, etc. of freight trains per day in the planning period and the existing passenger train timetable, the total travel time function of freight trains, i.e., the second objective function, is constructed as follows:

[0087]

[0088] Among them, Z2 is the second objective function; a f (j,D f ,s) is the time when train f arrives at the terminal on day s; d f (O f ,j,s) is the departure time of train f from the origin station on day s; F is the train set; f is the train index; D f is the terminal station; f is the departure station; s is the time index; T is the planned time period.

[0089] Step S33. Construct multiple constraint functions based on railway facility and equipment information and train operation information, and any basic data corresponds to at least one constraint function;

[0090] Specifically, step S33 specifically includes step S331, step S332, step S333, step S334, step S335, step S336 and step S337:

[0091] Step S331. Construct a train time constraint function based on the departure time, arrival time and stop time of all trains in the planning time period;

[0092] Specifically, all trains include freight trains, passenger trains and virtual trains. The virtual trains are used to represent the dynamic skylights, and there are differences in the constraint functions corresponding to different trains.

[0093] Specifically, step S331 specifically includes step S3311, step S3312 and step S3313:

[0094] Step S3311. Construct a time constraint function for a freight train based on the earliest departure time, the latest departure time, the actual departure time, the actual arrival time, the actual stop time, the minimum stop time and the pure running time of the freight train;

[0095] Specifically, the departure time of the daily freight trains in the planning period must be within the earliest and latest departure time windows specified on the day, and the train stop time must meet the minimum stop time requirement. The actual running time of the train in the section must not be less than the specified minimum section running time. The corresponding constraint functions are as follows:

[0096]

[0097]

[0098]

[0099]

[0100]

[0101] Among them, ts f (O f ,j,s) is the earliest departure time of train f at the departure station on day s; te f (O f ,j,s) is the latest departure time of train f at the departure station on day s; d f (O f ,j,s) is the departure time of train f from the originating station on day s; a f (i,j,s) is the time when train f arrives at station j in the interval (i,j) on day s; d f (i,j,s) is the departure time of train f from station i in the interval (i,j) on day s; w f (j,s) is the stop time of train f at station j on day s; is the minimum stop time of train f at station j on day s; y f (i,s) is the stop identification variable of train f at station i on day s; y f (j,s) is the stop identification variable of train f at station j on day s; FT f (i, j, s) is the pure running time of train f in the interval (i, j) on the sth day; M is a real number with a large value; DT is the additional start time of the train; AT is the additional stop time of the train; F ft is the set of freight trains; D is the set of stations on the railway line; i, j are station indexes; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period.

[0102] y f (j,s) is a 0-1 variable. If train f stops at station j for a time w f (j,s)>0, it means that train f has a stop demand at station j, then y f (j,s) takes the value of 1, otherwise it is 0; y f (i,s) is a 0-1 variable. If train f has a stop requirement at station i, then y f (i,s) takes the value of 1, otherwise it is 0.

[0103] Step S3312. Constructing a passenger train time constraint function based on the set departure time and the set arrival time of the passenger train;

[0104] Specifically, in order to meet the passenger travel needs, passenger trains have a higher priority when compiling train operation diagrams. Therefore, the present invention considers that the arrival and departure times of passenger trains at each station are arranged according to the arrival and departure times of the existing timetable, and tries not to change them to avoid affecting the passenger service quality. The time constraint function of the passenger train is as follows:

[0105]

[0106]

[0107] Among them, a f (i,j,s) is the time when train f arrives at station j in the interval (i,j) on day s; d f (i,j,s) is the departure time of train f from station i in the interval (i,j) on day s; A f (i, j) is the train arrival time in the existing passenger train timetable; D f (i, j) is the departure time of the train in the existing passenger train timetable; F pt is the set of passenger trains; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period.

[0108] Step S3313. Construct a virtual train time constraint function based on the actual start time, actual end time, minimum opening time, earliest start time and latest end time of the dynamic skylight;

[0109] Specifically, the maintenance dynamic skylight is regarded as a virtual train. Therefore, the departure time and arrival time of the virtual train from the station in the section are equal to the start time and end time of the maintenance dynamic skylight in the section. Considering that the maintenance dynamic skylight is usually opened during the day, the opening start time and end time must be within the specified time range, and the total duration cannot be less than the specified minimum skylight opening duration requirement. The virtual train time constraint function is as follows:

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] Among them, a f (i,j,s) is the time when train f arrives at station j in the interval (i,j) on day s; d f (i,j,s) is the departure time of train f from station i in interval (i,j) on day s; t start (i, j, s) is the start time of dynamic skylight maintenance; t end (i, j, s) is the end time of the maintenance dynamic skylight; MOT is the minimum opening time of the maintenance dynamic skylight; MOTs is the earliest start time of the maintenance dynamic skylight; MOT e The latest end time for dynamic skylight maintenance; F win is a set of virtual trains; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period.

[0116] Step S332. Construct a train sequence constraint function based on the departure sequence variables and arrival sequence variables of all trains in the planning time period;

[0117] Specifically, since trains cannot overtake each other in a section, the train section sequence relationship variable is used to clarify the departure and arrival order of any two trains in the same direction in the section to avoid overtaking in the section and causing safety accidents. The train sequence constraint function is as follows:

[0118]

[0119]

[0120]

[0121] in, Whether train f leaves the station before train f' on day s; Is the train f on day s arrive at the station before f'? Whether train f' leaves the station before f on day s; is whether train f' arrives at the station before f on day s; F ft Assemble for freight train; F pt Assemble for passenger trains; F win is a set of virtual trains; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period;

[0122] is a 0-1 variable, which takes the value 1 if train f leaves the station before f' on day s, and 0 otherwise; is a 0-1 variable, which takes the value of 1 if the train f arrives at the station before f' on the sth day, otherwise it takes the value of 0; is a 0-1 variable, which takes the value of 1 if the train f' leaves the station before f on the sth day, otherwise it takes the value of 0; It is a 0-1 variable, which takes the value of 1 if train f' arrives at the station before f on day s, and 0 otherwise.

[0123] Step S333. Construct a train time interval constraint function based on the arrival time interval, departure time interval and arrival / departure time interval of any two trains in the same travel direction within the planning time period;

[0124] Specifically, for actual trains, i.e., freight trains and passenger trains, in order to ensure driving safety, it is necessary to constrain the departure intervals of different trains in the same direction and the arrival intervals of different trains in the same direction. The train time interval constraint functions are as follows:

[0125]

[0126]

[0127]

[0128]

[0129]

[0130]

[0131] Among them, d f' (i,j,s) is the departure time of train f' from station i in the interval (i,j) on day s; d f (i,j,s) is the departure time of train f from station i in the interval (i,j) on day s; a f (i,j,s) is the time when train f arrives at station j in the interval (i,j) on day s; a f' (i,j,s) is the time when train f' arrives at station j in the interval (i,j) on day s; Whether train f leaves the station before train f' on day s; h is whether train f arrives at the station before train f' on day s; aa h is the time interval between the arrival of two trains f and f' in the same direction in the interval (i, j); dd is the departure time interval of two trains f,f' in the same direction in the interval (i,j); h ad is the time interval between the arrival and departure of two trains f and f' in the same direction in the interval (i, j); M is a real number with a large value; F ft Assemble for freight train; F ptAssemble for passenger trains; F win is a set of virtual trains; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period.

[0132] Considering that at any time, the number of arrival and departure tracks occupied by trains at a station cannot exceed the arrival and departure track capacity of the station, if two trains f and f' stop at the station at the same time and occupy different arrival and departure tracks, it is considered that f and f' "meet" at the station. Therefore, the arrival and departure track capacity restriction can be converted into the number restriction of the encounter relationship between trains. The constraint functions are as follows:

[0133]

[0134]

[0135]

[0136]

[0137]

[0138] in, is whether the two trains f and f' stop at station j at the same time; R y is the number of available arrival and departure lines at station j; is whether train f departs from station j earlier than train f'; is whether train f' departs from station j earlier than train f; a f (i,j,s) is the time when train f arrives at station j in the interval (i,j) on day s; a f' (i,j,s) is the time when train f' arrives at station j in the interval (i,j) on day s; d f' (j,k,s) is the departure time of train f' from station i in the interval (j,k) on day s; d f (j,k,s) is the departure time of train f from station i in the interval (j,k) on the sth day; M is a real number with a large value; (j,k), (i,j) are the time interval indexes of the flexible maintenance cycle; D is the set of stations on the railway line; i,j are station indexes; F is the set of trains; f, f' are train indexes.

[0139] is a 0-1 variable. When two trains f and f' stop at station j at the same time, they occupy different arrival and departure lines. Otherwise, the value is 0; is a 0-1 variable. If train f arrives at station y earlier than train f' departs from j, then Otherwise, the value is 0; is a 0-1 variable. If train f' arrives at station y earlier than train f departs from j, then Otherwise the value is 0.

[0140] Step S334. Construct a maintenance operation time constraint function based on the construction operation time and maintenance operation time within the planned time period;

[0141] Specifically, in order to avoid the situation of opening a second skylight, the start and end time of the maintenance work scheduled on a certain day can only be within the maintenance skylight of the corresponding day and interval, and the start and end time of the work on other days and intervals should be 0. The maintenance work time constraint function is as follows: (37) to (41):

[0142]

[0143]

[0144]

[0145]

[0146]

[0147] Among them, t start (i, j, s) is the start time of dynamic skylight maintenance; t end (i, j, s) is the end time of the dynamic skylight maintenance; x p (i,j,s) is whether the maintenance operation p is scheduled to be carried out within the interval (i,j) on the sth day; d p (i,j,s) is the start time of maintenance operation p on day s within the interval (i,j); a p (i,j,s) is the end time of maintenance operation p on day s within the interval (i,j); MT p (i, j, s) is the time required for maintenance operation p in the interval (i, j) on the sth day; M is a real number with a large value; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period; P r is the set of construction operations within the planning period; P k is the set of maintenance operations within the planning period; p is the maintenance operation index;

[0148] x p (i,j,s) is a 0-1 variable. If the maintenance operation p is scheduled to be performed within the interval (i,j) on the sth day, the value is 1, otherwise it is 0.

[0149] Step S335. Based on the compatible and mutually exclusive relationships among all maintenance operations within the planned time period, a mutual constraint function of the maintenance operations is constructed. The compatible relationship indicates that multiple maintenance operations can be performed at the same time on the same railway line, and the mutually exclusive relationship indicates that multiple maintenance operations cannot be performed at the same time on the same railway line;

[0150] Specifically, when arranging any two mutually exclusive operations in the same interval, in order to ensure the safety and standardization of the maintenance operation process, it should be ensured that the execution time of the two operations cannot be repeated, and the end time of the operation started first must be earlier than the end time of the operation started later. The constraint functions are as follows:

[0151]

[0152]

[0153] Among them, d p (i,j,s) is the start time of maintenance operation p on day s within the interval (i,j); a p (i,j,s) is the end time of maintenance operation p on day s within the interval (i,j); d p' (i,j,s) is the start time of the maintenance operation p' on the sth day within the interval (i,j); a p' (i,j,s) is the end time of the maintenance operation p' on the sth day within the interval (i,j); is whether maintenance operation p' should be started after maintenance operation p is completed; M is a real number with a large value; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period; P r is the set of construction operations within the planning period; P k is the set of maintenance operations within the planning period; p, p' are the maintenance operation indexes; M p is the set of maintenance operations that cannot be performed simultaneously with maintenance operation p;

[0154] is a 0-1 variable. If operation p' starts construction after operation p ends, then The value is 1, otherwise The value is 0.

[0155] Due to the limitation of human resources and mechanical equipment, the total number of operations performed at the same time in the interval should not exceed the specified maximum number requirement. Therefore, the same method as the capacity constraint of the arrival and departure line is adopted to transform the number limit problem of the operations being performed at the same time into an encounter problem. The constraint functions are as follows: (44) to (48):

[0156]

[0157]

[0158]

[0159]

[0160]

[0161] in, is whether two compatible maintenance operations p and p' are implemented simultaneously in the interval (i, j); MS is the maximum number of maintenance operations performed at the same time in the interval (i, j); d p (i,j,s) is the start time of maintenance operation p on day s within the interval (i,j); a p (i,j,s) is the end time of maintenance operation p on day s within the interval (i,j); d p' (i,j,s) is the start time of the maintenance operation p' on the sth day within the interval (i,j); a p' (i,j,s) is the end time of the maintenance operation p' on the sth day within the interval (i,j); Whether the maintenance operation p' should be started after the maintenance operation p is completed; is whether maintenance operation p should be started after maintenance operation p' is completed; M is a real number with a large value; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planned time period; P r is the set of construction operations within the planning period; P k is the set of maintenance operations within the planning period; p, p' is the maintenance operation index; M p is the set of maintenance operations that cannot be performed simultaneously with maintenance operation p; P is the set of main maintenance operations for the railway line.

[0162] is a 0-1 variable. When two compatible maintenance operations p and p' are implemented simultaneously in the interval (i, j), The value is 1, otherwise the value is 0.

[0163] Considering that a maintenance operation is performed at most once in the planning period, in order to ensure that the facilities and equipment are in good condition during driving, the maintenance operation usually needs to be arranged in time. However, when the traffic volume in the planning period is large, a small number of operations are allowed to be postponed to the next planning period, but a certain penalty must be given. The corresponding constraint function is as follows (49):

[0164]

[0165] Among them, xp (i, j, s) is whether maintenance operation p is scheduled to be performed within the interval (i, j) on the sth day; s is the time index; T is the planned time period; P k is the set of maintenance operations within the planning period; p is the maintenance operation index; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; s is the time index; T is the planning time period.

[0166] Step S336. Construct a maintenance operation continuity constraint function based on the maintenance operation start time, end time and operation duration;

[0167] Specifically, to ensure safety, construction work is usually carried out continuously for a specified number of days within a period of time. In order to ensure driving safety and not affect the work arrangement of the next planning period, the end time of the construction work must be within the planning period. The maintenance work continuity constraint function is as follows:

[0168]

[0169]

[0170]

[0171]

[0172]

[0173] Among them, g p is the start time of maintenance operation p; r p (i, j, s) is whether the maintenance operation p has been completed on the sth day; e p (i, j, s) is whether maintenance operation p has been implemented on day s; e p (i,j,s-1) is whether maintenance operation p has been implemented on day s-1; e p (i,j,1) is whether maintenance operation p has been implemented on the first day; r p (i,j,1) indicates whether the maintenance operation p has been completed on the first day; r p (i, j, s-1) is whether the maintenance operation p has been completed on the s-1 day; x p (i,j,s) is whether the maintenance operation p is scheduled to be carried out within the interval (i,j) on the sth day; D p is the number of days of maintenance operation p; s is the time index; T is the planned time period; P ris the set of construction operations within the planning period; p is the maintenance operation index; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line.

[0174] r p (i,j,s) is a 0-1 variable. If job p has finished executing on day s, then r p (i,j,s) takes the value of 1, otherwise it is 0; e p (i,j,s) is a 0-1 variable. If task p has been implemented on day s, then r p (i,j,s) takes the value of 1, otherwise it is 0.

[0175] Step S337. Based on the number of maintenance operations and the maximum number of maintenance operations, construct a maintenance operation quantity constraint function;

[0176] Specifically, the constraint function for the number of construction operations to be performed simultaneously when constructing a line is as follows (55):

[0177]

[0178] Among them, MN is the maximum number of maintenance operations in all intervals on the same day; x p (i, j, s) is whether maintenance operation p is scheduled to be performed within the interval (i, j) on the sth day; s is the time index; T is the planned time period; P r is the set of construction operations within the planning period; p is the maintenance operation index; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line.

[0179] Step S34. Constructing a multi-objective programming model based on the first objective function, the second objective function and the plurality of constraint functions;

[0180] Specifically, a multi-objective programming model is constructed based on all objective functions and constraint functions.

[0181] Step S40. Based on the constraint functions preset in the multi-objective programming model, the basic data is adjusted to obtain target data, where the target data is data that satisfies each constraint function in the multi-objective programming model;

[0182] Step S50: adjusting the dynamic sunroof accordingly based on the target data;

[0183] Specifically, in order to solve the railway dynamic skylight scheme that satisfies the resource conflict constraints between trains and the number of arrival and departure lines, the normalization factor z is introduced 1,min 、z 1,max 、z 2,min and z 2,max To unify the order of magnitude of the two objectives, the solution model is:

[0184]

[0185] Among them, z 1,min is the minimum value of the first objective function; z 1,max is the maximum value of the first objective function; z 2,min is the minimum value of the second objective function; z 2,max is the maximum value of the second objective function;

[0186] The specific steps to solve the model are:

[0187] S1. Linearize the nonlinear constraint functions (4), (6), (7) and objective function (8) in the model.

[0188] S2. The complex constraints (37) and (38) in the model are relaxed into the objective function by multiplying them with Lagrange multipliers to obtain a relaxed problem. The relaxed objective function is shown in formula (56). The relaxed problem is decomposed into several independent sub-problems of coordinated optimization of train operation plan and maintenance dynamic time window (SP1) and construction and maintenance plan compilation problem (SP2). Formula (56) is as follows:

[0189]

[0190] Among them, a f (j,D f ,s) is the time when train f arrives at the terminal on day s; d f (O f ,j,s) is the departure time of train f from the originating station on day s; C t (i, j, s) is the cost function of equipment maintenance; is the penalty cost of executing the maintenance operation p in the interval (i, j) within the planning period but exceeding the upper limit of the predicted maintenance time; is the penalty cost of the maintenance operation p in the interval (i, j) being executed within the planning period but with a super-elastic maintenance cycle; C p '(i,j) represents the penalty cost of maintenance operation p in interval (i,j) not being scheduled in the planning period; x p (i,j,s) is whether the maintenance operation p is scheduled to be carried out within the interval (i,j) on the sth day; is the Lagrange multiplier; t start (i, j, s) is the start time of dynamic skylight maintenance; t end (i, j, s) is the end time of the dynamic skylight maintenance; d p (i,j,s) is the start time of maintenance operation p on day s within the interval (i,j); a p(i,j,s) is the end time of maintenance operation p on day s within the interval (i,j); is a set of maintenance operations based on the predicted value of equipment status; A collection of maintenance operations based on a flexible maintenance cycle; is a set of construction operations based on the predicted value of equipment status; is a set of construction operations based on a flexible maintenance cycle; s is a time index; T is a planning time period; p is a maintenance operation index; (i, j) is a time interval index of a flexible maintenance cycle; E is a set of intervals between any adjacent stations on a railway line; P is a set of major maintenance operations on a railway line; F is a set of trains; f is a train index; M is a real number with a large value; ω1' is the first weight coefficient; ω2' is the second weight coefficient;

[0191] is the sub-problem of coordinated optimization of train operation plan and maintenance dynamic time window; Z(Λ p ) is the issue of preparing construction maintenance plans.

[0192] The sub-problem (SP1) of coordinated optimization of train operation plan and maintenance dynamic time window is as follows:

[0193]

[0194] Among them, a f (j,D f ,s) is the time when train f arrives at the terminal on day s; d f (O f ,j,s) is the departure time of train f from the origin station on day s; is the Lagrange multiplier; t start (i, j, s) is the start time of dynamic skylight maintenance; t end (i,j,s) is the end time of the dynamic maintenance window; ω1' is the first weight coefficient; p is the maintenance operation index; (i,j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; P is the set of major maintenance operations on the railway line; F is the train set; f is the train index.

[0195] The construction maintenance planning problem (SP2) is as follows:

[0196]

[0197] Among them, C t (i, j, s) is the cost function of equipment maintenance; is the penalty cost of executing the maintenance operation p in the interval (i, j) within the planning period but exceeding the upper limit of the predicted maintenance time; is the penalty cost of the maintenance operation p in the interval (i, j) being executed within the planning period but with a super-elastic maintenance cycle; C p '(i,j) represents the penalty cost of maintenance operation p in interval (i,j) not being scheduled in the planning period; x p (i,j,s) is whether the maintenance operation p is scheduled to be carried out within the interval (i,j) on the sth day; is the Lagrange multiplier; d p (i,j,s) is the start time of maintenance operation p on day s within the interval (i,j); a p (i, j, s) is the end time of the maintenance operation p on the sth day in the interval (i, j); M is a real number with a large value; ω2' is the second weight coefficient; is a set of maintenance operations based on the predicted value of equipment status; A collection of maintenance operations based on a flexible maintenance cycle; is a set of construction operations based on the predicted value of equipment status; is the set of construction operations based on the flexible maintenance cycle; p is the maintenance operation index; (i, j) is the time interval index of the flexible maintenance cycle; E is the set of intervals between any adjacent stations on the railway line; P is the set of major maintenance operations for the railway line; F is the set of trains; and f is the train index.

[0198] S3. Set the initial iteration number k = 0, obtain the existing train operation plan and construction and maintenance operation requirements of conventional railways, and the initial upper bound UB 0 is a larger value related to the current traffic demand, and the initial lower bound LB 0 =0, initial normalization factor z 1,min ,z 2,min ,z 1,max ,z 2,max , the initial values ​​of the step size parameter α and the number of unimproved lower bounds are set to 1 and 0, respectively.

[0199] S4. Use the GUROBI solver to directly solve the relaxed subproblems SP1 and SP2 and obtain the lower bound LB of the original problem k , output the start and end time of the dynamic maintenance time window (virtual train) of each section every day during the planning period and the daily construction and maintenance plan.

[0200] When solving each sub-problem, we do not first consider the huge number of arrival and departure line capacity constraints and the number constraints of compatible operations that must be implemented simultaneously. Instead, we use the designed algorithm to determine during iteration whether the currently obtained feasible solution violates the above resource limitation constraints, and then gradually add the above constraints.

[0201] Taking the arrival and departure events of a group of trains at the station as an example, for the SP1 subproblem, we first ignore the number of arrival and departure line constraints to generate a constraint subset, and then perform integer programming branch and bound solution under only the constraint subset. In the iterative process, we identify the stop train at station j at the arrival time of each train according to the feasible solution information of the current node. For the train f1 arriving at station j at If there is another train f, And the train leaves the station at time j This means that two trains occupy the arrival and departure tracks of station j at the same time. When the number of trains occupying the arrival and departure tracks of station j at the same time exceeds the number of available arrival and departure tracks of the station, record the train set F x If F is detected x If the related constraints (32) to (36) are not in the constraint pool, they are added to the constraint pool in the form of Lazy Constraints for the subsequent branch and bound solution process.

[0202] S5. Based on the Lagrange multiplier, the feasible solution corresponding to the relaxation problem is constructed. Taking into account the continuous operation attribute of the construction project, when canceling and adding operations, the construction part is not adjusted. After adjusting the operations in all intervals, the penalty value attached to the unscheduled operations is loaded into the objective function.

[0203] S51. Determine the violation of the relaxation constraint and determine the maintenance operation duration C for each interval. t Whether (i, j, s) exceeds the dynamic time window length, if so, go to step S511; otherwise, go to step S52.

[0204] S511. Use the strategy shown in Algorithm 1 to cancel some maintenance work at the end of each interval until the maintenance work duration satisfies the constraints (37) and (38), and put the canceled work in the form of [work number, work time, latest time of work scheduling, work scheduling mark variable (the value is 0 at this time)] into the set cancell_set(i,j) of the interval (i,j) and then go to step S512.

[0205] Algorithm 1: Maintenance operation adjustment strategy

[0206] Step 1: Assume that solving subproblem SP2 obtains the set of maintenance tasks {p1,…,p2,…,p n}, taking the maintenance interval and the corresponding maintenance operation set, and the dynamic time window opening period of the interval as input;

[0207] Step 2: Critical Time in, is the buffer time, t start (i,j,s) is the start time of dynamic skylight maintenance, tend (i, j, s) is the end time of the dynamic skylight maintenance, and the initialization operation index r = 1;

[0208] Step 3: If the critical time ext≤0, it means that the interval maintenance plan does not violate constraints (5)~(28), and the current adjustment ends; otherwise, go to step 3.1;

[0209] Step 3.1: If the end time of the rth maintenance operation Or the start time of the rth maintenance operation If the critical time ext is exceeded, the rth maintenance operation will be canceled and the values ​​of the relevant decision variables will be updated: the rth maintenance operation scheduling parameters The end time of the rth maintenance operation The start time of the rth maintenance operation And go to step 3.2, otherwise go to step 4;

[0210] Step 3.2: Cancel the job to That is, put [job number, job time, latest job schedule time, job schedule flag variable (value 0 at this time)] into the set cancel_set(i,j), and go to step 4;

[0211] Step 4: If the job index number r is less than the job number n, set the job index r=r+1 and go to step 3;

[0212] Step 5: Output the adjusted maintenance plan and the set cancel_set(i,j).

[0213] S512. Update the total maintenance operation time C of each section t (i, j, s), if the relaxation constraint violation judgment is completed for each interval of each day within the planning period, go to step 52; otherwise, go to step S51.

[0214] S52. Priority sorting of maintenance jobs to be scheduled: sort the jobs to be scheduled in the set cancell_set(i,j) in ascending order of the latest job scheduling time, where the latest job scheduling time is a known constant, and go to S53.

[0215] S53. Adjust the scheduled maintenance work: Determine the maintenance work duration C for each interval (i, j) t Is (i, j, s) less than the dynamic time window length? If so, go to S531; otherwise, go to S54.

[0216] S531. Use the strategy shown in Algorithm 2 to arrange the scheduled jobs in order at the end of each interval, ensuring that the increased maintenance job duration does not exceed the dynamic time window duration and the maintenance job duration C. t The difference between (i, j, s) and the set cancell_set(i, j) is updated, and then the process goes to S532.

[0217] Algorithm 2: Maintenance job rescheduling strategy

[0218] Step 1: Enter the maintenance interval and the corresponding final maintenance operation, the dynamic time window opening period of the interval and the set cancel_set(i,j), and the final operation end implementation time

[0219] Step 2: Remaining time rmt = (t end (i,j,s)-t start (i,j,s))-C t (i,j,s), where C t (i,j,s) is the maintenance operation duration, t start (i,j,s) is the start time of dynamic skylight maintenance, t end (i, j, s) is the end time of the dynamic skylight maintenance, the initialization operation index d = 1, and the operation quantity sz = 0;

[0220] Step 3: If the remaining time rmt = 0, it means that there is no remaining free time in the time window for scheduling the jobs in the set. If the job scheduling flag variables in the set cancel_set(i,j) are all 1, it means that there are no jobs to be scheduled. If any of the above situations occurs, the current adjustment ends. Otherwise, go to step 3.1.

[0221] Step 3.1: If the operation time of the dth maintenance operation in the set cancel_set(i,j) is less than or equal to the remaining time rmt and the value of the operation scheduling flag variable is 0, then schedule the operation to the interval (i,j) of the sth day and update the value of the relevant decision variables: the dth maintenance operation scheduling parameter The start time of the dth maintenance operation The end time of the dth maintenance operation in, is the operation time of the dth maintenance operation, and go to step 3.2; otherwise, go to step 4;

[0222] Step 3.2: Set job p in the cancel_set(i,j) d The corresponding job scheduling flag variable is set to 1, the job quantity sz = 1, and go to step 3.3;

[0223] Step 3.3: Check whether there is the d'th job in the set cancel_set(i,j) in, is the maintenance operation set and the corresponding operation time If it is less than the remaining time rmt and the job scheduling flag variable is 0, go to step 3.4 if it exists; otherwise go to step 4;

[0224] Step 3.4: Set the d'th job p d' Schedule the interval (i, j) to the sth day and update the values ​​of the relevant decision variables: the d'th job scheduling parameter The start time of the d'th job End time of the d'th job in, is the job time of job d', and the job p in the set cancel_set(i,j) is d' The corresponding job scheduling flag variable is set to 1, the job quantity sz is set to 2, and the process goes to step 4;

[0225] Step 4: If the number of operations sz = 2, update the end time of the last operation in, is the end time of the dth maintenance operation, is the end time of the d'th job, and the remaining time in, is the operation time of the dth maintenance operation, is the operation time of the d'th operation;

[0226] If the number of jobs sz = 1, update the end time of the last job in, Update the remaining time for the end time of the d'th job in, is the operation time of the dth maintenance operation; if the operation index d is less than the number of operations n, then set the operation index d=d+1 and go to step 3;

[0227] Step 5: Output the adjusted maintenance plan.

[0228] S532. Update the total maintenance time C of each section t (i,j,s), if the adjustment of the to-be-scheduled maintenance work has been completed in each section of each day within the planning period or the to-be-scheduled work has been fully arranged in each section, that is, the job arrangement mark variables in the set cancell_set(i,j) are all 1, then go to S54; if the adjustment of the to-be-scheduled maintenance work has not been completed in all sections, then go to S53.

[0229] S54. Align the maintenance plan with the dynamic time window: Shift the maintenance plan of each interval as a whole so that the start time of the first operation in each interval is consistent with the start time of the maintenance dynamic time window, and update the start and end times of the operation.

[0230] S55. Update upper bound solution: Calculate the current feasible target value UB and update the best upper bound UB so far k =min{UB,UB k}.

[0231] S6. Determine whether the algorithm termination condition is met: ① Relative error of upper and lower bounds Among them, UB k is the best upper bound; LB k is the best lower bound; within the given allowable error value π*; ② the number of iterations k reaches the set maximum number of iterations. If the termination condition is met, the algorithm ends and the current adjusted maintenance plan and train operation plan are output, otherwise go to S7.

[0232] S7. Determine whether the lower bound is not improved. If the lower bound is not improved, then LB k -ex_LB≤0, where LB k is the best lower bound, ex_LB is the best lower bound in history, then go to S39, otherwise set the best lower bound in history ex_LB=LB k , the number of unimproved times is reset to zero and go to S9.

[0233] S8. Set the number of unimproved times time=time+1. If the number of unimproved times time≥10, the step length parameter is halved, the number of unimproved times is reset to zero, and go to S9.

[0234] S9. Use the subgradient algorithm to update the Lagrange multiplier. The specific formula is as follows, and return to S4;

[0235]

[0236]

[0237] in,; is the Lagrange multiplier; is the Lagrange multiplier The associated sub-gradient components; is the Lagrange multiplier The relevant sub-gradient components; UB is the upper bound; LB is the lower bound; α, γ, ξ are the update parameters;

[0238] The difference between the right and left sides of the corresponding relaxed constraint function (37). Similarly, is and is related to the relaxed constraint function (38).

[0239] Embodiment 2:

[0240] like Figure 2 As shown, this embodiment provides a railway skylight solution optimization device, the device comprising:

[0241] An acquisition unit 10 is used to acquire railway equipment information and train operation information and determine a plurality of basic data, the railway equipment information includes railway equipment status prediction data and equipment fixed maintenance cycle, and the train operation information includes a transportation plan and a maintenance plan;

[0242] A division unit 20, for dividing the preset railway maintenance time into a plurality of skylights to obtain a plurality of dynamic skylights;

[0243] A first construction unit 30 is used to construct a collaborative optimization model based on multiple dynamic skylights and multiple basic data to obtain a multi-objective planning model, where the multi-objective planning model includes multiple objective functions;

[0244] A first adjustment unit 40 is used to adjust the basic data based on the constraint functions preset in the multi-objective programming model to obtain target data, where the target data is data that satisfies each constraint function in the multi-objective programming model;

[0245] The second adjustment unit 50 is used to make corresponding adjustments to the dynamic sunroof based on the target data.

[0246] In a specific embodiment disclosed in the present application, the first building unit 30 includes:

[0247] The second construction unit is used to construct a first objective function based on the time cost of equipment maintenance and the penalty cost of equipment maintenance, wherein the penalty cost of equipment maintenance is used to represent the additional cost of untimely equipment maintenance operations;

[0248] A third construction unit is used to construct a second objective function based on the departure time of the freight train and the arrival time of the freight train;

[0249] A fourth construction unit is used to construct a plurality of constraint functions based on railway facility and equipment information and train operation information, and any basic data corresponds to at least one constraint function;

[0250] The fifth construction unit is used to construct a multi-objective programming model based on the first objective function, the second objective function and the plurality of constraint functions.

[0251] In a specific embodiment disclosed in the present application, the second building block includes:

[0252] A first calculation unit is used to calculate the maintenance operation duration of each railway line within the planned time period to obtain a plurality of first values;

[0253] A first summing unit, used for summing all first values ​​to construct a time cost function for equipment maintenance;

[0254] A second calculation unit is used to calculate the product of the number of times the upper limit of the overhaul time of each railway line in the planning time period and the preset first unit penalty cost to obtain multiple second values;

[0255] A second summing unit is used to sum all the second values ​​to construct a penalty cost function for exceeding the upper limit of the overhaul time;

[0256] A third calculation unit is used to calculate the product of the number of super-elastic maintenance cycles of each railway line within the planning time period and the preset second unit penalty cost to obtain multiple third values;

[0257] A third summing unit is used to sum all third values ​​to construct a penalty cost function of a superelastic maintenance cycle;

[0258] A fourth calculation unit is used to calculate the product of the number of times that maintenance is not implemented within the planning time of each railway line within the planning time period and a preset third unit penalty cost to obtain a plurality of fourth values;

[0259] A fourth summing unit is used to sum all fourth values ​​to construct a penalty cost function for not implementing maintenance within the planning time;

[0260] The sixth construction unit is used to construct the first objective function based on the time cost function of equipment maintenance, the penalty cost function of exceeding the upper limit of maintenance time, the penalty cost function of the super-elastic maintenance cycle and the penalty cost function of not implementing maintenance within the planned time.

[0261] In a specific embodiment disclosed in the present application, the fourth building block includes:

[0262] A seventh construction unit is used to construct a train time constraint function based on the departure time, arrival time and stop time of all trains in the planning time period;

[0263] An eighth construction unit, used to construct a train sequence constraint function based on the departure sequence variables and arrival sequence variables of all trains in the planning time period;

[0264] The ninth construction unit is used to construct a train time interval constraint function based on the arrival time interval, departure time interval and arrival-departure time interval of any two trains in the same driving direction within the planning time period.

[0265] In a specific embodiment disclosed in the present application, the fourth building block further includes:

[0266] A tenth construction unit is used to construct a maintenance operation time constraint function based on the construction operation time and the maintenance operation time within the planning time period;

[0267] An eleventh construction unit is used to construct a mutual constraint function of maintenance operations based on the compatible relationship and mutually exclusive relationship between all maintenance operations in the planning time period, wherein the compatible relationship indicates that multiple maintenance operations can be performed at the same time on the same railway line, and the mutually exclusive relationship indicates that multiple maintenance operations cannot be performed at the same time on the same railway line;

[0268] A twelfth construction unit is used to construct a maintenance operation continuous constraint function based on the maintenance operation start time, end time and continuous operation time;

[0269] The thirteenth construction unit is used to construct a maintenance operation quantity constraint function based on the maintenance operation quantity and the maximum maintenance operation quantity.

[0270] In a specific embodiment disclosed in the present application, the seventh building block includes:

[0271] A fourteenth construction unit is used to construct a time constraint function of a freight train based on the earliest departure time, the latest departure time, the actual departure time, the actual arrival time, the actual stop time, the minimum stop time and the pure running time of the freight train;

[0272] A fifteenth construction unit is used to construct a passenger train time constraint function based on a set departure time and a set arrival time of the passenger train;

[0273] The sixteenth construction unit is used to construct a virtual train time constraint function based on the actual start time, actual end time, minimum opening time, earliest start time and latest end time of the dynamic skylight.

[0274] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0275] Embodiment 3:

[0276] Corresponding to the above method embodiment, this embodiment also provides a railway skylight scheme optimization device, and the railway skylight scheme optimization device described below and the railway skylight scheme optimization method described above can refer to each other.

[0277] Figure 3 FIG. 8 is a block diagram of a railway skylight solution optimization device 800 according to an exemplary embodiment. Figure 3As shown, the railway skylight solution optimization device 800 may include: a processor 801 and a memory 802. The railway skylight solution optimization device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0278] The processor 801 is used to control the overall operation of the railway skylight solution optimization device 800 to complete all or part of the steps in the above-mentioned railway skylight solution optimization method. The memory 802 is used to store various types of data to support the operation of the railway skylight solution optimization device 800, and these data may include, for example, instructions for any application or method operating on the railway skylight solution optimization device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the railway skylight solution optimization device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0279] In an exemplary embodiment, the railway skylight solution optimization device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned railway skylight solution optimization method.

[0280] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned railway skylight solution optimization method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the railway skylight solution optimization device 800 to complete the above-mentioned railway skylight solution optimization method.

[0281] Embodiment 4:

[0282] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the railway skylight solution optimization method described above can refer to each other.

[0283] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the railway skylight solution optimization method of the above method embodiment.

[0284] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0285] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0286] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A railway skylight scheme optimization method, characterized in that: include: Acquire railway equipment information and train operation information and determine a plurality of basic data, wherein the railway equipment information includes railway equipment status prediction data and equipment fixed maintenance cycle, and the train operation information includes transportation plan and maintenance plan; Divide the preset railway maintenance time into multiple skylights to obtain multiple dynamic skylights; Building a collaborative optimization model based on multiple dynamic skylights and multiple basic data to obtain a multi-objective planning model, wherein the multi-objective planning model includes multiple objective functions; Based on the constraint functions preset in the multi-objective programming model, the basic data is adjusted to obtain target data, where the target data is data that satisfies each constraint function in the multi-objective programming model; The dynamic sunroof is adjusted accordingly based on the target data.

2. The railway skylight scheme optimization method according to claim 1 is characterized in that ,Based on multiple dynamic skylights and multiple basic data, a collaborative optimization model is constructed to obtain a multi-objective planning model, which contains multiple objective functions, including: Constructing a first objective function based on the time cost of equipment maintenance and the penalty cost of equipment maintenance, wherein the penalty cost of equipment maintenance is used to represent the additional cost of untimely equipment maintenance operations; constructing a second objective function based on the departure time of the freight train and the arrival time of the freight train; Constructing a plurality of constraint functions based on the railway facility and equipment information and the train operation information, wherein any basic data corresponds to at least one constraint function; The multi-objective programming model is constructed based on the first objective function, the second objective function and a plurality of constraint functions.

3. The railway skylight scheme optimization method according to claim 2 is characterized in that ,Based on the time cost of equipment maintenance and the penalty cost of equipment maintenance, ,the first objective function is constructed, including: Calculating the maintenance operation duration of each railway line within the planned time period to obtain a plurality of first values; Sum all the first values ​​to construct a time cost function for the equipment maintenance; Calculate the product of the number of times the upper limit of the maintenance time of each railway line in the planned time period is exceeded and the preset first unit penalty cost to obtain multiple second values; The sum of all the second values ​​is calculated to construct a penalty cost function for exceeding the upper limit of the overhaul time; Calculating the product of the number of superelastic maintenance cycles of each railway line within the planning time period and the preset second unit penalty cost to obtain multiple third values; All third values ​​are summed up to construct a penalty cost function of the superelastic maintenance cycle; Calculate the product of the number of times maintenance is not performed within the planned time period for each railway line within the planned time period and a preset third unit penalty cost to obtain a plurality of fourth values; All fourth values ​​are summed up to construct a penalty cost function for not implementing maintenance within the planning time; The first objective function is constructed based on the time cost function of the equipment maintenance, the penalty cost function of exceeding the upper limit of the maintenance time, the penalty cost function of the super-elastic maintenance cycle, and the penalty cost function of not implementing maintenance within the planned time.

4. The railway skylight scheme optimization method according to claim 2 is characterized in that , construct multiple constraint functions based on the railway facility equipment information and the train operation information, and any basic data corresponds to at least one constraint function, including: Constructing a train time constraint function based on the departure time, arrival time and stop time of all trains in the planning time period; Constructing a train sequence constraint function based on the departure sequence variables and arrival sequence variables of all trains in the planning time period; A train time interval constraint function is constructed based on the arrival time interval, departure time interval and arrival / departure time interval of any two trains in the same travel direction within the planning time period.

5. A railway skylight solution optimization device, characterized in that: include: An acquisition unit, used to acquire railway equipment information and train operation information and determine a plurality of basic data, wherein the railway equipment information includes railway equipment status prediction data and equipment fixed maintenance cycle, and the train operation information includes a transportation plan and a maintenance plan; A division unit, used for dividing the preset railway maintenance time into a plurality of skylights to obtain a plurality of dynamic skylights; A first construction unit is used to construct a collaborative optimization model based on multiple dynamic skylights and multiple basic data to obtain a multi-objective planning model, wherein the multi-objective planning model includes multiple objective functions; A first adjustment unit, configured to adjust the basic data based on a constraint function preset in the multi-objective programming model to obtain target data, wherein the target data is data satisfying each constraint function in the multi-objective programming model; The second adjustment unit is used to make corresponding adjustments to the dynamic sunroof based on the target data.

6. The railway skylight solution optimization device according to claim 5, characterized in that: The first building block comprises: A second construction unit is used to construct a first objective function based on the time cost of equipment maintenance and the penalty cost of equipment maintenance, wherein the penalty cost of equipment maintenance is used to represent the additional cost of untimely equipment maintenance operations; A third construction unit is used to construct a second objective function based on the departure time of the freight train and the arrival time of the freight train; A fourth construction unit is used to construct a plurality of constraint functions based on the railway facility and equipment information and the train operation information, wherein any basic data corresponds to at least one constraint function; A fifth construction unit is used to construct the multi-objective programming model based on the first objective function, the second objective function and multiple constraint functions.

7. The railway skylight scheme optimization device according to claim 6 is characterized in that: The second building block comprises: A first calculation unit is used to calculate the maintenance operation duration of each railway line within the planned time period to obtain a plurality of first values; A first summing unit, used for summing all first values ​​to construct a time cost function for equipment maintenance; A second calculation unit is used to calculate the product of the number of times the upper limit of the maintenance time of each railway line in the planning time period is exceeded and the preset first unit penalty cost to obtain multiple second values; A second summing unit is used to sum all the second values ​​to construct a penalty cost function for exceeding the upper limit of the overhaul time; A third calculation unit is used to calculate the product of the number of super-elastic maintenance cycles of each railway line within the planning time period and the preset second unit penalty cost to obtain multiple third values; A third summing unit is used to sum all third values ​​to construct a penalty cost function of a superelastic maintenance cycle; A fourth calculation unit, used for calculating the product of the number of times maintenance is not implemented within the planning time of each railway line within the planning time period and a preset third unit penalty cost, to obtain a plurality of fourth values; A fourth summing unit is used to sum all fourth values ​​to construct a penalty cost function for not implementing maintenance within the planning time; The sixth construction unit is used to construct the first objective function based on the time cost function of the equipment maintenance, the penalty cost function of exceeding the upper limit of the maintenance time, the penalty cost function of the super-elastic maintenance cycle and the penalty cost function of not implementing maintenance within the planned time.

8. The railway skylight scheme optimization device according to claim 6, characterized in that: The fourth building block comprises: A seventh construction unit, configured to construct a train time constraint function based on the departure time, arrival time and stop time of all trains in the planned time period; an eighth construction unit, configured to construct a train sequence constraint function based on the departure sequence variables and arrival sequence variables of all trains within the planning time period; The ninth construction unit is used to construct a train time interval constraint function based on the arrival time interval, departure time interval and arrival-departure time interval of any two trains in the same driving direction within the planning time period.

9. A railway skylight solution optimization device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the railway skylight solution optimization method as described in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the railway skylight solution optimization method as claimed in any one of claims 1 to 4 are implemented.

Images