Heuristic interpolation automatic scheduling method for cross correlation of multi-dimensional data

Abstract

The invention discloses a multidimensional data cross-correlation heuristic interpolation automatic scheduling method, which comprises the following steps: S1, screening and selecting job tasks needing to be scheduled according to conditions, the selected job tasks belonging to one or more of the same project; s2, scheduling basic data are prepared, team, ship and task data are obtained, and team window period data and ship window period data obtained through calculation are obtained; s3, transmitting the obtained team, ship and task data as well as team window period data and ship window period data obtained by calculation to an AI scheduling algorithm for calculation until all tasks are calculated, and ending scheduling; and S4, after the scheduling result is obtained, manually adjusting the scheduling result, ending the scheduling, confirming the scheduling result by the user, and generating a scheduling plan. According to the method, the ship scheduling efficiency and quality are improved.

Description

Technical Field

[0001] The invention relates to a multi-dimensional data cross-correlation trial interpolation automatic scheduling method. Background Art

[0002] In the field of marine engineering, the scheduling management of offshore construction vessels is a key task, which is directly related to the progress of the project, cost control and resource utilization. With the development of marine resources and the increase in marine engineering projects, how to efficiently schedule ships has become the focus of the industry. At present, ship scheduling methods are mainly divided into two categories: manual scheduling and automatic scheduling. The manual scheduling method mainly relies on manual experience for ship scheduling, mainly based on the experience and intuition of the dispatcher, and optimizes ship scheduling through a series of rules and guidelines. The automatic scheduling method uses computer technology and optimization algorithms for ship scheduling. The main algorithms are: genetic algorithm, particle swarm optimization algorithm, ant colony algorithm, linear programming and integer programming, etc.

[0003] The existing scheduling methods have the following shortcomings: Manual Scheduling: Inefficiency: The process is cumbersome, time-consuming, and difficult to cope with large-scale ship dispatch.

[0004] Highly subjective: Relies on the dispatcher’s experience and intuition, and is easily influenced by personal preferences and cognitive limitations.

[0005] The degree of optimization is limited: it is difficult to find the global optimal solution, and often only the local optimal or satisfactory solution can be obtained.

[0006] Automatic Scheduling: High algorithm complexity: Some optimization algorithms are computationally complex and take a long time to solve, making it difficult to meet real-time scheduling requirements.

[0007] Poor model adaptability: Existing models are difficult to fully consider the various constraints and dynamic change factors in actual scheduling.

[0008] Highly data-dependent: A large amount of accurate and real-time data support is required, and data quality directly affects scheduling results.

[0009] Failure to consider meteorological factors: Meteorological data plays a very important role in marine engineering, and algorithms that do not consider meteorological factors are incomplete.

[0010] The current scheduling method for offshore construction ships still has certain deficiencies in terms of practicality, optimization and adaptability. Therefore, a heuristic interpolation automatic scheduling method based on cross-correlation of multi-dimensional data is provided. Summary of the invention

[0011] The purpose of the present invention is to overcome the existing defects and provide a multi-dimensional data cross-correlation heuristic interpolation automatic scheduling method, which improves the efficiency and quality of ship scheduling.

[0012] The technical solution to achieve the above purpose is: A multi-dimensional data cross-correlation heuristic interpolation automatic scheduling method, comprising: Step S1, filtering and selecting the job tasks to be scheduled according to the conditions, wherein the selected job tasks belong to one or more of the same project; Step S2, prepare basic scheduling data, obtain team, ship, task data, and calculated team window period data and ship window period data; Step S3, the obtained team, ship, task data, and the calculated team window period data and ship window period data are transmitted to the AI ​​scheduling algorithm for calculation until all tasks are calculated and the scheduling is terminated; Step S4: After the scheduling result comes out, the user manually adjusts the scheduling result to end the scheduling. The user confirms the scheduling result and generates a scheduling plan.

[0013] Preferably, in step S1, the operation task includes all the information of the operation, including but not limited to the task name, priority, task start time, latest completion time, estimated working time, estimated docking time, work team, estimated number of maintenance personnel, whether to return to the ship, whether to dock, selected ship, selected wharf, and destination.

[0014] Preferably, step S2 comprises: Step 21, reading the team data, dock geographic information, meteorological data, and ship data of all tasks from the meteorological information time series database and the business database; Step S22, calculating the working window of the team according to the team data and the existing resource occupancy, and setting the dock geographic information data; Step S23, calculating the ship's weather window period according to the ship's weather threshold and the weather forecast data of the destination.

[0015] Preferably, step S3 comprises: Step S31, assuming that there are x tasks in total, sort the x tasks according to their priorities, and calculate the task sorting information in sequence; Step S32, calculating the schedule according to the ship team library into three situations, including having a ship and a team, having / not having a ship but not having a team, and having a team but not having a ship, and performing interpolation operations and calculations for the three situations respectively; Step S33, if there is a ship and a team, then select a team and a ship for the task with the highest priority, and mark a task scheduling success; Step S34, recording the timeline of the occupied teams and ships in the outbound, working and return time periods, and then calculating the next task; Step S35, if there is / is no ship and no team, then traverse the timeline of the team required for the task and perform a trial interpolation operation without considering the ship; Step S36, if failed, continue to calculate the scheduling information of the next task; Step S37, if the interpolation is successful, then a trial interpolation operation is performed in the ship timeline to insert the round trip distance to the new task location. If the interpolation operation is successful, a task flag is scheduled successfully, and the next task is scheduled. If it fails, the next task is also scheduled. Step S38, if there is a team but no ship, traverse all ships, arrange and combine ships with redundant carrying capacity, and obtain all possible ships that can transport along the way; Step S39, if there is no possible ship for transportation along the way, calculate the schedule of the next task; Step S310, if there is a ship that transports goods along the way, select the ship that transports goods along the way and perform a trial interpolation operation on the ship that transports goods along the way, insert the voyage to and from the task location of the new team, if successful, mark a task scheduling success, and proceed to schedule the next task; Step S311, if the original task is to wait for a berth, the trial inserted voyage is from the dock to the new task location and then to the original task location; Step S312, after all x tasks are scheduled, execute the return scheduling subtask.

[0016] Preferably, the step S312 includes: Step S3121, using the scheduling results of the ship team library, traverse all ships in sequence; Step S3122, searching the current location and task completion time of the outbound team; Step S3123, sorting by team task completion time and sending a ship to pick up the personnel; Step S3124, determining whether the dispatched ship is a return ship; Step S3125, if not, continue to sort by team task end time and send a ship to pick up the people; Step S3126: If yes, return to the previous step, dispatch a ship again, and determine again whether the dispatched ship is a return ship. If not, continue to sort by the end time of the team task and dispatch a ship to pick up the people; Step S3127, if yes, cancel the ship dispatching task, backtrack and eliminate the voyage from the ship timeline, add a voyage for picking up passengers on the second day, and continue to determine the next task; Step S3128, until all teams have received the request and returned to the port, all task calculations are completed, and scheduling is ended.

[0017] The beneficial effects of the present invention are as follows: the present invention combines meteorological data, engineering task data, ship data, geographic information data, and human resources data to schedule and optimize offshore construction ships, taking into account the actual working modes of ships such as turnaround, waiting, and along-the-way transportation, using meteorological forecast data, combined with the meteorological threshold defined for ship construction, to calculate the available window period of the ship in the next 7 days, to ensure that the ship only operates when meteorological conditions permit, to ensure construction safety, to solve the problem of real-time data accuracy, to use Internet of Things technology to obtain the real-time position of the ship, and to provide improved calculation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a multi-dimensional data cross-correlation trial interpolation automatic scheduling method of the present invention; Figure 2 It is a specific flow chart of preparing basic scheduling data, obtaining team, ship, and task data, and calculating team window period data and ship window period data in the present invention; Figure 3 It is a specific flow chart of transmitting the obtained team, ship, task data, and the calculated team window period data and ship window period data to the AI ​​scheduling algorithm for calculation in the present invention; Figure 4 It is a specific flow chart of executing the return scheduling subtask after all tasks are scheduled and completed in the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0020] The present invention will be further described below in conjunction with the accompanying drawings.

[0021] like Figure 1 As shown, a multi-dimensional data cross-correlation heuristic interpolation automatic scheduling method includes: Step S1, screening and selecting the job tasks to be scheduled according to conditions, wherein the selected job tasks belong to one or more of the same project.

[0022] In the embodiment, the operation task includes all the information of the operation, including but not limited to the task name, priority, task start time, latest completion time, estimated working time, estimated docking time, work team, estimated number of maintenance personnel, whether to return to the ship, whether to dock, selected ship, selected wharf, and destination (wind farm wind turbine, booster station, ship).

[0023] Step S2, prepare basic scheduling data, obtain team, ship, task data, and calculated team window period data and ship window period data.

[0024] like Figure 2 As shown, step S2 includes: Step 21, read the team data, terminal geographic information, meteorological data, and ship data of all tasks in the meteorological information time series library and business database.

[0025] Step S22, according to the team data and the existing resource occupancy, calculate the team's work window and set the terminal geographic information data.

[0026] Step S23, calculating the ship's weather window period according to the ship's weather threshold and the weather forecast data of the destination.

[0027] Step S3, the obtained team, ship, task data, as well as the calculated team window period data and ship window period data are transmitted to the AI ​​scheduling algorithm for calculation until all tasks are calculated and the scheduling is ended.

[0028] like Figure 3 As shown, step S3 includes: Step S31, assuming that there are x tasks in total, sort the x tasks according to their priorities, and calculate the task sorting information in sequence.

[0029] Step S32, calculating the schedule according to the ship team library into three situations, including having a ship and a team, having / not having a ship but not having a team, and having a team but not having a ship, and performing interpolation operations and calculations for the three situations respectively.

[0030] Step S33, if there is a ship and a team, then select a team and a ship for the task with the highest priority, and mark a task scheduling success, wherein there is a ship and a team means that the ship and the team are at the dock and can depart at any time.

[0031] Step S34, record the timeline of the occupied teams and ships during the outbound, working and return periods, and then calculate the next task.

[0032] Step S35, if there is / is no ship and no crew, then traverse the timeline of the crew required for the task and perform a trial interpolation operation without considering the ship, wherein there is / is no ship and no crew means that the crew is working at sea, and the ship may or may not be at the dock.

[0033] Step S36: If failed, continue to calculate the scheduling information of the next task.

[0034] Step S37, if the interpolation is successful, then a trial interpolation operation is performed in the ship timeline to insert the round-trip voyage to the new mission location. If the interpolation operation is successful, a mission flag is scheduled successfully and the next mission is scheduled. If it fails, the next mission is also scheduled.

[0035] Step S38, if there is a team but no ship, traverse all ships, arrange and combine the ships with redundant carrying capacity, and obtain all possible ships for transportation along the way. Among them, if there is a team but no ship, the team and the ship have already set out from the dock and are working at sea.

[0036] Step S39: If there is no possible ship for transportation along the way, the schedule of the next task is calculated.

[0037] Step S310, if there is a ship that transports goods along the way, select the ship that transports goods along the way and perform a trial interpolation operation on the ship that is transported along the way, insert the voyage to and from the new team's task location, if successful, mark a task scheduling success, and proceed to schedule the next task.

[0038] Step S311, if the original task is to wait for a berthing ship, the trial inserted voyage is from the dock to the new task location and then to the original task location.

[0039] Step S312, after all x tasks are scheduled, execute the return scheduling subtask.

[0040] like Figure 4 As shown, step S312 includes: Step S3121, using the scheduling results of the ship team library, traverse all ships in sequence.

[0041] Step S3122, searching for the current location and task completion time of the outbound team.

[0042] Step S3123, sort by team task completion time and send a ship to pick up the people.

[0043] Step S3124, determine whether the dispatched ship is a return transport ship.

[0044] Step S3125, if not, continue to sort by team task end time and send a ship to pick up the people.

[0045] Step S3126, if yes, return to the previous step, send a ship again, and determine again whether the sent ship is a return ship. If not, continue to sort by the end time of the team task and send a ship to pick up people.

[0046] Step S3127, if yes, cancel the ship dispatching task, backtrack to eliminate the voyage from the ship timeline, add a voyage to pick up passengers on the second day, and continue to determine the next task.

[0047] Step S3128, until all teams have received the request and returned to the port, all task calculations are completed, and scheduling is ended.

[0048] Step S4: After the scheduling result comes out, the user manually adjusts the scheduling result to end the scheduling. The user confirms the scheduling result and generates a scheduling plan.

[0049] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some or all of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-dimensional data cross-correlation heuristic interpolation automatic scheduling method, characterized in that: include: Step S1, filtering and selecting the job tasks to be scheduled according to the conditions, wherein the selected job tasks belong to one or more of the same project; Step S2, prepare basic scheduling data, obtain team, ship, task data, and calculated team window period data and ship window period data; Step S3, the obtained team, ship, task data, and the calculated team window period data and ship window period data are transmitted to the AI ​​scheduling algorithm for calculation until all tasks are calculated and the scheduling is terminated; Step S4: After the scheduling result comes out, the user manually adjusts the scheduling result to end the scheduling. The user confirms the scheduling result and generates a scheduling plan.

2. The method for automatic scheduling based on heuristic interpolation of multi-dimensional data cross-correlation according to claim 1, characterized in that: In step S1, the operation task includes all the information of the operation, including but not limited to the task name, priority, task start time, latest completion time, estimated working time, estimated docking time, work team, estimated number of maintenance personnel, whether to return to the ship, whether to dock, selected ship, selected wharf, and destination.

3. The method for automatic scheduling based on heuristic interpolation of multi-dimensional data cross-correlation according to claim 1, characterized in that: The step S2 comprises: Step 21, reading the team data, dock geographic information, meteorological data, and ship data of all tasks in the meteorological information time series database and the business database; Step S22, calculating the working window of the team according to the team data and the existing resource occupancy, and setting the dock geographic information data; Step S23, calculating the ship's weather window period according to the ship's weather threshold and the weather forecast data of the destination.

4. The method for automatic scheduling based on heuristic interpolation of multi-dimensional data cross-correlation according to claim 1, characterized in that: The step S3 comprises: Step S31, assuming that there are x tasks in total, sort the x tasks according to their priorities, and calculate the task sorting information in sequence; Step S32, calculating the schedule according to the ship team library into three situations, including having a ship and a team, having / not having a ship but not having a team, and having a team but not having a ship, and performing interpolation operations and calculations for the three situations respectively; Step S33, if there is a ship and a team, then select a team and a ship for the task with the highest priority, and mark a task scheduling success; Step S34, recording the timeline of the occupied teams and ships in the outbound, working and return time periods, and then calculating the next task; Step S35, if there is / is no ship and no team, then traverse the timeline of the team required for the task and perform a trial interpolation operation without considering the ship; Step S36, if failed, continue to calculate the scheduling information of the next task; Step S37, if the interpolation is successful, then a trial interpolation operation is performed in the ship timeline to insert the round trip distance to the new task location. If the interpolation operation is successful, a task flag is scheduled successfully, and the next task is scheduled. If it fails, the next task is also scheduled. Step S38, if there is a team but no ship, traverse all ships, arrange and combine ships with redundant carrying capacity, and obtain all possible ships that can transport along the way; Step S39, if there is no possible ship for transportation along the way, calculate the schedule of the next task; Step S310, if there is a ship that transports goods along the way, select the ship that transports goods along the way and perform a trial interpolation operation on the ship that transports goods along the way, insert the voyage to and from the task location of the new team, if successful, mark a task scheduling success, and proceed to schedule the next task; Step S311, if the original task is to wait for a berth, the trial inserted voyage is from the dock to the new task location and then to the original task location; Step S312, after all x tasks are scheduled, execute the return scheduling subtask.

5. The method for automatic scheduling based on heuristic interpolation of multi-dimensional data cross-correlation according to claim 4, characterized in that: The step S312 includes: Step S3121, using the scheduling results of the ship team library, traverse all ships in sequence; Step S3122, searching the current location and task completion time of the outbound team; Step S3123, sorting by team task completion time and sending a ship to pick up the personnel; Step S3124, determining whether the dispatched ship is a return ship; Step S3125, if not, continue to sort by team task end time and send a ship to pick up the people; Step S3126: If yes, return to the previous step, dispatch a ship again, and determine again whether the dispatched ship is a return ship. If not, continue to sort by the end time of the team task and dispatch a ship to pick up the people; Step S3127, if yes, cancel the ship dispatching task, backtrack and eliminate the voyage from the ship timeline, add a voyage for picking up passengers on the second day, and continue to determine the next task; Step S3128, until all teams have received the request and returned to the port, all task calculations are completed, and scheduling is ended.

Images