Port scheduling simulation method

Abstract

The invention discloses a port scheduling simulation method. The method comprises the following steps: S1, constructing a port three-dimensional model; s2, an operation equipment model and a transportation equipment model are added into the port three-dimensional model, a simulation model is obtained, and the operation equipment model and the transportation equipment model respectively comprise an operation rule and a first AI model; s3, port dispatching data are input into the simulation model and run, and simulation data are obtained; and S4, according to the simulation data, scoring the operation rule and the first AI model by using a first scoring model and a second scoring model, and adjusting the operation rule and the first AI model according to a scoring result. According to the invention, co-simulation of the operation equipment and the transportation equipment is realized, and a basis is provided for optimizing port scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field related to port scheduling, and more specifically, to a port scheduling simulation method. Background Art

[0002] Port scheduling refers to the unified scheduling of the port's operating equipment, transportation equipment, etc. to improve the efficiency of cargo turnover. At present, port scheduling mainly relies on manual labor, which requires high experience and ability of manual labor, and it is difficult to maximize the efficiency of cargo turnover. Some existing technologies have attempted to use computer technology to achieve port scheduling, but these existing technologies usually only consider transportation equipment, such as the invention patent with application number CN2024102187228, which fails to consider the overall situation of the port and cannot reflect the real scheduling scenario. Therefore, it is necessary to design a technical solution that can overcome the above-mentioned defects. Summary of the invention

[0003] One object of the present invention is to provide a port scheduling simulation method, which realizes the collaborative simulation of operating equipment and transportation equipment and provides a basis for optimizing port scheduling.

[0004] In order to achieve these objectives and other advantages of the present invention, according to one aspect of the present invention, the present invention provides a port scheduling simulation method, including: S1: constructing a three-dimensional model of the port; S2: adding an operating equipment model and a transportation equipment model to the three-dimensional model of the port to obtain a simulation model, wherein the operating equipment model and the transportation equipment model respectively include operating rules and a first AI model; S3: inputting port scheduling data into the simulation model and running it to obtain simulation data; S4: based on the simulation data, scoring the operating rules and the first AI model respectively using a first scoring model and a second scoring model, and adjusting the operating rules and the first AI model according to the scoring results.

[0005] Furthermore, in S1, the three-dimensional model of the port is constructed according to the port map and the size of port facilities.

[0006] Furthermore, multiple groups of the port scheduling data are extracted from historical port scheduling events, input into the simulation model and run to obtain multiple groups of simulation data.

[0007] Furthermore, the simulation data includes equipment operating efficiency, the equipment operating efficiency is input into the first scoring model to obtain a first score, and the operating rules of the operating equipment model are adjusted according to the first score.

[0008] Furthermore, the simulation data also includes a moving path of the transportation equipment, a speed change curve of the transportation equipment and a conflict position of the transportation equipment. The moving path of the transportation equipment, the speed change curve of the transportation equipment and the conflict position of the transportation equipment are input into the second scoring model, a second score is output, and the transportation rules of the transportation equipment model are adjusted according to the second score.

[0009] Furthermore, the second scoring model is obtained by training a convolutional neural network, and the moving path of the transportation equipment, the speed change curve of the transportation equipment and the conflict position of the transportation equipment are converted into a moving path image, a speed change image and a conflict distribution image, and input into the second scoring model to obtain the second score.

[0010] Furthermore, in S4, the operating rules and the parameters of the first AI model are adjusted multiple times using the second AI model, and the simulation model is repeatedly run after the adjustment, and the first scoring model and the second scoring model are used to obtain the first score and the second score, multiple sets of adjustment data and the first score and the second score obtained by running the simulation model are obtained, a fine-tuning data set is established, and the second AI model is fine-tuned using the fine-tuning data set.

[0011] Furthermore, it also includes: S5: when the first score is greater than a first threshold and the second score is greater than a second threshold, the obtained operating rules and the first AI model are used for the management of operating equipment and the control of transportation equipment respectively.

[0012] The present invention has at least the following beneficial effects:

[0013] The present invention first constructs a three-dimensional model of the port, and then adds an operating equipment model and a transportation equipment model to the three-dimensional model of the port to obtain a simulation model, inputs the port scheduling data into the simulation model, and runs it to obtain simulation data, and according to the simulation data, respectively uses a first scoring model and a second scoring model to score the operating rules and the first AI model, and adjusts the operating rules and the first AI model according to the scoring results; the present invention performs collaborative simulation on the operating equipment and the transportation equipment, and uses a pre-established scoring model to score them, so that the operating rules and the first AI model can be fully optimized and adjusted, providing a basis for optimizing port scheduling.

[0014] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an embodiment of the present application. DETAILED DESCRIPTION

[0016] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0017] It should be understood that the terms such as "having", "including" and "comprising" used in the embodiments of the present application do not exclude the existence or addition of one or more other elements or their combinations. In the embodiments of the present application, all directional indications (such as up, down, left, right, front, back ...) are only used to explain the relative positional relationship, movement, etc. between the components under a certain specific posture. If the specific posture changes, the directional indication also changes accordingly. When an element is referred to as "fixed on" or "set on" another element, it can be directly on another element or there may be a centering element at the same time. When an element is referred to as "connecting" another element, it can be directly connected to another element or it can also be indirectly connected to another element through a centering element. The description of the embodiments of the present application involving "first", "second", etc. is only for descriptive purposes, and cannot be understood as indicating or implying its relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features.

[0018] It should be noted that the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0019] like Figure 1 As shown, an embodiment of the present application provides a port scheduling simulation method, including:

[0020] S1: Construct a three-dimensional model of the port;

[0021] Exemplarily, the three-dimensional model of the port is constructed according to a port map and the size of port facilities.

[0022] Exemplarily, port facilities include berths, roads, yards, warehouses, etc.;

[0023] S2: adding an operating equipment model and a transport equipment model to the three-dimensional port model to obtain a simulation model, wherein the operating equipment model and the transport equipment model respectively include an operating rule and a first AI model;

[0024] Exemplarily, the operating equipment is a quay crane, a yard crane, etc.;

[0025] Exemplarily, the transport equipment is an AGV (automatic guided vehicle), a container truck, etc.;

[0026] For example, the operation rules may include the number of quay cranes, loading and unloading technology, the number of yard cranes, operator proficiency factors, environmental impact factors (loading and unloading technology impact factors, operator proficiency impact factors), etc., and assign values ​​to factors such as loading and unloading technology, operator proficiency factors, and environmental impact factors to facilitate adjustment;

[0027] For example, there are many transport equipments in the port, and they have different states (idle, loading and unloading, driving, faulty, charging, etc.) and positions. The first AI model includes a neural network, etc., which obtains the states and positions of different transport equipments, performs optimization operations, and performs task and path planning for each transport equipment.

[0028] S3: inputting the port dispatching data into the simulation model and running the model to obtain simulation data;

[0029] Exemplarily, the port dispatch data includes the number of ships, the location of ships, the loading capacity of ships, etc.;

[0030] Exemplarily, multiple groups of the port scheduling data are extracted from historical port scheduling events, input into the simulation model and run, to obtain multiple groups of simulation data, so as to reflect the real port scheduling scenario as much as possible;

[0031] S4: Scoring the operation rules and the first AI model using a first scoring model and a second scoring model respectively according to the simulation data, and adjusting the operation rules and the first AI model according to the scoring results;

[0032] This step does not specifically limit the first scoring model and the second scoring model, and existing weighted scoring methods, machine learning algorithms, etc. may be used;

[0033] Exemplarily, the simulation data includes equipment operating efficiency, the equipment operating efficiency is input into the first scoring model to obtain, a first score is output, and the operating rules of the operating equipment model are adjusted according to the first score; the first scoring model may be a pre-established scoring table, and the first score is obtained according to the equipment operating efficiency obtained by simulation;

[0034] Exemplarily, the simulation data further includes a moving path of the transport equipment, a speed change curve of the transport equipment, and a conflict position of the transport equipment. The moving path of the transport equipment, the speed change curve of the transport equipment, and the conflict position of the transport equipment are input into the second scoring model, a second score is output, and the transport rules of the transport equipment model are adjusted according to the second score.

[0035] Exemplarily, the second scoring model may be a pre-set scoring rule, taking into account the time utilization rate, space utilization rate, etc. of the transportation equipment, and scoring the transportation equipment moving path, the transportation equipment speed change curve, and the transportation equipment conflict position in sequence, and the second score may be a weighted average of the scoring values;

[0036] Exemplarily, the effectiveness of the operating rules and the first AI model is judged according to the scoring results, and then the values ​​of the number of quay cranes, loading and unloading processes, the number of yard cranes, operator proficiency factors, environmental impact factors, etc. are adjusted, and the parameters in the first AI model, that is, the internal adjustable variables, are adjusted, and the operating rules and the first AI model are gradually optimized to obtain the optimal operating rules and the first AI model, which provide a basis for subsequent further simulation and actual port scheduling;

[0037] This embodiment conducts collaborative simulation of operating equipment and transportation equipment, which is closer to the actual port scenario and overcomes the defects of considering operating equipment or transportation equipment in isolation. It also uses a pre-established scoring model for scoring, and reversely optimizes and adjusts the operating rules and the first AI model, thereby providing data support for optimizing port scheduling.

[0038] In another embodiment, the second scoring model is obtained by training a convolutional neural network, and the moving path of the transport equipment, the speed change curve of the transport equipment, and the conflict position of the transport equipment are converted into a moving path image, a speed change image, and a conflict distribution image, and input into the second scoring model to obtain the second score;

[0039] Exemplarily, based on the port plan, a movement path image and a conflict distribution image are further generated, and a speed change image is generated from the speed curve that changes over time. After preprocessing, these images are input into a second scoring model trained by a convolutional neural network to obtain a second score; the second scoring model is trained by a pre-established training set, and the training set includes a movement path image, a speed change image, a conflict distribution image and an expert score.

[0040] In another embodiment, in S4, the operating rules and the parameters of the first AI model are adjusted multiple times using the second AI model, the simulation model is repeatedly run after the adjustment, and the first scoring model and the second scoring model are used to obtain the first score and the second score, multiple sets of adjustment data and the first score and the second score obtained by running the simulation model are obtained, a fine-tuning data set is established, and the second AI model is fine-tuned using the fine-tuning data set;

[0041] In this embodiment, the second AI model is used to adjust the operating rules and the first AI model to obtain multiple new operating rules and the adjusted first AI model, the simulation model is updated and run to obtain simulation data, the first score and the second score are obtained by the same method as above, and a fine-tuning data set including the first score, the second score and the adjustment data is established. The second AI model learns the fine-tuning data set and performs fine-tuning to obtain a fine-tuned second AI model, which is used for adjusting the operating rules and the first AI model to facilitate fast and accurate optimization results. The obtained second AI model can also be used for optimizing the operating rules and the first AI model in other simulation models.

[0042] In another embodiment, the method further includes: S5: when the first score is greater than a first threshold and the second score is greater than a second threshold, the obtained operation rule and the first AI model are respectively used for the management of the operation equipment and the control of the transportation equipment;

[0043] In this step, the first threshold and the second threshold are determined by experts. When the first score and the second score meet the conditions at the same time, the obtained operating rules and the first AI model are needed. The obtained operating rules can be used for the management of operating equipment, such as selecting the number of quay cranes, loading and unloading processes, the number of yard cranes, operators, and preparing plans according to the environment and weather. The obtained first AI model can be directly used for path planning and control of transportation equipment.

[0044] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A port scheduling simulation method, characterized in that: include: S1: Construct a three-dimensional model of the port; S2: adding an operating equipment model and a transport equipment model to the three-dimensional port model to obtain a simulation model, wherein the operating equipment model and the transport equipment model respectively include an operating rule and a first AI model; S3: inputting the port dispatching data into the simulation model and running the model to obtain simulation data; S4: According to the simulation data, the operation rules and the first AI model are scored using a first scoring model and a second scoring model respectively, and the operation rules and the first AI model are adjusted according to the scoring results.

2. The port scheduling simulation method according to claim 1, characterized in that: In S1, the three-dimensional model of the port is constructed according to the port map and the size of port facilities.

3. The port scheduling simulation method according to claim 1, characterized in that: A plurality of groups of the port scheduling data are extracted from historical port scheduling events, input into the simulation model and run to obtain a plurality of groups of simulation data.

4. The port scheduling simulation method according to claim 1, characterized in that: The simulation data includes equipment operation efficiency, the equipment operation efficiency is input into the first scoring model to obtain a first score, and the operation rules of the operation equipment model are adjusted according to the first score.

5. The port scheduling simulation method according to claim 1, characterized in that: The simulation data also includes a moving path of the transport equipment, a speed change curve of the transport equipment and a conflict position of the transport equipment. The moving path of the transport equipment, the speed change curve of the transport equipment and the conflict position of the transport equipment are input into the second scoring model, a second score is output, and the transport rules of the transport equipment model are adjusted according to the second score.

6. The port scheduling simulation method according to claim 5, characterized in that: The second scoring model is obtained by training a convolutional neural network, which converts the moving path of the transportation equipment, the speed change curve of the transportation equipment and the conflict position of the transportation equipment into a moving path image, a speed change image and a conflict distribution image, and inputs them into the second scoring model to obtain the second score.

7. The port scheduling simulation method according to claim 1, characterized in that: In S4, the operating rules and the parameters of the first AI model are adjusted multiple times using the second AI model. After the adjustment, the simulation model is repeatedly run, and the first scoring model and the second scoring model are used to obtain the first score and the second score, multiple groups of adjustment data and the first score and the second score obtained by running the simulation model are obtained, a fine-tuning data set is established, and the second AI model is fine-tuned using the fine-tuning data set.

8. The port scheduling simulation method according to claim 7, characterized in that: Also includes: S5: When the first score is greater than a first threshold and the second score is greater than a second threshold, the obtained operating rules and the first AI model are used for the management of operating equipment and the control of transportation equipment, respectively.

Images