A port material scheduling simulation method for collaboration between ships and ground transportation vehicles

By constructing a port material scheduling model and employing genetic algorithms and edge computing technology to dynamically adjust the scheduling scheme, the problem of low port material turnover efficiency was solved, and efficient port material turnover and resource optimization were achieved.

CN118608028BActive Publication Date: 2024-11-22CHINA WATERBORNE TRANSPORT RES INST
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410749010.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-12
Publication Date
2024-11-22
Estimated Expiration
2044-06-12

AI Technical Summary

Technical Problem

In existing technologies, port material turnover methods mainly rely on manual scheduling and fixed operating procedures, which leads to information lag, inability to adjust scheduling plans in real time, and the occurrence of waiting for ships and vehicles, resulting in low material turnover efficiency.

Method used

By acquiring historical information related to ships and ground transport vehicles, a port material scheduling model is constructed. A genetic algorithm is used for simulation, and edge computing technology is combined to process real-time status information, dynamically adjust the scheduling scheme, and display the results visually.

Benefits of technology

It has enabled efficient turnover of port materials, improved the accuracy and flexibility of scheduling schemes, and enhanced port operation efficiency and resource utilization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118608028B_ABST
    Figure CN118608028B_ABST
Patent Text Reader

Abstract

The present invention discloses a port material scheduling simulation method for collaboration between ships and ground transport vehicles. The method belongs to the field of ship management technology, and includes the following steps: obtaining historical related information of ships and ground transport vehicles; constructing a port material scheduling model based on the acquired related information; simulating the port material scheduling model using a genetic algorithm; generating a scheduling plan based on the simulation results; monitoring the implementation of the scheduling plan in real time, obtaining real-time status information of ships and ground transport vehicles through a sensor network, and using edge computing technology to process the real-time status information in real time to obtain real-time processing data; dynamically adjusting the scheduling plan based on the real-time processing data; and visually displaying the scheduling plan. The present invention achieves efficient turnover of port materials by simulating the port material scheduling model using a genetic algorithm and using a time series analysis algorithm, solving the problem of low turnover efficiency of port materials in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ship management, and in particular to a port material dispatching simulation method in which ships and ground transport vehicles cooperate. Background Art

[0002] With the continuous growth of global trade, ports, as important nodes for material transportation, have become particularly important in terms of dispatch efficiency. Collaborative transportation is a form of logistics transportation that involves close cooperation between operators or partners of different modes of transportation, such as ships and ground transportation vehicles, to jointly undertake the task of transporting goods. Port material dispatch refers to a series of activities within the port to plan, organize, direct and coordinate the goods entering and leaving the port.

[0003] The existing ship and ground transport vehicle system is implemented through manual experience and simple scheduling software, and lacks intelligent and coordinated scheduling solutions, resulting in long waiting times for ships and low utilization rates of ground transport vehicles, which in turn affects the overall operating efficiency of the port.

[0004] For example, the invention patent with announcement number: CN105117793B announces a method for optimizing ship scheduling in a two-way navigable port, including: establishing a mode conversion constraint according to the one-way / two-way navigation conversion characteristics, establishing a continuity constraint according to the continuity of the ship's operation in the port, and establishing a safety constraint according to the longitudinal safety distance and the lateral safety distance of the ship; establishing a multi-objective genetic model according to the mode conversion constraint, the continuity constraint and the safety constraint; initializing the multi-objective genetic model; decoding the chromosomes corresponding to the multi-objective genetic model, and combining the continuity constraint and the safety constraint to obtain a ship scheduling plan, the scheduling plan including the start time of ship scheduling and the time of sailing to other key positions, the adjusted speed, and the time waiting to enter the port or waiting to leave the port.

[0005] For example, the invention patent with announcement number: CN108629485B discloses a ship scheduling method under uncertain demand conditions, including: after calculating the scheduling sequence with the highest profit, the problem of converting the number of slots that can increase the profit is calculated based on the scheduling sequence, and the optimal scheduling scheme is re-calculated based on the number of slots with the highest profit, until the two goals of the optimal number of slots and the scheduling sequence are completely consistent when the profit is the highest. The present invention takes uncertain demand into account, and the result obtained can enable the shipping company to respond to demand changes caused by economic fluctuations in the most stable manner.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, the traditional port material turnover method mainly relies on manual scheduling and fixed operating procedures. Manual scheduling and planning lead to information lags and the inability to adjust the scheduling plan in real time. It is easy for ships and vehicles to wait, resulting in low port material turnover efficiency. Summary of the invention

[0008] The embodiment of the present application solves the problem of low port material turnover efficiency in the prior art by providing a port material scheduling simulation method in which ships and ground transport vehicles are coordinated, thereby achieving efficient turnover of port materials.

[0009] An embodiment of the present application provides a port material scheduling simulation method for the collaboration of ships and ground transport vehicles, comprising the following steps: obtaining historical related information of ships and ground transport vehicles; constructing a port material scheduling model based on the obtained related information; simulating the port material scheduling model using a genetic algorithm; generating a scheduling plan based on the simulation results; monitoring the implementation of the scheduling plan in real time, obtaining real-time status information of ships and ground transport vehicles through a sensor network, and using edge computing technology to process the real-time status information in real time to obtain real-time processed data; dynamically adjusting the scheduling plan based on the real-time processed data; and visually displaying the scheduling plan.

[0010] Furthermore, the step of obtaining historical related information of ships and ground transport vehicles includes: obtaining the estimated arrival time of the ship, the type and quantity of cargo and the unloading time information, and storing this information in the port database; obtaining the type, quantity, capacity, current location and available time information of ground transport vehicles, and inputting this information into the port database; using the sensor network and GPS system to monitor and update the location information and status information of the ground transport vehicles in real time; integrating all the information of ships and ground transport vehicles to obtain historical related information of ships and ground transport vehicles.

[0011] Furthermore, the steps of constructing the port material scheduling model include: analyzing the ship information and ground transport vehicle information, and comprehensively considering the constraints inside and outside the port; analyzing the acquired ship information and ground transport vehicle information to establish a data set; using a multi-objective optimization algorithm to optimize the data set to obtain a preliminary scheduling strategy; using a time series analysis algorithm to predict the ship arrival time and the available time of ground transport vehicles to generate prediction data; combining the preliminary scheduling strategy obtained by the multi-objective optimization algorithm with the prediction data to construct the port material scheduling model.

[0012] Furthermore, the port material scheduling simulation method for the coordination of ships and ground transport vehicles is characterized in that: the internal and external constraints of the port include: berth quantity constraints: Berth usage constraints: Vehicle capacity constraints: Traffic congestion constraint: y kt ≤J t ; Where B represents the number of berths, j represents the number of berths, j = 1, 2, ..., B, N s Represents the total number of ships, i represents the ship number, i=1,2,...,N s , x ij is a decision variable, indicating whether the i-th ship berths at the j-th berth, N v represents the total number of ground transport vehicles, k represents the number of ground transport vehicles, k=1,2,...,N v , C k represents the transport capacity of the kth vehicle, t represents the number of the time period, t=1,2,...,T, T represents the total time period, Q t represents the demand for goods in the tth time period, y kt Indicates whether the kth ground transportation vehicle is used in the tth time period, J t Indicates the maximum number of vehicles allowed to pass through the road within time t.

[0013] Furthermore, the port material scheduling simulation method for the collaboration of ships and ground transport vehicles is characterized in that: the step of simulating the port material scheduling model using a genetic algorithm includes: randomly generating an initial population, each individual representing a scheduling plan; generating a fitness function, calculating the minimization of ship waiting time, maximization of transport vehicle utilization and minimization of material loading and unloading time; using selection, crossover and mutation operations, iteratively optimizing the scheduling plan, and obtaining the best fitness function.

[0014] Furthermore, the port material scheduling simulation method for the coordination of ships and ground transport vehicles is characterized in that the mathematical formula of the optimal fitness function is:

[0015]

[0016] Where α+β+γ=1, f(I) represents the fitness function, which is used to evaluate the overall scheduling scheme, α represents the weight of minimizing the waiting time of the ship, β represents the weight of maximizing the utilization rate of the transport vehicle, γ represents the weight of minimizing the material loading and unloading time, and W s represents the total waiting time of the ship, W max Indicates the maximum waiting time of the ship, U v represents the utilization rate of transport vehicles, U max represents the maximum utilization rate of transport vehicles, E m Represents the total material loading and unloading time, E max Indicates the maximum value of material loading and unloading time.

[0017] Furthermore, the port material scheduling simulation method for the coordination of ships and ground transport vehicles is characterized in that: the step of dynamically adjusting the scheduling plan based on real-time processing data includes: using a genetic algorithm to evaluate the fitness of each generation of scheduling plans in the simulation process, and selecting the plan with the highest fitness as the current optimal plan; generating the unloading sequence of the ship and the scheduling sequence of the ground transport vehicles based on the current optimal plan; generating a detailed scheduling plan, including the ship's berthing position, unloading time schedule, and the scheduling path and time schedule of the transport vehicle.

[0018] Furthermore, the port material scheduling simulation method for collaboration between ships and ground transport vehicles is characterized in that: the step of using edge computing technology to perform real-time processing of real-time status information includes: using a sensor network to receive and process real-time status information, the real-time status information including the ship's location, the ground transport vehicle's location and cargo status information; using edge computing nodes to perform data preprocessing and analysis on the real-time status information, filtering out noise data and extracting key information.

[0019] Furthermore, the port material scheduling simulation method for the collaboration of ships and ground transport vehicles is characterized in that: the step of dynamically adjusting the scheduling plan according to actual conditions includes: utilizing a sensor network to obtain real-time status information of ships and ground transport vehicles in real time; performing data preprocessing and analysis on the received real-time status information to generate a real-time status report; comparing the expected status in the current scheduling plan with the actual status in the real-time status report to identify any deviations; adjusting the unloading sequence and berthing position of the ship according to the identified deviations; rearranging the scheduling path and time of ground transport vehicles to ensure that they match the adjusted ship unloading time; and recalculating the optimal scheduling plan using a multi-objective optimization algorithm.

[0020] Furthermore, the port material scheduling simulation method for the collaboration of ships and ground transport vehicles is characterized in that: the visual display of the scheduling plan includes: visualizing the optimal scheduling plan to display the unloading sequence of the ship, the scheduling sequence and path planning of the ground transport vehicles; dynamically displaying the real-time position and status of the ship and ground transport vehicles in the visual interface; marking the ship's berthing position, unloading progress, cargo type and quantity information through charts and graphics, and distinguishing various types of ground transport vehicles and their scheduling status; providing interactive functions to allow dispatchers to adjust the scheduling plan in real time through click and drag operations.

[0021] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0022] 1. By using genetic algorithms to simulate the port material scheduling model, the optimal scheduling plan is generated, and the fitness function is used to iteratively optimize the scheduling plan, thereby achieving efficient turnover of port materials and effectively solving the problem of low port material turnover efficiency in the existing technology.

[0023] 2. By using the time series analysis algorithm to predict the arrival time of ships and the available time of ground transportation vehicles, and combining it with the multi-objective optimization algorithm, a port material scheduling model is constructed, thereby achieving the accuracy and flexibility of the scheduling plan, so that the scheduling plan can dynamically adapt to changes in actual conditions.

[0024] 3. By adopting edge computing technology to process real-time status information in real time, efficient processing of real-time status information of ships and ground transport vehicles can be achieved, and then the scheduling plan can be dynamically adjusted according to the real-time processing data. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of a port material dispatch simulation method for collaboration between ships and ground transport vehicles provided in an embodiment of the present application;

[0026] Figure 2 This is a fitness function data graph provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The embodiment of the present application solves the problem of low port material turnover efficiency in the prior art by providing a port material scheduling simulation method for collaboration between ships and ground transport vehicles. The efficient turnover of port materials is achieved by simulating the port material scheduling model using a genetic algorithm, using a time series analysis algorithm to predict the arrival time of ships and the available time of ground transport vehicles, and combining a multi-objective optimization algorithm.

[0028] The technical solution in the embodiment of the present application is to solve the problem of low material turnover efficiency in the above-mentioned port, and the overall idea is as follows: by obtaining historical related information of ships and ground transport vehicles; building a port material scheduling model based on the obtained related information; using a genetic algorithm to simulate the port material scheduling model; generating a scheduling plan based on the simulation results; real-time monitoring of the implementation of the scheduling plan, obtaining real-time status information of ships and ground transport vehicles through a sensor network, and using edge computing technology to process the real-time status information in real time to obtain real-time processing data; dynamically adjusting the scheduling plan based on the real-time processing data; and visually displaying the scheduling plan to achieve efficient turnover of port materials.

[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0030] In this embodiment, a port material scheduling model is constructed to optimize port logistics operations. The sensor network includes the following contents: First, sensor nodes are deployed at key locations in the port to collect data from ships and ground transport vehicles in real time. The data that these sensor nodes can collect include the current position, speed, cargo status of the ship, and the current position, speed and cargo status of the ground transport vehicle. Secondly, these sensor nodes transmit the collected data to the port control center through wireless communication technology to ensure the timeliness and accuracy of the data. The sensor network adopts self-organizing network technology to ensure the stability and reliability of data transmission, and has the ability to automatically discover and configure sensor nodes. The sensor network also includes a data processing module to pre-process and preliminarily analyze the collected data, filter noise data and extract key information to ensure efficient data processing. Finally, the sensor network works in conjunction with the edge computing node, and through the efficient data processing capability of the edge computing node, efficient processing and analysis of real-time status information is achieved to ensure that the scheduling plan can be adjusted and optimized in time.

[0031] Furthermore, the steps of obtaining historical related information of ships and ground transport vehicles include: obtaining the estimated arrival time of the ship, the type and quantity of cargo and the unloading time information, and storing this information in the port database; obtaining the type, quantity, capacity, current location and available time information of ground transport vehicles, and entering this information into the port database; using the sensor network and GPS system to monitor and update the location information and status information of ground transport vehicles in real time; integrating all the information of ships and ground transport vehicles to obtain historical related information of ships and ground transport vehicles.

[0032] In this embodiment, a comprehensive data foundation can be constructed by obtaining detailed information of ships and ground transportation vehicles, including the estimated arrival time of ships, cargo type and quantity, and unloading time information, and the type, quantity, capacity, current location, and available time information of ground transportation vehicles.

[0033] Furthermore, the steps of constructing a port material scheduling model include: analyzing the ship information and ground transportation vehicle information, and comprehensively considering the constraints inside and outside the port; analyzing the acquired ship information and ground transportation vehicle information to establish a data set; using a multi-objective optimization algorithm to optimize the data set and obtain a preliminary scheduling strategy; using a time series analysis algorithm to predict the ship arrival time and the available time of ground transportation vehicles to generate forecast data; combining the preliminary scheduling strategy obtained by the multi-objective optimization algorithm with the forecast data to construct a port material scheduling model.

[0034] In this embodiment, the multi-objective optimization algorithm is such as a genetic algorithm, and the time series analysis algorithm is such as a long short-term memory network. The input data of the genetic algorithm include: the expected arrival time of the ship, the type and quantity of cargo, the unloading time, the type, quantity, capacity, current location and available time of ground transportation vehicles, the number of berths, the berth usage time, and traffic conditions. Output data: the optimal scheduling plan, including the unloading sequence of the ship and the scheduling path and time arrangement of the ground transportation vehicles. The input data of the long short-term memory network: historical ship arrival time data, historical ground transportation vehicle available time data. Output data: predicted ship arrival time, available time of ground transportation vehicles.

[0035] Comprehensively consider the constraints inside and outside the port: introduce the constraints inside and outside the port into the ship information and ground transportation vehicle information as the constraints of the port material scheduling model, combine these constraints with the ship and vehicle information to form a data set under multiple constraints. Through comprehensive analysis of ship and vehicle information, combined with multi-objective optimization algorithms and time series analysis, a dynamic and accurate port material scheduling model can be constructed to improve the accuracy and practicality of the scheduling plan. Through the multi-objective optimization algorithm, multiple optimization goals are balanced to achieve the optimal allocation of resources, reduce ship waiting time, maximize the utilization of ground transportation vehicles, minimize material loading and unloading time, and improve the overall port operation efficiency. Through data analysis and prediction, the formulation of the scheduling plan is based on actual data and scientific analysis, which improves the scientificity and reliability of decision-making and reduces the subjectivity and errors of human decision-making.

[0036] Furthermore, the constraints inside and outside the port include: Berth quantity constraints:

[0037] Berth usage constraints:

[0038] Vehicle capacity constraints:

[0039] Traffic congestion constraint: y kt ≤J t ;

[0040] Where B represents the number of berths, j represents the number of berths, j = 1, 2, ..., B, N s Represents the total number of ships, i represents the ship number, i=1,2,...,N s , x ij is a decision variable, indicating whether the i-th ship berths at the j-th berth, N v represents the total number of ground transport vehicles, k represents the number of ground transport vehicles, k=1,2,...,N v , C krepresents the transport capacity of the kth vehicle, t represents the number of the time period, t=1,2,...,T, T represents the total time period, Q t represents the demand for goods in the tth time period, y kt Indicates whether the kth ground transportation vehicle is used in the tth time period, J t Indicates the maximum number of vehicles allowed to pass through the road within time t, and the maximum number of vehicles is 300.

[0041] In this embodiment, the berth quantity constraint condition: ensure that each berth is not occupied by multiple ships at any time point to avoid berth conflicts. Berth use constraint condition: ensure that each berth is only used by one ship at any time point to optimize berth resource allocation. Vehicle capacity constraint condition: ensure that there are enough ground transportation vehicles to meet the cargo transportation demand in each time period to avoid delays caused by insufficient capacity. Traffic congestion constraint condition: ensure that the traffic flow in each time period does not exceed the road carrying capacity to avoid traffic congestion and improve transportation efficiency.

[0042] Furthermore, the steps of simulating the port material scheduling model using a genetic algorithm include: randomly generating an initial population, each individual representing a scheduling plan; generating a fitness function, calculating how to minimize ship waiting time, maximize transportation vehicle utilization, and minimize material loading and unloading time; using selection, crossover, and mutation operations to iteratively optimize the scheduling plan and obtain the best fitness function.

[0043] In this embodiment, selection operation: select individuals from the current population according to the fitness value. Through the selection operation, excellent individuals are retained. Crossover operation: select two scheduling schemes, generate a new scheme by exchanging part of the scheduling arrangement, and the crossover operation combines the advantages of the two scheduling schemes to generate a new scheduling scheme, which increases the diversity of the scheme. Mutation operation: randomly change part of the arrangement in the scheduling scheme to generate a new scheduling scheme, and iteratively optimize the scheduling scheme: through selection, crossover and mutation operations, continuously generate new populations, and each generation of populations will be closer to the optimal solution than the previous generation. Through the random generation of the initial population, fitness evaluation and iterative optimization of the genetic algorithm, the optimal scheduling scheme can be effectively found to ensure the shortest waiting time for ships, the highest utilization rate of transport vehicles and the shortest material loading and unloading time. The random generation of the initial population and the mutation operation ensure the diversity of the scheduling scheme. The crossover operation introduces new combinations, increases the flexibility of the scheduling scheme, and avoids falling into the local optimal solution. The precise design of the fitness function and multiple iterative optimizations ensure the scientificity and reliability of the scheduling scheme, so that the scheduling scheme can be efficiently executed in actual operation. The automation characteristics of the genetic algorithm reduce manual intervention, and the optimization process is automatically carried out, which improves the intelligence level and operation efficiency of port material scheduling.

[0044] As shown in Table 1, the fitness function data table:

[0045] Table 1 Fitness function data table

[0046]

[0047]

[0048] like Figure 2 The fitness function data is shown in the figure, where α is 0.3, β is 0.4, and γ is 0.3. α, β, and γ are obtained through historical experience of experts. The maximum waiting time of the ship is 20 hours, which is obtained through historical experience. The maximum utilization rate of the transport vehicle is 100%, and the total material loading and unloading time is 15 hours, which can be obtained through historical experience.

[0049] From Table 1 and Figure 2 It can be seen that the group with the highest fitness value is group 5, with a fitness value of 0.810. Its ship waiting time is 2 hours, the utilization rate of transport vehicles is 95%, and the material loading and unloading time is 7 hours. This shows that it performs best in minimizing ship waiting time, maximizing transport vehicle utilization, and minimizing material loading and unloading time. The group with the lowest fitness value is group 6, with a fitness value of 0.580. This shows that the scheduling scheme of group 6 performs the worst in the above indicators. The fitness values ​​of other groups are between 0.665 and 0.807, indicating that these groups perform relatively balanced in the above indicators. Transport vehicle utilization: The transport vehicle utilization rate of most groups is between 80% and 95%, which is a good performance. By comparing the fitness values, it can be determined which scheduling schemes perform well and which need to be improved. Groups 5 and 9 are better scheduling schemes, which are worthy of further study and application. The fluctuation of fitness values ​​reflects that the scheduling scheme needs to be continuously and dynamically adjusted according to actual conditions to improve overall efficiency and resource utilization.

[0050] Furthermore, the mathematical formula of the optimal fitness function is:

[0051]

[0052] Where α+β+γ=1, f(I) represents the fitness function, which is used to evaluate the overall scheduling scheme, α represents the weight of minimizing the waiting time of the ship, β represents the weight of maximizing the utilization rate of the transport vehicle, γ represents the weight of minimizing the material loading and unloading time, and W s represents the total waiting time of the ship, W max Indicates the maximum waiting time of the ship, U v represents the utilization rate of transport vehicles, U max represents the maximum utilization rate of transport vehicles, E m Represents the total material loading and unloading time, E max Indicates the maximum value of material loading and unloading time.

[0053] In this example, the waiting time of the ship is minimized:

[0054]

[0055] Where W s represents the total waiting time of the ship, N s Represents the total number of ships, i represents the ship number, i=1,2,...,N s , B represents the number of berths, j represents the number of berths, j = 1, 2, ..., B, T aij represents the actual arrival time of the i-th ship at the j-th berth, T s represents the estimated arrival time of the i-th ship, x ij is a decision variable, indicating whether the i-th ship is berthed at the j-th berth. If so, then x ij =1, otherwise x ij =0.

[0056] Maximize the utilization of transport vehicles:

[0057]

[0058] Where U v represents the utilization rate of transport vehicles, N v represents the total number of ground transport vehicles, k represents the number of ground transport vehicles, k=1,2,...,N v , T represents the total time period, t represents the number of the time period, t=1,2,...,T,y kt Indicates whether the kth ground transport vehicle is used in the tth time period. If so, then y kt =1, otherwise y kt = 0. Minimize material loading and unloading time:

[0059]

[0060] In the formula, E m Represents the total material loading and unloading time, U s represents the unloading time of the i-th ship.

[0061] Furthermore, the step of dynamically adjusting the scheduling plan according to the real-time processing data includes: using a genetic algorithm to evaluate the fitness of each generation of scheduling plans in the simulation process, and selecting the plan with the highest fitness as the current optimal plan; generating the unloading sequence of the ship and the scheduling sequence of the ground transport vehicles according to the current optimal plan; generating a detailed scheduling plan, including the ship's berthing position, unloading time schedule, and the scheduling path and time schedule of the transport vehicle.

[0062] In this embodiment, a detailed scheduling scheme is generated, including the ship berthing position, unloading time arrangement, and the scheduling path and time arrangement of the transport vehicle. For example: ship berthing position arrangement, according to the optimal scheduling scheme, determine the specific berthing position of each ship, allocate berths according to the size, type and unloading demand of the ship, and limit each berth to be allocated to only one ship at any time point according to the berth use constraint. Unloading time arrangement: determine the unloading start time and end time of each ship, ensure that the unloading time arrangement takes into account the expected arrival time of the ship, the quantity of cargo and the unloading speed, and coordinate the scheduling time of ground transport vehicles so as to load and unload the unloaded cargo in time. The scheduling path and time arrangement of the transport vehicle: determine the specific scheduling path of each transport vehicle to ensure the minimization of the empty driving time; arrange the scheduling time of the transport vehicle to ensure that it arrives at the corresponding berth when the unloading is completed; according to the vehicle capacity constraint, allocate enough transport vehicles to meet the unloading demand; according to the traffic congestion constraint, adjust the vehicle scheduling path to avoid traffic congestion during peak hours. The steps of fitness evaluation include: first, initialize the population, randomly generate a number of individuals, each of which represents a possible scheduling scheme. During the simulation process, the fitness of all individuals in each generation of the population is evaluated. The specific method is to calculate the fitness value of each individual according to the preset fitness function. The fitness function comprehensively considers factors such as minimizing the waiting time of ships, maximizing the utilization rate of transport vehicles, and minimizing the time of material loading and unloading, and calculates the performance of each individual on different goals through formulas. The total waiting time of ships from arriving at the port to completing unloading, the total utilization rate of transport vehicles, and the total time of material loading and unloading in each scheduling scheme are calculated through the fitness function. These calculation results are used to evaluate the pros and cons of each scheduling scheme. The higher the fitness value, the better its performance. The individuals are sorted according to the fitness value, and the individuals with higher fitness are selected to enter the next generation. A new population is generated through selection, crossover and mutation operations. The selection, crossover and mutation operations are repeated until the fitness value converges, and the optimal scheduling scheme is finally obtained. In this way, the genetic algorithm can gradually optimize the scheduling scheme and improve the efficiency and accuracy of port material scheduling.

[0063] Furthermore, the steps of using edge computing technology to process real-time status information in real time include: using a sensor network to receive and process real-time status information, the real-time status information includes the location of the ship, the location of the ground transport vehicle, and the status information of the cargo; using edge computing nodes to pre-process and analyze the real-time status information, filter out noise data, and extract key information.

[0064] In this embodiment, the sensor network is composed of sensor nodes deployed at key locations of the port, which are used to collect real-time status information of ships and ground transport vehicles in real time. Real-time status information includes ship position, speed, cargo status, and current position, speed, cargo status and other information of ground transport vehicles. The sensor node transmits the collected data to the edge computing node through wireless communication technology. The application of edge computing technology makes data processing more intelligent and efficient, provides technical support for the intelligent management of port material scheduling, and improves overall scheduling efficiency and resource utilization. The specific analysis steps are: using the long short-term memory network to perform time series analysis on the historical ship arrival time and the available time data of ground transport vehicles. Through data preprocessing, the historical data is converted into a format suitable for the input of the long short-term memory network model to predict the future ship arrival time and vehicle available time. These prediction results are used as initial input data to generate expected scheduling requirements in the future time period. Then, combined with these predicted data, a port material scheduling model is constructed. The model includes constraints (such as the number of berths, traffic conditions, etc.) and objective functions (such as minimizing ship waiting time, maximizing vehicle utilization, and minimizing material loading and unloading time). The results of the long short-term memory network are used as the input of the multi-objective optimization algorithm (genetic algorithm). The genetic algorithm first generates an initial population, and each individual represents a possible scheduling scheme. Based on the fitness function, the fitness value of each scheme is calculated, comprehensively considering minimizing ship waiting time, maximizing vehicle utilization, and minimizing material loading and unloading time. Then, the scheduling scheme is iteratively optimized through selection, crossover, and mutation operations to continuously improve the fitness value. The scheduling scheme with the highest fitness value is output as the optimal port material scheduling strategy. By combining the time series prediction of the long short-term memory network and the multi-objective optimization of the genetic algorithm, the model can dynamically adjust the scheduling scheme to improve port operation efficiency and resource utilization.

[0065] The specific steps of data preprocessing are as follows: First, collect and organize historical ship arrival times and available time data of ground transportation vehicles to ensure the integrity and accuracy of the data. Then, clean the data to remove missing values ​​and outliers to ensure data quality. Next, scale the cleaned data to a fixed range (such as 0 to 1) to meet the input requirements of the long short-term memory network. The scaled data is divided into training sets and test sets in chronological order to ensure that the training sets and test sets are representative and temporally continuous. Subsequently, the segmented data is converted into a suitable format, which usually includes adjustments to the time step and feature dimension. For example, slide and slice the continuous time series data according to the set time step (such as 10 steps) to generate training samples and corresponding labels.

[0066] Furthermore, the steps of dynamically adjusting the scheduling plan according to actual conditions include: using a sensor network to obtain real-time status information of ships and ground transport vehicles in real time; performing data preprocessing and analysis on the received real-time status information to generate a real-time status report; comparing the expected status in the current scheduling plan with the actual status in the real-time status report to identify any deviations; adjusting the unloading sequence and berthing position of the ship according to the identified deviations; rearranging the scheduling path and time of the ground transport vehicles to ensure that they match the adjusted ship unloading time; and recalculating the optimal scheduling plan using a multi-objective optimization algorithm.

[0067] In this embodiment, the expected state in the current scheduling scheme is compared with the actual state in the real-time status report. Through the comparison, the difference between the expected state and the actual state is identified, such as delayed arrival of ships at the port, untimely vehicle scheduling, etc. According to the real-time status, the unloading order of the ship is adjusted, and urgent goods or ships delayed at the port are given priority. The berthing position of the ship is reallocated to ensure the optimal utilization of berth resources and avoid berth conflicts and long waiting time for ships. According to the traffic conditions and real-time status inside and outside the port, the scheduling path of ground transportation vehicles is rearranged to avoid traffic congestion, improve transportation efficiency, ensure that the scheduling time of ground transportation vehicles matches the adjusted ship unloading time, reduce waiting time, and improve loading and unloading efficiency. By combining a multi-objective optimization algorithm, the optimal scheduling scheme can be found in a complex and changing environment, and the intelligence level and overall efficiency of port material scheduling can be improved.

[0068] Furthermore, the visual display of the scheduling plan includes: visualizing the optimal scheduling plan, showing the unloading order of the ship, the scheduling order and path planning of the ground transport vehicles; dynamically displaying the real-time position and status of the ship and ground transport vehicles in the visual interface; marking the ship's berthing position, unloading progress, cargo type and quantity information through charts and graphics, and distinguishing various types of ground transport vehicles and their scheduling status; providing interactive functions, allowing dispatchers to adjust the scheduling plan in real time by clicking and dragging.

[0069] In this embodiment, the optimized scheduling scheme is displayed through a graphical interface so that the dispatchers can intuitively understand the scheduling situation. The display content includes key information such as the unloading order of the ship, the scheduling order of the ground transport vehicles and the path planning. The real-time position and status of the ship and the ground transport vehicle are dynamically displayed on the visual interface: the status information of the ship and the ground transport vehicle is obtained in real time through the sensor network and edge computing technology. The real-time status data is dynamically displayed on the visual interface, including the current position, speed, unloading progress of the ship, and the current position, speed, cargo status of the ground transport vehicle, etc., to ensure that the dispatchers can keep abreast of the latest scheduling status and make timely adjustments and decisions. Through the visual display, the details of the scheduling scheme are clear at a glance, and the dispatchers and managers can clearly understand the current scheduling status and future arrangements, improving transparency and communication efficiency. The status information of ships and ground transport vehicles is displayed in real time, and the dispatchers are allowed to make immediate adjustments to ensure that the scheduling scheme can dynamically adapt to changes in actual conditions and improve the flexibility and response speed of scheduling.

[0070] In summary, this embodiment simulates the port material scheduling model by using a genetic algorithm to generate an optimal scheduling plan, and uses a fitness function to iteratively optimize the scheduling plan, thereby achieving efficient turnover of port materials.

[0071] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0076] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A port material dispatch simulation method for collaboration between ships and ground transport vehicles, characterized in that: The following steps are involved: Obtain historical information about vessels and ground transportation vehicles; Construct a port material scheduling model based on the relevant information obtained; Genetic algorithm is used to simulate the port material scheduling model; Generate a scheduling plan based on the simulation results; Monitor the implementation of the dispatching plan in real time, obtain the real-time status information of ships and ground transport vehicles through the sensor network, and use edge computing technology to process the real-time status information in real time to obtain real-time processing data; Dynamically adjust the scheduling plan based on real-time processing data; Visualize the scheduling plan; The step of obtaining historical information related to ships and ground transportation vehicles includes: Obtain the estimated arrival time of the ship, cargo type and quantity, and unloading time information, and store this information in the port database; Obtain information on the type, quantity, capacity, current location and availability of ground transportation vehicles and enter this information into the port database; Using sensor networks and GPS systems to monitor and update the location and status information of ground transportation vehicles in real time; Integrate all the information of ships and ground transport vehicles to obtain historical information related to ships and ground transport vehicles; The steps of constructing the port material scheduling model include: Analyze ship information and ground transportation vehicle information, and comprehensively consider the restrictions inside and outside the port; Analyze the acquired ship information and ground transportation vehicle information to establish a data set; A multi-objective optimization algorithm is used to optimize the data set and obtain a preliminary scheduling strategy; Generate forecast data by using time series analysis algorithms to predict vessel arrival times and ground transportation vehicle availability; The preliminary scheduling strategy obtained by the multi-objective optimization algorithm is combined with the forecast data to build a port material scheduling model; The restrictions inside and outside the port include: Berth quantity constraints Berth usage constraints Vehicle capacity constraints: Traffic congestion constraint: y kt ≤J t ; Where B represents the number of berths, j represents the number of berths, j = 1, 2, ..., B, N s Represents the total number of ships, i represents the ship number, i=1,2,...,N s , x ij is a decision variable, indicating whether the i-th ship berths at the j-th berth, N v represents the total number of ground transport vehicles, k represents the number of ground transport vehicles, k=1,2,...,N v , C k represents the transport capacity of the kth vehicle, t represents the number of the time period, t=1,2,...,T, T represents the total time period, Q t represents the demand for goods in the tth time period, y kt Indicates whether the kth ground transportation vehicle is used in the tth time period, J t Indicates the maximum number of vehicles allowed to pass through the road within time t; The step of simulating the port material scheduling model using a genetic algorithm comprises: The initial population is randomly generated, and each individual represents a scheduling plan; Generate a fitness function to calculate the minimum waiting time for ships, the maximum utilization rate of transport vehicles and the minimum material loading and unloading time; Use selection, crossover and mutation operations to iteratively optimize the scheduling scheme and obtain the best fitness function; The mathematical formula of the optimal fitness function is: Where α+β+γ=1, f(I) represents the fitness function, which is used to evaluate the overall scheduling scheme, α represents the weight of minimizing the waiting time of the ship, β represents the weight of maximizing the utilization rate of the transport vehicle, γ represents the weight of minimizing the material loading and unloading time, and W s represents the total waiting time of the ship, W max Indicates the maximum waiting time of the ship, U v represents the utilization rate of transport vehicles, U max represents the maximum utilization rate of transport vehicles, E m Represents the total material loading and unloading time, E max Indicates the maximum value of material loading and unloading time; The step of dynamically adjusting the scheduling scheme according to the real-time processing data includes: Genetic algorithms are used to evaluate the fitness of each generation of scheduling schemes in the simulation process, and the scheme with the highest fitness is selected as the current optimal scheme; Generate the unloading sequence of ships and the dispatching sequence of ground transport vehicles according to the current optimal plan; Generate detailed dispatch plans, including vessel berthing locations, unloading schedules, and transport vehicle dispatch routes and schedules.

2. A method for simulating port material dispatching in coordination with ships and ground transport vehicles as claimed in claim 1, characterized in that: The step of using edge computing technology to process real-time status information in real time includes: Using a sensor network to receive and process real-time status information, the real-time status information includes the location of the vessel, the location of the ground transportation vehicle, and the status of the cargo; Edge computing nodes are used to preprocess and analyze real-time status information, filter out noise data and extract key information.

3. The method for simulating port material dispatching in coordination with ships and ground transport vehicles as claimed in claim 1, characterized in that: The step of dynamically adjusting the scheduling scheme according to the real-time processing data includes: Use sensor networks to obtain real-time status information of ships and ground transportation vehicles; Perform data preprocessing and analysis on the received real-time status information to generate a real-time status report; Compare the expected status in the current dispatch plan with the actual status in the real-time status report and identify any deviations; Adjust the unloading sequence and berthing position of the vessel based on the identified deviations; Rearrange the dispatching routes and times of ground transportation vehicles to ensure that they match the adjusted ship unloading time; The multi-objective optimization algorithm is used to recalculate the optimal scheduling solution.

4. The method for simulating port material dispatching in coordination with ships and ground transport vehicles as claimed in claim 1, characterized in that: The visual display of the scheduling scheme includes: Visualize the optimal scheduling plan to show the unloading order of ships, the scheduling order of ground transportation vehicles and path planning; Dynamically display the real-time position and status of ships and ground transport vehicles on the visual interface; Charts and graphs are used to mark the ship's berthing position, unloading progress, cargo type and quantity information, and to distinguish various types of ground transport vehicles and their dispatch status; Provides interactive functions, allowing dispatchers to adjust the dispatch plan in real time by clicking and dragging.

Citation Information

Patent Citations

  • Two-way navigable port ship scheduling optimization method

    CN105117793A

  • Ship scheduling method under the condition of uncertain requirements

    CN108629485A

  • Vehicle-port-ship cooperative scheduling method and system

    CN111785028A

  • Ship-vehicle-box consistency coordination regulation and control method for sea-railway combined transportation of U-shaped wharf

    CN117391293A

  • KR20240062918A