Method and system for allocating berths in uncertain environment of bulk cargo terminal

Abstract

The invention belongs to the technical field of bulk cargo wharf berth distribution, and particularly relates to a berth distribution method and system in an uncertain environment of a bulk cargo wharf. The method comprises the following steps: firstly, obtaining an initial scheduling plan by using an FCFS method which is based on manual scheduling experience and considers berth preference for a berth allocation problem in uncertain environments such as meteorological conditions and the health degree of loading and unloading equipment, and carrying out calculation and prediction analysis on the loading and unloading efficiency of the loading and unloading equipment by using a deep learning algorithm of LSTM; a scheduling plan is calculated by a heuristic method of a genetic algorithm, algorithm parameter selection is carried out by taking a fitness function as an evaluation basis, the influence of two uncertain factors, namely meteorological conditions and equipment health degree, on berth allocation is analyzed, and analysis is carried out through multiple instance scales, so that the berth allocation efficiency is improved. And finally, obtaining an optimal solution of berth allocation in the uncertain environment of the bulk cargo wharf.

Description

Technical Field

[0001] The present application belongs to the technical field of berths at bulk cargo terminals, and specifically relates to a berth allocation method and system in an uncertain environment at a bulk cargo terminal. Background Art

[0002] In bulk cargo terminals, the berth allocation process is more manual, and many operating processes and procedures need to be completed by manual operation. Manual operation takes a long time to complete the arrangement and scheduling of tasks, and is easily affected by human factors, resulting in low efficiency. It can often only adapt to tasks and situations within a certain range and is difficult to cope with complex and changing scenarios. At the same time, it is also prone to omissions or incomplete considerations, resulting in low accuracy in task scheduling. The application of new technologies such as heuristic algorithms and machine learning algorithms in scheduling to achieve intelligent scheduling is different from traditional manual scheduling methods. It can greatly improve berth utilization and reduce resource waste, which is of great significance to the efficient operation of bulk cargo terminals.

[0003] Intelligent terminal scheduling refers to the process of breaking through the traditional methods of manual scheduling and static scheduling during the loading and unloading of goods, and realizing dynamic and intelligent scheduling management of complex terminal operation processes. It is a dynamic scheduling process. In the field of intelligent terminal scheduling research, there are relatively many studies on intelligent scheduling of container terminals. The core issues of intelligent scheduling of container terminals are container truck scheduling and yard optimization. In the field of intelligent scheduling research of bulk cargo terminals, the core issues of scheduling are berth allocation and yard allocation. Domestic research on intelligent scheduling of bulk cargo terminals is still in its infancy, and there are relatively few related literatures. Most of the results have not yet been put into practical application in bulk cargo terminals. At present, domestic bulk cargo terminals are actively carrying out automation and intelligent exploration to provide support for the realization of intelligent berth allocation. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a bulk cargo terminal berth allocation optimization method and system, which can improve the bulk cargo terminal berth utilization efficiency and reduce operating costs.

[0005] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0006] A berth allocation method in an uncertain environment of a bulk cargo terminal comprises the following steps:

[0007] According to the pre-constructed berth allocation objective function and constraints, a mixed integer linear programming mathematical model for berth allocation optimization is established;

[0008] A genetic algorithm is used to solve the mixed integer linear programming model of berth allocation, and a long short-term memory network (LSTM) deep learning algorithm is used to solve the loading and unloading efficiency of each loading and unloading equipment under two uncertain environments of meteorology and equipment health; and an optimization plan for berth allocation is obtained;

[0009] The berth allocation objective function is constructed and obtained according to the predetermined berth allocation optimization requirements; the constraint conditions include bulk carrier arrival time conflict constraint, berth and loading sequence conflict constraint, ship and berth matching constraint and ship time constraint;

[0010] The LSTM deep learning algorithm is used to solve the loading and unloading efficiency of the bulk ship loading and unloading equipment.

[0011] Preferably, the berth allocation objective function is constructed and obtained according to the predetermined berth allocation optimization requirements, including: the delay cost of the ship, the loading and unloading cost of the ship, and the sum of the two is the ship operation cost; the corresponding objective function is constructed with the lowest bulk carrier operation cost as the goal, and the objective function expression is as follows:

[0012]

[0013] In formula (1), represents the average service cost per unit time of bulk carrier i; represents the average delay cost per unit time of bulk carrier i; z itm Binary variable, if the ship is served by the loading and unloading gantry crane m in period t, the variable value is 1, otherwise it is 0; ldc i represents the loading and unloading completion time of bulk carrier i; ETD i It represents the estimated departure time of bulk carrier i.

[0014] Preferably, the berth and loading sequence conflict constraints include: berth position constraint, berthing time later than arrival time constraint, total number of loading and unloading equipment constraint, number of loading and unloading equipment allocated to a single ship constraint, the same loading and unloading equipment only serves one ship in the same time period constraint, only one ship is berthed at the same position of the berth at the same time constraint, the relative position of two ships at the same time does not overlap constraint, and the berthing time of two ships does not overlap constraint, and the corresponding constraint expressions are:

[0015] POS i +L i +s≤Len,i∈V (2)

[0016] In formula (2), pos i represents the berthing position of bulk carrier i, i∈V; L irepresents the length of bulk carrier i, i∈V; s represents the safety distance between bulk carriers in the berth (constant); Len represents the total length of the bulk carrier terminal berth (constant); V represents the set of bulk carriers to be berthed; Formula (2) ensures that the allocated berth position is within the total length of the berth;

[0017] T max ≥ldc i ≥ bt i ≥ETA i ,i∈V (3)

[0018] In formula (3), T max Indicates the end time of the planning time period; bt i Indicates the berthing time of bulk carrier i; ETA i represents the estimated arrival time of bulk carrier i; Formula (3) ensures that the allocated loading and unloading completion time and berthing time are within the planned time period, and ensures that the ship berthing time is later than the arrival time;

[0019] ∑ i ∑ m z itm ≤M max ,i∈C,t∈T,m∈M (4)

[0020] In formula (4), M max represents the maximum number of loading and unloading gantry cranes; M represents the set of loading and unloading gantry cranes that can be allocated to bulk carriers; Formula (4) ensures that the number of loading and unloading equipment in operation at any time does not exceed the total number of loading and unloading equipment;

[0021]

[0022] In formula (5), The minimum number of loading and unloading gantry cranes assigned to ship i, i and greater than or equal to 1; The maximum number of loading and unloading gantry cranes allocated to ship i is less than or equal to the number of cargo holds of bulk carrier i; Formula (5) ensures that the number of loading and unloading equipment allocated to the ship is within the minimum and maximum number;

[0023] ∑ i z itm ≤1,i∈V,t∈T,m∈M (6)

[0024] Formula (6) ensures that the same loading and unloading equipment only serves one ship in the same time period;

[0025] POS i +L i +s≤pos j +N(1-y ij ),i,j∈V (7)

[0026] In formula (7), pos i ,pos j Respectively represent the berthing positions of bulk carriers i and j; N represents a very large constant; y ij represents a binary variable, which takes the value of 1 when the berthing position of ship i∈V is on the left side of ship j∈V, otherwise it takes the value of 0; Formula (7) ensures that only one ship is berthed at the same position on the berth at the same time;

[0027] y ij +y ji ≤1,i,j∈V (8)

[0028] Formula (8) ensures that the relative positions of two ships at the same berthing time do not overlap;

[0029] bt i +ldc i -lds i ≤ bt j +N(1-x ij ),i,j∈V (9)

[0030] In formula (9), lds i represents the loading and unloading start time of bulk carrier i, i∈V; bt j represents the berthing time of bulk carrier i, i∈V; x ij represents a binary variable. If the berthing time of i∈V is earlier than that of j∈V, it takes the value of 1, otherwise it takes the value of 0. Formula (9) ensures that the loading and unloading tasks of two bulk carriers at the same berthing position can be completed normally. N is a super large constant.

[0031] x ij +x ji ≤1,i,j∈V (10)

[0032] Formula (10) ensures that the berthing times of the two ships do not overlap;

[0033] y ij +y ji +x ij +x ji ≤1,i,j∈V (11)

[0034] Formula (11) ensures that there will be no overlap of ships at the same shoreline location at the same time.

[0035] Preferably, the genetic algorithm is used to solve the mixed integer linear programming model for optimizing berth allocation at bulk cargo terminal, comprising:

[0036] Step (1): The berthing position, berthing time, and number of assigned loading and unloading equipment of each bulk carrier are taken as decision variables, and the decision variables of all ships are encoded to form a genetic encoding of a two-dimensional array matrix;

[0037] Step (2): Initialize the genetic code according to the artificial experience FCFS to generate an initial population;

[0038] Step (3): Calculating the fitness of the initial population, and selecting the population using a roulette wheel method to form a paired parent generation;

[0039] Step (4): performing crossover and mutation operations on the paired parent generations to generate a new population;

[0040] Step (5): performing gene repair on the new population according to the constraint conditions;

[0041] Step (6): Return to step (3) and continue iterating until the error requirement is met and the optimal solution is obtained.

[0042] Preferably, performing gene repair on the new population according to the constraint conditions comprises:

[0043] Step (51): Determine whether the gene value of the bulk carrier berthing position in the chromosome is in [0, Len-L i ], if so, execute step (52); otherwise, randomly generate a new gene value within the range, and then execute step (52);

[0044] Step (52): The gene value of the berthing time assigned to the bulk carrier in the chromosome is in the range [0, T max ], if so, execute step (53); otherwise, randomly generate a new gene value within the range, and then execute step (53);

[0045] Step (54): Determine whether the gene value of the number of loading and unloading equipment allocated to bulk carriers in the chromosome is If it is within the range, no gene repair is performed; otherwise, a new gene value is randomly generated within the range to complete the gene repair process.

[0046] Preferably, the method comprises the following steps:

[0047] Step (1): Select meteorological factors that affect the efficiency of bulk cargo ship loading and unloading equipment, including wind speed, wind direction, visibility and precipitation; select equipment factors that affect the efficiency of bulk cargo ship loading and unloading equipment, including equipment type, bulk cargo type and equipment health;

[0048] Step (2): Determine the network structure of the input gate, output gate, and forget gate of the LSTM model, and determine the hyperparameters of the model through grid search;

[0049] Step (3): Obtain the forecast information of meteorological factors within the time period to be allocated through the existing meteorological information service system of the port; obtain the health information of each loading and unloading equipment within the time period to be allocated through the existing equipment life cycle management system of the port;

[0050] Step (4): Perform pre-processing operations such as data cleaning and data normalization on the three categories of historical data, measured data, and predicted data of bulk terminal loading and unloading operations, environment, and equipment status;

[0051] Step (5): Based on the historical data of each loading and unloading equipment, the LSTM model is trained to predict the ship loading and unloading efficiency under different meteorological factors and different equipment influencing factors;

[0052] Step (6): Based on the predicted loading and unloading efficiency and the loading and unloading volume of the bulk carrier, the corresponding loading and unloading time is calculated, and then the loading and unloading operation cost is calculated, and the objective function value of the entire berth allocation scheme is evaluated, thereby realizing the optimization of berth allocation.

[0053] A bulk cargo terminal berth allocation system includes a ship information acquisition module, a weather forecast analysis module, an equipment health monitoring module, a berth allocation module, and a data storage module; wherein:

[0054] Ship information acquisition module: The ship information acquisition module is used to obtain information such as the arrival time and planned departure time of bulk carriers, ship length, draft depth, cargo type, cargo capacity, planned loading and unloading capacity, etc.

[0055] Weather forecast analysis module: The weather forecast analysis module provides weather conditions at the terminal during the planning period, and analyzes and predicts the loading and unloading efficiency of port machinery and equipment based on the entry and exit time of bulk cargo ships and current weather information;

[0056] Equipment health monitoring module: The equipment health monitoring module provides information about the loading and unloading equipment on the dock side within the planned time, and predicts the loading and unloading efficiency of port machinery equipment based on the previous loading and unloading efficiency and the health of the current equipment;

[0057] Berth allocation module: The berth allocation module analyzes the berths suitable for bulk carriers to dock according to the acquired ship information and allocates them;

[0058] Data storage module: The data storage module stores bulk carrier data, meteorological data, equipment efficiency data, and production operation data during the operation process, and exchanges information with the port production scheduling system.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] In order to solve the berth allocation problem under uncertain environment such as meteorological conditions and the health of loading and unloading equipment, the FCFS method based on manual scheduling experience and berth preference is used to obtain the initial scheduling plan. The LSTM deep learning algorithm is used to calculate and predict the loading and unloading efficiency of loading and unloading equipment. The genetic algorithm heuristic method is used to calculate the scheduling plan. The fitness function is used as the evaluation basis for the selection of algorithm parameters. The impact of two uncertain factors, meteorological conditions and equipment health, on berth allocation is analyzed, and the analysis is carried out through multiple instance scales. Finally, the optimal solution for berth allocation under uncertain environment of bulk cargo terminal is obtained. For engineering application, a berth allocation system is developed to realize the application verification of this method. The berth allocation system software coordinates the work between various functional modules to achieve unified management and scheduling of multiple tasks such as ships entering and leaving the port, scheduling, and production, which greatly reduces the difficulty and workload of manual berth allocation and scheduling. Compared with manual scheduling, the error rate is low and the efficiency is improved, which effectively avoids the increase in operating costs caused by unreasonable manual scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of a mathematical model for berth allocation of bulk cargo terminals taking into account uncertain factors provided by an embodiment of the present invention;

[0062] Figure 2 is a flow chart of a bulk cargo terminal berth allocation optimization method provided by an embodiment of the present invention;

[0063] Figure 3 It is a flow chart of a method for solving a mixed integer linear programming model for berth allocation optimization of a bulk cargo terminal using a genetic algorithm provided by an embodiment of the present invention;

[0064] Figure 4 It is a flow chart of a method for gene repair when a berth allocation scheme does not meet constraint conditions provided by an embodiment of the present invention;

[0065] Figure 5 This is a comparison chart of the prediction results of ship loading and unloading efficiency of LSTM and RNN neural networks provided in an embodiment of the present invention;

[0066] Figure 6 It is a schematic diagram of iterative convergence of genetic algorithm hyperparameter settings provided by an embodiment of the present invention;

[0067] Figure 7 It is a schematic diagram of berth allocation optimization results of a bulk cargo terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The technical solution of the present invention is described in detail below through specific embodiments and drawings. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application, and the specific technical features can be combined with each other.

[0069] A berth allocation method in an uncertain environment of a bulk cargo terminal comprises the following steps:

[0070] According to the pre-constructed berth allocation objective function and constraints, a mixed integer linear programming mathematical model for berth allocation optimization is established;

[0071] A genetic algorithm is used to solve the mixed integer linear programming model of berth allocation, and LSTM is used to solve the loading and unloading efficiency of each loading and unloading equipment under two uncertain environments of meteorology and equipment health; and an optimization plan for berth allocation is obtained;

[0072] The berth allocation objective function is constructed and obtained according to the predetermined berth allocation optimization requirements; the constraint conditions include bulk carrier arrival time conflict constraint, berth and loading sequence conflict constraint, ship and berth matching constraint and ship time constraint;

[0073] The LSTM deep learning algorithm is used to solve the loading and unloading efficiency of the bulk ship loading and unloading equipment.

[0074] The berth allocation objective function is constructed and obtained according to the predetermined berth allocation optimization requirements, including: the delay cost of the ship, the loading and unloading cost of the ship, and the sum of the two is the ship operation cost; the corresponding objective function is constructed with the lowest bulk carrier operation cost as the goal, and the objective function expression is as follows:

[0075]

[0076] In formula (1), represents the average service cost per unit time of bulk carrier i; represents the average delay cost per unit time of bulk carrier i; z itm Binary variable, if the ship is served by the loading and unloading gantry crane m in period t, the variable value is 1, otherwise it is 0; ldc i represents the loading and unloading completion time of bulk carrier i; ETD i It represents the estimated departure time of bulk carrier i.

[0077] The berth and loading sequence conflict constraints include: berth position constraint, berthing time later than arrival time constraint, total number of loading and unloading equipment constraint, number of loading and unloading equipment allocated to a single ship constraint, the same loading and unloading equipment only serves one ship in the same time period, only one ship is berthed at the same position of the berth at the same time, the relative positions of two ships at the same time do not overlap, and the berthing time of two ships does not overlap. The corresponding constraint expressions are:

[0078] POS i +L i +s≤Len,i∈V (2)

[0079] In formula (2), pos i represents the berthing position of bulk carrier i, i∈V; L i represents the length of bulk carrier i, i∈V; s represents the safety distance between bulk carriers in the berth (constant); Len represents the total length of the bulk carrier terminal berth (constant); V represents the set of bulk carriers to be berthed; Formula (2) ensures that the allocated berth position is within the total length of the berth;

[0080] T max ≥ldc i ≥ bt i ≥ETA i ,i∈V (3)

[0081] In formula (3), T max Indicates the end time of the planning time period; bt i represents the berthing time of bulk carrier i, i∈V; ETA i represents the estimated arrival time of bulk carrier i, i∈V. Formula (3) ensures that the allocated loading and unloading completion time and berthing time are within the planned time period, and ensures that the ship berthing time is later than the arrival time;

[0082] ∑ i ∑ m z itm ≤M max ,i∈V,t∈T,m∈M (4)

[0083] In formula (4), M max represents the maximum number of loading and unloading gantry cranes; M represents the set of loading and unloading gantry cranes that can be assigned to bulk carriers. Formula (4) ensures that the number of loading and unloading equipment in operation at any time does not exceed the total number of loading and unloading equipment;

[0084]

[0085] In formula (5), The minimum number of loading and unloading gantry cranes assigned to ship i, i∈V, and greater than or equal to 1; The maximum number of loading and unloading gantry cranes assigned to ship i, i∈V, is less than or equal to the number of cargo holds of bulk carrier i. Formula (5) ensures that the number of loading and unloading equipment assigned to a ship is within the minimum and maximum number;

[0086] ∑ i z itm ≤1,i∈V,t∈T,m∈M (6)

[0087] Formula (6) ensures that the same loading and unloading equipment only serves one ship in the same time period;

[0088] POS i +L i +s≤pos j +N(1-y ij ),i,j∈V (7)

[0089] In formula (7), pos i ,pos j Respectively represent the berthing positions of bulk carriers i and j; N represents a very large constant; y ij It represents a binary variable. When the berthing position of ship i∈V is on the left side of ship j∈V, it takes the value of 1, otherwise it takes the value of 0. Formula (7) ensures that only one ship is berthed at the same position on the berth at the same time;

[0090] y ij +y ji ≤1,i,j∈V (8)

[0091] Formula (8) ensures that the relative positions of two ships at the same berthing time do not overlap;

[0092] bt i +ldc i -lds i ≤ bt j +N(1-x ij ),i,j∈V (9)

[0093] In formula (9), lds i represents the loading and unloading start time of bulk carrier i, i∈V; bt j represents the berthing time of bulk carrier i, i∈V; x ji represents a binary variable. If the berthing time of i∈V is earlier than that of j∈V, it takes the value of 1, otherwise it takes the value of 0. Formula (9) ensures that the loading and unloading tasks of two ships at the same berthing position can be completed normally. N is a super large constant;

[0094] x ij +x ji ≤1,x,j∈V (10)

[0095] Formula (10) ensures that the berthing times of the two ships do not overlap;

[0096] y ij +y ji +x ji +x ji ≤1,i,j∈V (11)

[0097] Formula (11) ensures that there will be no overlap of ships at the same shoreline location at the same time.

[0098] The method of using a genetic algorithm to solve the mixed integer linear programming model for berth allocation optimization of bulk cargo terminal includes:

[0099] Step (1): The berthing position, berthing time, and number of assigned loading and unloading equipment of each bulk carrier are taken as decision variables, and the decision variables of all ships are encoded to form a genetic encoding of a two-dimensional array matrix;

[0100] Step (2): Initialize the genetic code according to the artificial experience FCFS to generate an initial population;

[0101] Step (3): Calculating the fitness of the initial population, and selecting the population using a roulette wheel method to form a paired parent generation;

[0102] Step (4): performing crossover and mutation operations on the paired parent generations to generate a new population;

[0103] Step (5): performing gene repair on the new population according to the constraint conditions;

[0104] Step (6): Return to step (3) and continue to iterate until the error requirement is met and the optimal solution is formed. The gene repair of the new population according to the constraint conditions includes:

[0105] Step (51): Determine whether the gene value of the bulk carrier berthing position in the chromosome is in [0, Len-L i ], if so, execute step (52); otherwise, randomly generate a new gene value within the range, and then execute step (52);

[0106] Step (52): The gene value of the berthing time assigned to the bulk carrier in the chromosome is in the range [0, T max ], if so, execute step (53); otherwise, randomly generate a new gene value within the range, and then execute step (53);

[0107] Step (54): Determine whether the gene value of the number of loading and unloading equipment allocated to bulk carriers in the chromosome is If it is within the range, no gene repair is performed; otherwise, a new gene value is randomly generated within the range to complete the gene repair process.

[0108] The LSTM model berth allocation optimization includes the following steps:

[0109] Step (1): Select meteorological factors that affect the efficiency of bulk cargo ship loading and unloading equipment, including wind speed, wind direction, visibility and precipitation; select equipment factors that affect the efficiency of bulk cargo ship loading and unloading equipment, including equipment type, bulk cargo type and equipment health;

[0110] Step (2): Determine the network structure of the input gate, output gate, and forget gate of the LSTM model, and determine the hyperparameters of the model through grid search;

[0111] Step (3): Obtain the forecast information of meteorological factors within the time period to be allocated through the existing meteorological information service system of the port; obtain the health information of each loading and unloading equipment within the time period to be allocated through the existing equipment life cycle management system of the port;

[0112] Step (4): Perform pre-processing operations such as data cleaning and data normalization on the three categories of historical data, measured data, and predicted data of bulk terminal loading and unloading operations, environment, and equipment status;

[0113] Step (5): Based on the historical data of each loading and unloading equipment, the LSTM model is trained to predict the ship loading and unloading efficiency under different meteorological factors and different equipment influencing factors;

[0114] Step (6): Based on the predicted loading and unloading efficiency and the loading and unloading volume of the bulk carrier, the corresponding loading and unloading time is calculated, and then the loading and unloading operation cost is calculated, and the objective function value of the entire berth allocation scheme is evaluated, thereby realizing the optimization of berth allocation.

[0115] A bulk cargo terminal berth allocation system of a method includes a ship information acquisition module, a weather forecast analysis module, an equipment health monitoring module, a berth allocation module, and a data storage module; wherein:

[0116] Ship information acquisition module: The ship information acquisition module is used to obtain information such as the arrival time and planned departure time of bulk carriers, ship length, draft depth, cargo type, cargo capacity, planned loading and unloading capacity, etc.

[0117] Weather forecast analysis module: The weather forecast analysis module provides weather conditions at the terminal during the planning period, and analyzes and predicts the loading and unloading efficiency of port machinery and equipment based on the ship's entry and exit time and current weather information;

[0118] Equipment health monitoring module: The equipment health monitoring module provides information about the loading and unloading equipment on the dock side within the planned time, and predicts the loading and unloading efficiency of port machinery equipment based on the previous loading and unloading efficiency and the health of the current equipment;

[0119] Berth allocation module: The berth allocation module analyzes the berths suitable for ships to dock according to the acquired ship information and allocates them;

[0120] Data storage module: The data storage module stores the ship data, meteorological data, equipment efficiency data, and production operation data during the operation process, and exchanges information with the port production scheduling system.

[0121] Figure 2 This is a flow chart of a bulk cargo terminal berth allocation optimization method in Example 1 of the present invention. This flow chart shows the logical sequence of the method described in this embodiment. The method can be executed by a bulk cargo terminal berth allocation system software platform, and the software can be installed in a high-performance computer device such as a server or a workstation. The method of this implementation specifically includes the following steps:

[0122] Step (1): Based on the constructed bulk terminal berth allocation objective function and constraints, a mixed integer linear programming model for berth allocation optimization is established;

[0123] Step (2): Use the LSTM algorithm to predict the efficiency of the loading and unloading equipment and obtain the loading and unloading efficiency of each bulk cargo loading and unloading equipment serving the bulk cargo ship during working hours;

[0124] Step (3): using a genetic algorithm to solve the berth allocation optimization mixed integer linear programming model to obtain a bulk carrier berth allocation plan;

[0125] Among them, the bulk carrier berth allocation objective function is constructed according to actual needs; the constraints mainly include bulk carrier arrival time conflict constraints, berth and loading sequence conflict constraints, ship and berth matching constraints and ship time constraints.

[0126] It should be understood that the berth allocation optimization requirements and the constraints can be adjusted according to the actual conditions such as the business processes, business types, and user preferences of different bulk cargo terminals.

[0127] Embodiment 2:

[0128] like Figure 4 As shown in the figure, based on uncertain factors such as the meteorological conditions of the bulk cargo terminal and the health of the equipment, the efficiency of the loading and unloading equipment is predicted based on LSTM. The specific implementation steps are as follows:

[0129] Step (1): Select meteorological factors that affect the efficiency of bulk carrier loading and unloading equipment; mainly including wind speed, wind direction, visibility, and precipitation, a total of 4 factors;

[0130] Step (2): Select equipment influencing factors that affect the efficiency of bulk cargo ship loading and unloading equipment; mainly including equipment type, bulk cargo type, and equipment health, a total of 3 factors;

[0131] Step (3): Determine the network structure of the input gate, output gate, and forget gate of the LSTM model, and determine various hyperparameters of the model through grid search or other methods;

[0132] Step (4): Obtain the meteorological factor forecast information within the allocated time period through the existing meteorological information service system of the port.

[0133] Step (5): Obtain the health information of each loading and unloading equipment within the allocated time period through the port's existing equipment life cycle management system.

[0134] Step (6): Perform pre-processing operations such as data cleaning and data normalization on the three categories of historical data, measured data, and predicted data, including bulk terminal loading and unloading operations, environment, and equipment status.

[0135] Step (7): Based on the historical data of each loading and unloading equipment, the LSTM model is trained to predict the ship loading and unloading efficiency under different meteorological factors and different equipment influencing factors.

[0136] Step (8): Based on the predicted loading and unloading efficiency and the loading and unloading volume of the bulk carrier, the corresponding loading and unloading time is calculated, and then the loading and unloading operation cost is calculated, and the objective function value of the entire berth allocation scheme is evaluated, thereby realizing the optimization of berth allocation.

[0137] Embodiment three:

[0138] like Figure 3 As shown in the figure, according to the genetic rules to process the objective function and constraints, a genetic algorithm is designed to solve the mixed integer linear programming model for berth allocation optimization of bulk cargo terminals. The specific implementation steps are as follows:

[0139] Step (1): The berthing position, berthing time, and number of assigned loading and unloading equipment of each bulk carrier are taken as decision variables, and the decision variables of all ships are encoded to form a genetic encoding of a two-dimensional array matrix;

[0140] Step (2): Initializing the genetic code according to the FCFS considering the berth preference based on artificial experience to generate an initial population;

[0141] Step (3): Calculating the fitness of the initial population, and selecting the population using a roulette wheel method to form a paired parent generation;

[0142] Step (4): performing crossover and mutation operations on the paired parent generations to generate a new population;

[0143] Step (5): performing gene repair on the new population according to the constraint conditions;

[0144] Step (6): Return to step (3) and continue iterating until the error requirement is met and the optimal solution is obtained.

[0145] Embodiment 4:

[0146] The present invention provides a bulk cargo terminal berth allocation software system, the system comprising five modules:

[0147] Module 1: Ship information acquisition module, used to obtain information such as bulk carrier’s port entry time and planned port departure time, ship length, draft, cargo type, cargo capacity, planned loading and unloading capacity, etc.

[0148] Module 2: Weather forecast analysis module, which provides weather conditions at the terminal during the planning period, and analyzes and predicts the loading and unloading efficiency of port machinery and equipment based on the ship's entry and exit time and current weather information;

[0149] Module 3: Equipment health monitoring module, which provides the status of the loading and unloading equipment on the dock side within the planned time, and predicts the loading and unloading efficiency of port machinery equipment based on the previous loading and unloading efficiency and the health of the current equipment;

[0150] Module 4: Berth allocation module, which analyzes the berths suitable for ships to dock according to the acquired ship information and allocates them;

[0151] Module 5: Data storage module, which stores the ship data, meteorological data, equipment efficiency data, and production operation data during the operation process, and exchanges information with the port production scheduling system.

[0152] When the software system program is executed by a processor, the steps of the method described in Embodiments 1 to 3 are implemented.

[0153] The following is a verification of the method provided by the embodiment of the invention in combination with the specific data of a large bulk cargo terminal. This embodiment is coded based on the Python language and analyzes the scenario of 9 bulk cargo ships at consecutive berths. The berth water depth meets the ship draft requirements. The ship information is shown in Table 1 below, the loading and unloading gantry crane equipment information is shown in Table 2, and the weather forecast information for the next 36 hours is shown in Table 3:

[0154] Table 1

[0155]

[0156]

[0157] Table 2

[0158]

[0159] Table 3

[0160]

[0161] The comparison of the prediction results of ship loading and unloading efficiency between LSTM and RNN neural networks provided by the embodiment of the present invention is shown in the figure Figure 5 shown.

[0162] The population size of the genetic algorithm is set to 50, the number of iterations is set to 200, the crossover probability is set to 0.8, and the mutation probability is set to 0.01. The schematic diagram of the iterative convergence of the genetic algorithm is shown in Figure 6 Taking a bulk cargo terminal as an example, the berth length is 1200m, the planning time is 120h, and there are 9 ships. The schematic diagram of the optimization result of the berth allocation of the bulk cargo terminal is as follows: Figure 7 shown.

[0163] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A berth allocation method in an uncertain environment of a bulk cargo terminal, characterized in that: The following steps are involved: According to the pre-constructed berth allocation objective function and constraints, a mixed integer linear programming mathematical model for berth allocation optimization is established; A genetic algorithm is used to solve the mixed integer linear programming model of berth allocation, and a deep learning algorithm of a long short-term memory network (LSTM) is used to solve the loading and unloading efficiency of each loading and unloading equipment under two uncertain environments of meteorology and equipment health; and an optimization plan for berth allocation is obtained; The berth allocation objective function is constructed and obtained according to the predetermined berth allocation optimization requirements; the constraint conditions include bulk carrier arrival time conflict constraint, berth and loading sequence conflict constraint, ship and berth matching constraint and ship time constraint; LSTM is used to solve the loading and unloading efficiency of the bulk ship loading and unloading equipment.

2. The berth allocation method in an uncertain environment of a bulk cargo terminal according to claim 1 is characterized in that: The berth allocation objective function is constructed and obtained according to the predetermined berth allocation optimization requirements, including: the delay cost of the ship, the loading and unloading cost of the ship, and the sum of the two is the ship operation cost; the corresponding objective function is constructed with the lowest bulk carrier operation cost as the goal, and the objective function expression is as follows: In formula (1), represents the average service cost per unit time of bulk carrier i; represents the average delay cost per unit time of bulk carrier i; z itm Binary variable, if the ship is served by the loading and unloading gantry crane m in period t, the variable value is 1, otherwise it is 0; ldc i represents the loading and unloading completion time of bulk carrier i; ETD i It represents the estimated departure time of bulk carrier i.

3. The berth allocation method in an uncertain environment of a bulk cargo terminal according to claim 1, characterized in that: The berth and loading sequence conflict constraints include: berth position constraint, berthing time later than arrival time constraint, total number of loading and unloading equipment constraint, number of loading and unloading equipment allocated to a single ship constraint, the same loading and unloading equipment only serves one ship in the same time period, only one ship is berthed at the same position of the berth at the same time, the relative positions of two ships at the same time do not overlap, and the berthing time of two ships does not overlap. The corresponding constraint expressions are: pos i +L i +s≤Len,i∈V (2) In formula (2), pos i represents the berthing position of bulk carrier i, i∈V; L i represents the length of bulk carrier i, i∈V; s represents the safe distance between bulk carriers in the berth; Len represents the total length of the bulk terminal berth; V represents the set of bulk carriers to be berthed; Formula (2) ensures that the allocated berth position is within the total length of the berth; T max ≥ldc i ≥bt i ≥ETA i ,i∈V (3) T max Indicates the end time of the planning time period; bt i represents the berthing time of bulk carrier i, i∈V; ETA i represents the estimated arrival time of bulk carrier i, i∈V; Formula (3) ensures that the assigned loading and unloading completion time and berthing time are within the planned time period, ensuring that the ship berthing time is later than the arrival time; ∑ i ∑ m With itm ≤M max ,i∈V,t∈T,m∈M (4) In formula (4), M max represents the maximum number of loading and unloading gantry cranes; M represents the set of loading and unloading gantry cranes that can be allocated to bulk carriers; Formula (4) ensures that the number of loading and unloading equipment in operation at any time does not exceed the total number of loading and unloading equipment; In formula (5), The minimum number of loading and unloading gantry cranes assigned to ship i, i∈V, and greater than or equal to 1; The maximum number of loading and unloading gantry cranes assigned to ship i, i∈V, is less than or equal to the number of cargo holds of bulk carrier i; Formula (5) ensures that the number of loading and unloading equipment assigned to the ship is within the minimum and maximum number; ∑ i With itm ≤1,i∈V,t∈T,m∈M (6) Formula (6) ensures that the same loading and unloading equipment only serves one ship in the same time period; pos i +L i +s≤pos j +N(1-y ij ),i,j∈V (7) In formula (7), pos i ,pos j Respectively represent the berthing positions of bulk carriers i and j; N represents a very large constant; y ij represents a binary variable, which takes the value of 1 when the berthing position of ship i∈V is on the left side of ship j∈V, otherwise it takes the value of 0; Formula (7) ensures that only one ship is berthed at the same position on the berth at the same time; and ij +y ji ≤1, i, j∈V (8) Formula (8) ensures that the relative positions of two ships at the same berthing time do not overlap; bt i +ldc i -lds i ≤bt j +N(1-x ij ),i,j∈V (9) In formula (9), lds i represents the loading and unloading start time of bulk carrier i, i∈V; bt j represents the berthing time of bulk carrier i, i∈V; x ij represents a binary variable. If the berthing time of i∈V is earlier than that of j∈V, it takes the value of 1, otherwise it takes the value of 0. Formula (9) ensures that the loading and unloading tasks of two bulk carriers at the same berthing position can be completed normally. N is a super large constant. x ij +x ji ≤1,i,j∈V (10) Formula (10) ensures that the berthing times of the two ships do not overlap; and ij +y ji +x ij +x ji ≤1, i, j∈V (11) Formula (11) ensures that there will be no overlap of ships at the same shoreline location at the same time.

4. The bulk cargo terminal berth allocation optimization method according to claim 3, characterized in that: The method of using a genetic algorithm to solve the mixed integer linear programming model for berth allocation optimization of bulk cargo terminal includes: Step (1): The berthing position, berthing time, and number of assigned loading and unloading equipment of each bulk carrier are taken as decision variables, and the decision variables of all ships are encoded to form a genetic encoding of a two-dimensional array matrix; Step (2): Initialize the genetic code according to the artificial experience FCFS to generate an initial population; Step (3): Calculating the fitness of the initial population, and selecting the population using a roulette wheel method to form a paired parent generation; Step (4): performing crossover and mutation operations on the paired parent generations to generate a new population; Step (5): performing gene repair on the new population according to the constraint conditions; Step (6): Return to step (3) and continue iterating until the error requirement is met and the optimal solution is obtained.

5. The bulk cargo terminal berth allocation optimization method according to claim 4, characterized in that: The performing gene repair on the new population according to the constraint conditions comprises: Step (51): Determine whether the gene value of the bulk carrier berthing position in the chromosome is in [0, Len-L i ], if so, execute step (52); otherwise, randomly generate a new gene value within the range, and then execute step (52); Step (52): The gene value of the berthing time assigned to the bulk carrier in the chromosome is in the range [0, T max ], if so, execute step (53); otherwise, randomly generate a new gene value within the range, and then execute step (53); Step (54): Determine whether the gene value of the number of loading and unloading equipment allocated to bulk carriers in the chromosome is If it is within the range, no gene repair is performed; otherwise, a new gene value is randomly generated within the range to complete the gene repair process.

6. The bulk cargo terminal berth allocation optimization method according to claim 1, characterized in that: The following steps are involved: Step (1): Select meteorological factors that affect the efficiency of bulk carrier loading and unloading equipment, including wind speed, wind direction, visibility and precipitation; The equipment influencing factors that affect the efficiency of bulk cargo ship loading and unloading equipment include equipment type, bulk cargo type and equipment health; Step (2): Determine the network structure of the input gate, output gate, and forget gate of the LSTM model, and determine the hyperparameters of the model through grid search; Step (3): Obtain the forecast information of meteorological factors within the time period to be allocated through the existing meteorological information service system of the port; obtain the health information of each loading and unloading equipment within the time period to be allocated through the existing equipment life cycle management system of the port; Step (4): Perform pre-processing operations such as data cleaning and data normalization on the three categories of historical data, measured data, and predicted data of bulk terminal loading and unloading operations, environment, and equipment status; Step (5): Based on the historical data of each loading and unloading equipment, the LSTM model is trained to predict the ship loading and unloading efficiency under different meteorological factors and different equipment influencing factors; Step (6): Based on the predicted loading and unloading efficiency and the loading and unloading volume of the bulk carrier, the corresponding loading and unloading time is calculated, and then the loading and unloading operation cost is calculated, and the objective function value of the entire berth allocation scheme is evaluated, thereby realizing the optimization of berth allocation.

7. A bulk cargo terminal berth allocation system based on the method according to any one of claims 1 to 6, characterized in that: It includes ship information acquisition module, weather forecast analysis module, equipment health monitoring module, berth allocation module and data storage module; among which: Ship information acquisition module: The ship information acquisition module is used to obtain information such as the arrival time and planned departure time of bulk carriers, ship length, draft depth, cargo type, cargo capacity, planned loading and unloading capacity, etc. Weather forecast analysis module: The weather forecast analysis module provides weather conditions at the terminal during the planning period, and analyzes and predicts the loading and unloading efficiency of port machinery and equipment based on the entry and exit time of bulk cargo ships and current weather information; Equipment health monitoring module: The equipment health monitoring module provides the status of the loading and unloading equipment on the dock side within the planned time, and predicts the loading and unloading efficiency of port machinery equipment based on the previous loading and unloading efficiency and the current health status of the equipment; Berth allocation module: The berth allocation module analyzes the berths suitable for bulk carriers to dock according to the acquired ship information and allocates them; Data storage module: The data storage module stores bulk carrier data, meteorological data, equipment efficiency data, and production operation data during the operation process, and exchanges information with the port production scheduling system.

Images