Port multi-vehicle parallel scheduling optimization method considering storage yard priority

Abstract

The invention relates to a port multi-vehicle parallel scheduling optimization method considering storage yard priorities, and belongs to the field of port logistics optimization. The method comprises the following steps: carrying out initialization setting on ant colony algorithm parameters, genetic algorithm parameters, path calculation parameters and storage yard priorities; establishing a fitness function according to the transportation time, the oil consumption and the storage yard priority, and establishing a corresponding constraint condition to obtain a problem model; searching a path through an ant colony algorithm on the premise of combining the piling priority influence to obtain a path set; adopting a genetic algorithm, taking the obtained path set as an initial population, and obtaining an optimal solution after various mutation operations; and according to a calculation result of the optimal path, determining a specific driving path, a loading and unloading task and a time table of each vehicle. According to the method, the problems of insufficient path planning and insufficient multi-objective optimization in existing port logistics can be effectively solved, the port logistics efficiency is improved, and the energy consumption is reduced.

Description

Technical Field

[0001] The invention belongs to the field of port logistics optimization and relates to a port multi-vehicle parallel scheduling optimization method considering yard priority. Background Art

[0002] In modern port logistics management, vehicle scheduling optimization is a key issue to improve port transportation efficiency and reduce operating costs. Especially in large-scale cargo transportation and yard management, how to reduce waiting time, optimize transportation routes, reduce energy consumption and improve overall work efficiency through reasonable scheduling strategies has always been the focus of research and practice. Traditional port transportation vehicle scheduling mostly relies on manual planning or simple mathematical models. These methods often ignore complex factors in reality, such as route selection, transportation time, fuel consumption, number of turns, etc.

[0003] Currently, many related studies have involved the use of optimization algorithms for port vehicle scheduling. For example, the ant colony optimization algorithm (ACO) and the genetic algorithm (GA) have been widely used in solving vehicle path optimization problems. The ant colony algorithm can perform efficient global optimization in the search space by simulating the foraging process of ants, solving large-scale and complex vehicle scheduling problems that are difficult to handle with traditional scheduling methods. The genetic algorithm has a strong global optimization capability by simulating processes such as natural selection and gene crossover, and is suitable for finding the global optimal solution to the optimization problem.

[0004] However, there are also certain shortcomings and limitations in the existing technology, which are mainly reflected in the following aspects:

[0005] Path selection and scheduling efficiency: Traditional path optimization algorithms, such as the nearest neighbor algorithm and the greedy algorithm, are prone to fall into local optimality when dealing with multi-vehicle and multi-task scheduling problems and cannot effectively solve large-scale problems. As the scale of ports expands, a single scheduling algorithm often cannot meet the requirements of real-time performance and global optimality.

[0006] Insufficient trade-off between time and fuel consumption: Most existing optimization algorithms do not fully consider the balance between time and fuel consumption during transportation when calculating transportation routes, especially when multiple ships, yards, and transportation tasks are involved. Existing technologies usually focus on reducing one aspect of time or fuel consumption, while ignoring the comprehensive optimization of both aspects.

[0007] Influence of the number of turns: In the process of port vehicle scheduling, the number of turns has an important impact on transportation time and fuel consumption, but the existing optimization algorithm pays little attention to the number of turns, resulting in the actual effect of the scheduling scheme being far less than the theoretical optimization value in a complex port environment.

[0008] Traditional methods fail to fully consider multiple constraints such as the inventory situation at the yard, transportation priority, and fuel consumption, making it difficult to achieve optimal transportation efficiency and fuel consumption.

[0009] Problems and defects in the prior art

[0010] Local optimal solution problem: Existing path optimization algorithms often have difficulty overcoming the problem of local optimal solution. In vehicle scheduling at large-scale ports, traditional algorithms have difficulty handling complex constraints, such as scheduling problems with multiple vehicles, multiple tasks, multiple yards, multiple ships, and yard priorities, which may result in their calculation results being far from the global optimal solution.

[0011] Lack of comprehensive optimization model: Many existing technologies only focus on minimizing time or fuel consumption when considering vehicle scheduling, and fail to integrate these two factors into a unified optimization model. As a result, the optimization results may not have good applicability in practical applications and cannot achieve the best economic benefits.

[0012] Imperfect pheromone decay and update strategy: In the ant colony optimization algorithm, the decay and update of pheromones are key factors. However, in some existing technologies, the pheromone update strategy is too simple and fails to fully consider the multiple feedbacks and adjustments in the path optimization process, resulting in instability of the optimization results. Summary of the invention

[0013] In view of this, an object of the present invention is to provide a port multi-vehicle parallel scheduling optimization method considering yard priority.

[0014] In order to achieve the above object, the present invention provides the following technical solutions:

[0015] A method for optimizing parallel dispatching of multiple vehicles in a port considering yard priority, the method comprising the following steps:

[0016] S1. Initialize and set the ant colony algorithm parameters, genetic algorithm parameters, path calculation parameters and yard priority;

[0017] S2. Establish a fitness function based on transportation time, fuel consumption, and yard priority, and establish corresponding constraints to obtain a problem model;

[0018] S3, using the ant colony algorithm, searching for paths under the premise of combining the influence of stacking priorities, and obtaining a path set;

[0019] S4, using a genetic algorithm, taking the obtained path set as the initial population, and obtaining the optimal solution after multiple mutation operations;

[0020] S5. According to the calculation result of the optimal path, determine the specific driving path, loading and unloading tasks and schedule of each vehicle.

[0021] Further, in step S1, initializing the ant colony algorithm parameters includes: setting the size of the ant colony m, the initial value of the pheromone τ 0 , pheromone volatility ρ, heuristic factor α, pheromone weighting factor β, maximum number of iterations max_iterations;

[0022] Initializing genetic algorithm parameters includes: setting population size population_size, crossover probability p crossover , mutation probability p mutation , select strategy;

[0023] Initializing the path calculation related parameters includes: setting the maximum load, speed, loading and unloading time of the vehicle, setting the capacity of the yard, and the coordinates of the starting and ending points of the transportation path;

[0024] Initializing the yard priority parameters includes: assigning a priority to each yard based on the existing inventory of the yard, and the yard with a higher inventory will be given priority for delivery; the priority calculation method is:

[0025]

[0026] Where current_inventory i Indicates the current inventory of the yard, total_capacity i Indicates the yard capacity.

[0027] Further, in step S2, the following steps are included:

[0028] S21, calculate the Euclidean distance dist(i,j) between each point of the port and establish a distance matrix;

[0029] S22, constructing a fitness function based on transportation time, fuel consumption, and yard priority factors as the optimization target of the ant colony algorithm and the genetic algorithm;

[0030] S23. The established constraints include:

[0031] Vehicle capacity restrictions: The cargo volume of each vehicle cannot exceed the maximum capacity;

[0032] Yard capacity limit: The inventory of each yard shall not exceed its maximum capacity;

[0033] Path constraints: Vehicles must operate in a specific order.

[0034] Furthermore, the fitness function considers the impact of the yard priority and weights it in the following way:

[0035]

[0036] Among them, time_cost(path) is the transportation time on the path, fuel_cost(path) is the fuel consumption on the path, priority_score i is the priority of yard i, ω i is the weighting coefficient of yard i, reflecting the actual impact of priority;

[0037] Further, in step S3, the process of searching the path by the ant colony algorithm is as follows:

[0038] S31, initialize the position of the ants at the starting point, each ant selects the next site according to the pheromone and heuristic information, and gradually builds the path; when selecting the next site, combined with the yard priority, give priority to the yard with large inventory or urgent demand; the ant path selection formula is:

[0039]

[0040] Among them, τ ij is the pheromone concentration of path i to j, η ij is the heuristic information, i.e., the inverse of the distance or the weighted value of the yard priority; next_possible indicates the node that the ant may choose at the current node i, and k indicates the next node selected by the ant;

[0041] S32. Weighting the priorities of the storage yards to ensure that the storage yards with higher priorities have a greater probability in path selection. The selection probability is adjusted as follows:

[0042]

[0043] Among them, priority_weight(j) is the priority weighted value of yard j;

[0044] S33. The path is continuously updated within the set number of iterations, and the ants gradually concentrate on the optimal path.

[0045] Further, in step S4, the process of determining the optimal solution in the path set by the genetic algorithm is as follows:

[0046] S41, initializing the initial population of the genetic algorithm according to the search results of the ant colony algorithm, each individual represents a possible path; the selection of the initial individuals is biased towards selecting a yard with a high priority according to the yard priority, thereby increasing the proportion of this type of path;

[0047] S42, using a crossover operation to generate a new individual, that is, exchanging the path parts of two parent individuals to generate a new child individual;

[0048] S43, performing mutation operation on individuals;

[0049] S44, evaluate the fitness of each individual in the population, calculate the weighted value of the transportation time and fuel consumption factors of each path, and consider the impact of the yard priority;

[0050] S45. Perform multiple generations of iterations, continuously optimize the path plan, and finally obtain the optimal solution.

[0051] Further, in step S42, the crossover operation formula is:

[0052] path new =path 1 [0:crossover_point]+path 2 [0:crossover_point]

[0053] Where crossover_point represents the location of the intersection; path 1 and path 2 They represent the paths of different parent individuals respectively;

[0054] In step S43, two points in the path are randomly exchanged to generate a new variant path. Let i and j be the indexes of two different nodes in the path, and i≠j. Then the mutated path path mutated It can be expressed as:

[0055] path mutated =(p 1 , p 2 , ..., p i-1 , p i , p i+1 , ..., p j-1 , p j , p j+1 , ..., p n )

[0056] Further, in step S5, the optimized logistics time is calculated as follows: by calculating the travel time of the vehicle from the starting point to the end point and considering the fixed time t required for each loading loading , optimize the total time during transportation:

[0057]

[0058] In the formula, dist(i, i+1) represents the distance between two nodes, v represents the speed of the forklift, and n represents the number of loading and unloading times;

[0059] The optimized fuel consumption calculation method is: the fuel consumption is calculated based on the vehicle's travel distance and number of turns. total Including vehicle fuel consumption pedistance Fuel consumption in corneringper_turn , the fuel consumption calculation formula is:

[0060]

[0061] The optimized calculation formula for the number of turns is:

[0062]

[0063] In the formula, segment i and segment i+1 They represent the horizontal and vertical coordinate positions of the current node and the next node of the forklift respectively. When both are equal, the number of turns increases by one.

[0064] The beneficial effects of the present invention are:

[0065] 1. Improve transportation efficiency and optimize energy consumption

[0066] The present invention optimizes both time and fuel consumption, effectively reducing fuel consumption while ensuring the shortest transportation time, thereby improving overall transportation efficiency. Traditional path optimization often only focuses on a single goal (such as the shortest path) and ignores fuel consumption and other operating costs. The present invention optimizes through comprehensive multi-objective optimization, greatly improving the overall efficiency of the port logistics system.

[0067] 2. Consider practical constraints and optimize feasibility

[0068] In path planning, the present invention takes into account actual constraints such as transportation volume, yard capacity, and ship cargo volume, ensuring the feasibility of the path planning results. In practical applications, the system can dynamically adjust the path to avoid infeasible paths or inability to complete tasks due to unsatisfied constraints, ensuring the practicality of the optimization results.

[0069] 3. Improve the path planning accuracy between yards

[0070] The present invention can find the optimal connection path between multiple yards by considering the increase in the number of yards, combining global path optimization with transportation route planning between local yards. No matter how complex the distribution of yards is, the system can ensure that the path planning is still accurate in an environment with a large number of yards by combining the updated pheromone matrix with the genetic algorithm, avoiding the problem of lengthy or unreasonable paths caused by the long distance between yards in traditional methods.

[0071] 4. Optimization capability of multi-vehicle collaborative operation

[0072] When there are many yards, the scheduling of multiple vehicles between different yards becomes more complicated. The present invention combines genetic algorithm and ant colony algorithm to enable multiple vehicles to work together efficiently and reasonably allocate transportation tasks. The coordination and path planning between vehicles are optimized, which can minimize the empty load and waiting time of vehicles in a multi-yard environment, thereby improving the overall transportation efficiency.

[0073] 5. Optimize yard management and cargo dispatch

[0074] The introduction of yard priority enables the system to dispatch according to the inventory situation of each yard, so as to better manage the yard inventory while meeting the transportation demand and avoid the situation where the yard is overcrowded or empty. The dynamic adjustment of yard priority enables the system to adjust the priority according to actual demand, improving the flexibility and accuracy of cargo distribution.

[0075] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0077] Figure 1 It is a schematic diagram of the overall process of the port multi-vehicle parallel scheduling optimization method considering the yard priority of the present invention;

[0078] Figure 2 A schematic diagram of a port yard in an embodiment;

[0079] Figure 3 A schematic diagram of fitness change during the iteration process of a hybrid algorithm in an embodiment;

[0080] Figure 4 A schematic diagram showing a fuel consumption comparison between a hybrid algorithm with iterative output and other algorithms in an embodiment;

[0081] Figure 5 A schematic diagram showing a comparison of logistics time between a hybrid algorithm with iterative output and other algorithms under an embodiment;

[0082] Figure 6 A schematic diagram showing a comparison of the number of turns of a hybrid algorithm with iterative output and other algorithms under an embodiment;

[0083] Figure 7The figure is a schematic diagram for comparing the optimal results of a hybrid algorithm and other algorithms under an embodiment. DETAILED DESCRIPTION

[0084] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0085] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0086] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0087] See also Figure 1 to Figure 7 , which is a multi-vehicle parallel scheduling optimization method for ports considering yard priority.

[0088] In the prior art, vehicle path planning usually only considers a single objective (such as time or fuel consumption), but fails to comprehensively consider multiple factors such as time and fuel consumption, resulting in unsatisfactory optimization results. In addition, when dealing with complex path planning problems, traditional algorithms are prone to fall into local optimal solutions and cannot obtain global optimal solutions. The present invention proposes a multi-objective optimization method based on a combination of genetic algorithm and ant colony algorithm, which can dynamically adjust the vehicle path based on comprehensive consideration of transportation time and fuel consumption to minimize the total transportation time and fuel consumption, while improving the efficiency of task completion.

[0089] The technical solution of the present invention uses the pheromone update mechanism, the crossover and mutation operations of the genetic algorithm, and the comprehensive evaluation function to enable vehicles to perform cargo transportation tasks more efficiently in a complex port environment, achieve multi-objective optimization, effectively solve the shortcomings of traditional methods, and provide a more flexible and efficient path optimization solution.

[0090] like Figure 1 As shown, the multi-vehicle parallel scheduling optimization method for ports considering yard priority of the present invention specifically includes the following steps:

[0091] S1. Initialize and set the ant colony algorithm parameters, genetic algorithm parameters, path calculation parameters and yard priority;

[0092] S2. Establish a fitness function based on transportation time, fuel consumption, and yard priority, and establish corresponding constraints to obtain a problem model;

[0093] S3, using the ant colony algorithm, searching for paths under the premise of combining the influence of stacking priorities, and obtaining a path set;

[0094] S4, using a genetic algorithm, taking the obtained path set as the initial population, and obtaining the optimal solution after multiple mutation operations;

[0095] S5. According to the calculation result of the optimal path, determine the specific driving path, loading and unloading tasks and schedule of each vehicle.

[0096] In step S1 of this embodiment, initializing the ant colony algorithm parameters includes: setting the size of the ant colony m (i.e., the number of ants), the initial value of the pheromone τ 0 , pheromone volatility ρ, heuristic factor α (weight affecting heuristic information), pheromone weighting factor β (weight affecting path selection). The maximum number of iterations per time is max_iterations.

[0097] Initializing genetic algorithm parameters includes: setting population size population_size, crossover probability p crossover , set the mutation probability p mutation , set the selection strategy (roulette wheel selection).

[0098] Initializing the path calculation related parameters includes: setting the vehicle's maximum load, speed, loading and unloading time and other parameters, the yard's capacity, the coordinates of the starting and ending points of the transportation path, etc.

[0099] Initializing the yard priority parameters includes assigning a priority to each yard based on the existing inventory of the yard. The yard with higher inventory should be delivered first. The priority is calculated as follows:

[0100]

[0101] Where current_inventory i Indicates the current inventory of the yard, total_capacity i Indicates the yard capacity.

[0102] In step S2 of this embodiment, the following steps are specifically included:

[0103] S21, calculate the distance matrix: calculate the Euclidean distance dist(i, j) between various points in the port (such as ships, storage yards, garages, etc.) and establish a distance matrix;

[0104] S22. A fitness function is constructed based on factors such as transportation time, fuel consumption, and yard priority as the optimization target of the ant colony algorithm and the genetic algorithm. The fitness function takes into account the impact of the yard priority and is weighted in the following way:

[0105]

[0106] Among them, time_cost(path) is the transportation time on the path, fuel_cost(path) is the fuel consumption on the path, priority_score i is the priority of yard i, ω i is the weighting coefficient of yard i, reflecting the actual impact of priority.

[0107] S23. The established constraints include: Vehicle capacity limit: The cargo load of each vehicle cannot exceed the maximum capacity.

[0108] Yard capacity limit: The inventory volume of each yard shall not exceed its maximum capacity.

[0109] Path constraints: Vehicles must operate in a specific order.

[0110] In step S3 of this embodiment, the process of searching the path by the ant colony algorithm is as follows:

[0111] S31. Initialize the position of the ant at the starting point (garage). Each ant selects the next site based on pheromone and heuristic information, and gradually builds the path. When selecting the next site, the yard priority is combined to give priority to yards with large inventory or urgent demand. The specific approach is to assign a higher probability to the yard when selecting the path, so that the possibility of path selection is greater.

[0112] Path selection formula:

[0113]

[0114] Among them, τ ij is the pheromone concentration of path i to j, ηij is the heuristic information, i.e., the inverse of the distance or the weighted value of the yard priority; next_possible indicates the node that the ant may choose at the current node i, and k indicates the next node selected by the ant.

[0115] S32. Determine the impact of yard priority on path selection: Weight the priority of the yard to ensure that the yard with a high priority has a greater probability in path selection. Adjust the selection probability:

[0116]

[0117] Among them, priority_weight(j) is the priority weighted value of yard j.

[0118] S33. The path is continuously updated within the set number of iterations, and the ants gradually converge on the optimal path.

[0119] In step S4 of this embodiment, the process of determining the optimal solution in the path set by using the genetic algorithm is as follows:

[0120] S41, Individual initialization: Initialize the initial population of the genetic algorithm based on the search results of the ant colony algorithm, and each individual represents a possible path. The selection of the initial individuals will be biased towards the yard with a high priority according to the yard priority, increasing the proportion of this type of path;

[0121] S42, crossover operation: Use the crossover operation to generate a new individual, that is, exchange the path parts of two parent individuals to generate a new child individual. The crossover operation formula is:

[0122] path new =path 1 [0:crossover_point]+path 2 [0:crossover_point]

[0123] Where crossover_point represents the location of the intersection; path 1 and path 2 They represent the paths of different parent individuals.

[0124] S43, mutation operation: Perform mutation operation on individuals, randomly exchange the positions of two points in the path, and increase the diversity of solutions. The mutation operation formula is:

[0125] path mutated =path original with two points swapped

[0126] S44, fitness evaluation: Perform fitness evaluation on each individual (path) in the population, calculate the weighted values ​​of factors such as transportation time and fuel consumption for each path, and consider the impact of yard priority.

[0127] S45. Perform multiple generations of iterations, continuously optimize the path plan, and finally obtain the optimal solution.

[0128] In step S5 of this embodiment, the specific driving path, loading and unloading tasks and schedule of each vehicle are determined based on the calculation results of the optimal path. The high-priority yard will be scheduled first. Verify whether the result meets the constraints, such as the transportation task of each vehicle, yard capacity, etc.

[0129] Calculate the total transportation time, fuel consumption and other indicators after optimization, and conduct comparative analysis of the results.

[0130] Time optimization: by calculating the travel time of the vehicle from the starting point to the end point and taking into account the fixed time t required for each loading loading , optimize the total time during transportation:

[0131]

[0132] Fuel consumption optimization: Calculate fuel consumption based on the distance traveled and the number of turns, and optimize the route to reduce fuel consumption. total Including vehicle fuel consumption perdistance Fuel consumption in cornering per_turn , the fuel consumption calculation formula is:

[0133]

[0134] The formula for calculating the number of turns is:

[0135]

[0136] In general, the present invention proposes the following:

[0137] Multi-objective optimization model: Combines the two objectives of time and fuel consumption, and optimizes them comprehensively through weighted method to avoid the deviation caused by single-objective optimization.

[0138] Improved ant colony algorithm: Improves the ability to search for the global optimal solution through the volatilization and strengthening mechanism of pheromones.

[0139] Genetic algorithm crossover and mutation: Use crossover and mutation operations to increase the diversity of path combinations and improve global search capabilities.

[0140] Introduction of yard priority: The present invention assigns a priority to each yard according to the inventory situation of the yard. In the process of path selection and scheduling, the yard with large inventory is given priority to ensure that the yard with high priority is served first.

[0141] Weighted yard priority in path selection: In the path selection process of the ant colony algorithm, the weighted calculation of the yard priority is added to enhance the consideration of the yard priority in path selection. In the path selection formula, the yard priority affects the selection probability of vehicle scheduling, thereby improving the scheduling efficiency of high-priority yards.

[0142] Integration of fitness evaluation and crossover and mutation operations: In the genetic algorithm, path crossover and mutation operations are used to continuously optimize the path through multiple generations of iterations, thereby improving the quality of the scheduling results. During the crossover process, the path selection is biased towards the yard with higher priority, thereby performing efficient optimization search in the solution space.

[0143] Adapt to constraints: Consider actual constraints such as transportation volume and yard capacity to ensure the feasibility of the optimization plan.

[0144] Multi-vehicle collaborative scheduling: Optimize the paths of multiple vehicles carrying out transportation tasks simultaneously to improve overall transportation efficiency.

[0145] Through the above technical scheme, the present invention can effectively solve the problems of insufficient path planning and insufficient multi-objective optimization in existing port logistics, and provide a new, multi-objective optimization path planning method, which improves the efficiency of port logistics and reduces energy consumption.

[0146] In this embodiment, the algorithm of the present invention is run in Windows 10, 64-bit system, Python 3.11 environment, and a batch of unloading cases at a port are used as examples to determine the vehicle scheduling plan through experimental analysis. Figure 2 , According to the model and algorithm programming, the initial parameter information is set as shown in Table 1.

[0147] Table 1

[0148] Yard quantity 20 Single yard capacity 1500t berth 3 Vessel deadweight per berth 7500t Pheromone Volatilization Rate 0.5 Forklift load 10t Initial pheromone value 1 Forklift speed 18km / h Mutation rate 0.1 Number of forklifts 5 Average loading and unloading time 6min Fuel consumption per unit distance 0.1L Fuel consumption per turn 0.5L Time Weight 0.6 Fuel consumption weight 0.4

[0149] The fitness of the iterative process obtained by programming is as follows Figure 3 According to the change of fitness, it shows that the algorithm converges quickly and has high stability. The output of each iteration is as follows Figure 4-6 As shown, Figure 4 It is a schematic diagram comparing the fuel consumption of the hybrid algorithm of the present invention, the traditional method and the ant colony algorithm. Figure 5 It is a schematic diagram of logistics time comparison between the hybrid algorithm of the present invention, the traditional method and the ant colony algorithm; Figure 6 It is a schematic diagram comparing the number of turns of the hybrid algorithm of the present invention, the traditional method and the ant colony algorithm.

[0150] Depend on Figure 4-6It can be seen that the logistics time obtained in the 9th iteration is the shortest and the fuel consumption is the lowest. The lowest number of turns obtained in each iteration is 81 times. Therefore, the optimal path generated by the 9th iteration result is selected.

[0151] Figure 7 The schematic diagram of the comparison of the optimal results of the three optimization algorithms is shown. It can be seen that the ant colony and genetic hybrid algorithms of the present invention are the best in terms of the number of turns, fuel consumption, logistics time, etc.

[0152] Table 2 shows the optimization results of different algorithms:

[0153] Table 2

[0154] Traditional methods Ant Colony Algorithm Hybrid Ant Colony Genetic Algorithm Logistics time (min) 3654.00 2119.22 1995.23 Number of turns (times) 450 120 81 Fuel consumption(L) 1706.7 384.58 265.98

[0155] Combined with the optimization results in Table 2, the hybrid ant colony genetic algorithm shows significant advantages in logistics time, number of turns and fuel consumption. Compared with the traditional method, the algorithm reduces the logistics time from 3654 units to 1995.23 units, significantly improves the loading and unloading efficiency, reduces the waiting time for goods and site congestion; the number of turns is reduced from 450 to 81, reducing the difficulty of forklift operation and mechanical loss in complex paths; fuel consumption is reduced from 1706.7 units to 265.98 units, saving a lot of fuel costs, while reducing carbon emissions, in line with the development goals of green ports. In practical applications, the hybrid ant colony genetic algorithm can be embedded in the port intelligent scheduling system to dynamically generate the optimal path according to the real-time location of the forklift, the cargo stacking point and the yard layout. This can not only improve the operating efficiency, but also reduce the repeated operation and empty driving rate of the forklift, further reduce the operating cost and enhance the competitiveness of the port. Through the optimization of this algorithm, the timber port can achieve high-quality development with both efficiency and environmental protection, which is an important step in achieving intelligent and sustainable operations.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing parallel dispatching of multiple vehicles in a port considering yard priority, characterized by: The method comprises the following steps: S1. Initialize and set the ant colony algorithm parameters, genetic algorithm parameters, path calculation parameters and yard priority; S2. Establish a fitness function based on transportation time, fuel consumption, and yard priority, and establish corresponding constraints to obtain a problem model; S3, using the ant colony algorithm, searching for paths under the premise of combining the influence of stacking priorities, and obtaining a path set; S4, using a genetic algorithm, taking the obtained path set as the initial population, and obtaining the optimal solution after multiple mutation operations; S5. According to the calculation result of the optimal path, determine the specific driving path, loading and unloading tasks and schedule of each vehicle.

2. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 1, characterized in that: In step S1, the parameters of the ant colony algorithm are initialized, including: setting the size of the ant colony m, the initial value of the pheromone τ0, the pheromone volatility rate ρ, the heuristic factor α, the weighting factor β of the pheromone, and the maximum number of iterations max_iterations; Initializing genetic algorithm parameters includes: setting population size population_size, crossover probability p crossover , mutation probability p mutation , select strategy; Initializing the path calculation related parameters includes: setting the maximum load, speed, loading and unloading time of the vehicle, setting the capacity of the yard, and the coordinates of the starting and ending points of the transportation path; Initializing the yard priority parameters includes: assigning a priority to each yard based on the existing inventory of the yard, and the yard with a higher inventory will be given priority for delivery; the priority calculation method is: Where current_inventory i Indicates the current inventory of yard i, total_capacity i represents the capacity of yard i.

3. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 2, characterized in that: In step S2, the following steps are included: S21, calculate the Euclidean distance dist(i,j) between each point of the port and establish a distance matrix; S22, constructing a fitness function based on transportation time, fuel consumption, and yard priority factors as the optimization target of the ant colony algorithm and the genetic algorithm; S23. The established constraints include: Vehicle capacity restrictions: The cargo volume of each vehicle cannot exceed the maximum capacity; Yard capacity limit: The inventory of each yard shall not exceed its maximum capacity; Path constraints: Vehicles must operate in a specific order.

4. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 3 is characterized in that: The fitness function considers the impact of the yard priority and weights it in the following way: Among them, time_cost(path) is the transportation time on the path, fuel_cost(path) is the fuel consumption on the path, priority_score i is the priority of yard i, ω i is the weighted coefficient of yard i, reflecting the actual impact of priority.

5. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 3 is characterized in that: In step S3, the process of searching the path by the ant colony algorithm is as follows: S31, initializing the position of the ants at the starting point, each ant selects the next site according to the pheromone and heuristic information, and gradually constructs the path; When selecting the next site, the ant takes into account the priority of the yard and gives priority to the yard with large inventory or urgent demand. The ant's path selection formula is: Among them, τ ij is the pheromone concentration of path i to j, η ij is the heuristic information, i.e., the inverse of the distance or the weighted value of the yard priority; next_possible indicates the node that the ant may choose at the current node i, and k indicates the next node selected by the ant; S32. Weighting the priorities of the storage yards to ensure that the storage yards with higher priorities have a greater probability in path selection. The selection probability is adjusted as follows: Among them, priority_weight(j) is the priority weighted value of yard j; S33. The path is continuously updated within the set number of iterations, and the ants gradually concentrate on the optimal path.

6. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 5, characterized in that: In step S4, the process of determining the optimal solution in the path set by genetic algorithm is as follows: S41, initializing the initial population of the genetic algorithm according to the search results of the ant colony algorithm, each individual represents a possible path; the selection of the initial individuals is biased towards selecting a yard with a high priority according to the yard priority, thereby increasing the proportion of this type of path; S42, using a crossover operation to generate a new individual, that is, exchanging the path parts of two parent individuals to generate a new child individual; S43, performing mutation operation on individuals; S44, evaluate the fitness of each individual in the population, calculate the weighted value of the transportation time and fuel consumption factors of each path, and consider the impact of the yard priority; S45. Perform multiple generations of iterations, continuously optimize the path plan, and finally obtain the optimal solution.

7. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 6, characterized in that: In step S42, the crossover operation formula is: path new =path1[0:crossover_point]+path2[0:crossover_point] In the formula, crossover_point represents the crossover point; path1 and path2 represent the paths of different parent individuals respectively; In step S43, two points in the path are randomly exchanged to generate a new variant path. Let i and j be the indexes of two different nodes in the path, and i≠j. Then the mutated path path mutated It is expressed as: path mutated =(p1,p2,...,p i-1 ,p i ,p i+1 ,...,p j-1 ,p j ,p j+1 ,...,p n )。 8. The method for optimizing the parallel dispatch of multiple vehicles in a port considering the priority of a storage yard according to claim 6, characterized in that: In step S5, the optimized logistics time is calculated as follows: by calculating the travel time of the vehicle from the starting point to the end point and considering the fixed time t required for each loading loading , optimize the total time during transportation: In the formula, dist(i,i+1) represents the distance between two nodes, v represents the speed of the forklift, and n represents the number of loading and unloading times; The optimized fuel consumption calculation method is: the fuel consumption is calculated based on the vehicle's travel distance and number of turns. total Including vehicle fuel consumption perdistance Fuel consumption in cornering per_turn , the fuel consumption calculation formula is: The optimized calculation formula for the number of turns is: In the formula, segment i and segment i+1 They represent the horizontal and vertical coordinates of the current node and the next node where the forklift is located respectively. When the two are not equal, the number of turns increases by one.

Images