Intelligent cargo collection system for aviation logistics

Through the intelligent cargo collection system of aviation logistics, combined with the K-means cluster decomposition and dimensionality reduction method, the cargo collection strategy is optimized, and the problem of inflexible cargo collection in traditional methods is solved, thus maximizing profits of aviation logistics companies and improving operational efficiency is achieved. .

CN119090374APending Publication Date: 2024-12-06GUILIN UNIVERSITY OF TECHNOLOGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410976721.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-21
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Air logistics companies need to quickly complete the collection of goods after completing orders, but traditional methods lack flexibility and calculate transportation weights based only on location, weight and volume, resulting in waste of resources and financial losses, affecting the signing of the capacity agreement.

Method used

An intelligent cargo collection system for air logistics is designed to generate flexible access order by calculating the transportation weights of transportation points. Combined with the K-means clustering decomposition and dimensionality reduction method, multi-objective optimization problems are optimized, and cargo types, locations, and fines are considered. Formulate reasonable cargo collection strategies such as factors such as air freight costs and special goods.

Benefits of technology

It has realized a rapid generation and feasible cargo collection strategy, improved the profits of air logistics companies by more than 8%, improved operational efficiency and flexibility, adapted to complex business environments, and enhanced operational capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090374A_ABST
    Figure CN119090374A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent cargo collection system for aviation logistics, and aims to solve the problem of travelers for freight collection in the field of aviation logistics. According to the system, the access sequence of the transportation points is quickly generated by utilizing the existing order and place data, so that the cost is minimized, and the efficiency is improved. The data of a certain logistics enterprise is used for preliminary testing, and the result shows that the cost of the system can be saved by more than 8%. Under the background of global economic acceleration and rapid growth of aviation logistics business, aviation logistics intelligent cargo collection becomes a key link. According to the system, factors such as cargo types, transportation point positions, penalty amount, air transportation cost, minimum cargo capacity, weight and volume of orders, special cargos and the like are comprehensively considered, and a transportation point access sequence with minimum cost is provided. Through the intelligent cargo collection and path planning system, an aviation logistics company can make a reasonable cargo collection strategy more accurately according to the order condition, and the overall benefit maximization is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent optimization, aims to meet the actual needs of the aviation logistics industry, and designs an intelligent cargo collection system for aviation logistics. Based on the capacity procurement agreement and current order status of the aviation logistics company, the system calculates the corresponding transportation weights of the transportation points to generate a set of high-quality access sequences for the type, weight, volume, location, route requirements and other information of the cargo in the order, so that the aviation logistics company can quickly collect and load the cargo at each location. By rationally allocating capacity and orders and customizing cargo collection strategies, the system helps aviation logistics companies increase profits. Background Art

[0002] In the current air logistics field, air logistics companies usually use traditional methods to solve the traveling salesman problem of cargo collection. However, this collection method has some limitations. It only calculates the transportation weight based on the location, weight and volume of the cargo, and lacks flexibility in solving the traveling salesman problem. Moreover, air logistics companies need to quickly complete cargo collection after reaching a certain number of orders. If the collection is not completed, it will not only waste transportation resources and cause financial losses, but also affect the signing of the company's next cycle capacity agreement.

[0003] Therefore, when air logistics companies reach a certain number of orders, they need to complete cargo collection flexibly and quickly, calculate the transportation weight based on the type of cargo, location of transportation points, amount of fines, air freight costs, minimum cargo load, order weight and volume, and special cargo, and formulate cargo collection strategies to improve efficiency and increase profits. In order to solve this problem, we conducted a detailed investigation and developed an air logistics intelligent cargo collection system.

[0004] Compared with the traditional transportation weight calculation and TSP solution method, the intelligent cargo collection system can quickly generate a flexible and feasible access sequence based on the existing order status and agreement data to maximize profits. Preliminary calculations using data from an aviation logistics company found that the use of this cargo collection system can increase profits by more than 8%.

[0005] With the acceleration of economic globalization and the rapid growth of air logistics business, the air logistics industry presents huge profit potential. In this context, intelligent cargo collection in air logistics has become a key link, involving multiple aspects such as the transportation resources purchased by air logistics companies and existing orders. The main goal of this system is to provide a flexible order of access to transportation points, taking into account information such as cargo type, transportation point location, fine amount, air freight cost, minimum cargo load, and order weight and volume, as well as special cargo and other factors. Through the intelligent cargo collection system, air logistics companies can more accurately formulate reasonable cargo collection strategies based on order conditions to maximize overall benefits. Summary of the invention

[0006] The implementation of the present invention is mainly divided into two parts: problem modeling and algorithm optimization.

[0007] 1. Problem Modeling

[0008] The intelligent cargo collection problem in air logistics requires calculating the transportation weight and planning the cargo collection strategy based on the transportation information and current order information. Transportation information includes the location of the transportation point, the amount of fines, air transportation costs, and the minimum cargo capacity. Current order information includes the type of cargo, order route, weight and volume, and special cargo. Based on this information, the transportation weight is calculated and the objective function is set to ensure that a feasible and high-quality cargo collection strategy is calculated. If customized adjustments are required according to specific requirements, the model can be flexibly modified to meet specific needs.

[0009] 2. Algorithm optimization

[0010] Intelligent cargo collection in aviation logistics involves multi-objective optimization problems and traveling salesman problems, that is, optimization problems with multiple conflicting objectives. In multi-objective optimization problems, optimizing the performance of one objective may have a significant negative impact on the performance of other objectives. Traditional mathematical optimization algorithms often have difficulty dealing with multi-objective optimization problems where the objective function is not differentiable or has no clear mathematical expression. Evolutionary algorithms have a natural advantage in solving multi-objective optimization problems because they do not need to make any assumptions about the problem. Therefore, evolutionary algorithms are used to solve multi-objective optimization problems.

[0011] The Traveling Salesman Problem (TSP) is a typical combinatorial optimization problem and an NP-hard problem. It refers to finding the order with the lowest cost to visit a given set of cities, where the travel distance (or travel cost) between cities is also given, and each city is required to be visited only once and return to the starting city. TSP has a wide range of applications in transportation, logistics, computer science and other fields. The three-dimensional traveling salesman problem (3D-TSP) is a generalization of the classic TSP problem. The solution algorithm of 3D-TSP is similar to that of the classic TSP. The only difference is the calculation of the distance matrix. It plays an important role in the field of forest fire patrol path planning and drone detection. Many existing studies focus on the shortest path of TSP in two-dimensional space. The shortest path in three-dimensional space has not been fully studied. Using genetic algorithm (GA) to solve TSP is a common method, in which the initial population determines the initial quality of the population, the parent generation crosses over to generate offspring, and the mutation operator maintains the diversity of individuals. For genetic algorithms, how to initialize a high-quality population plays an important role in solving the problem.

[0012] When using heuristic algorithms to solve TSP, the K-means clustering algorithm can be mixed with random generation methods to improve the quality of the initial population. Generate the number of clusters 𝑐𝑝 in the geometric problem space. The main idea is to first decompose the problem into 𝑐𝑝 sub-problems (classes), and then solve the optimal solution for each sub-problem, that is, to obtain the optimal sub-route, and then select two sub-routes to merge into a new sub-route, and so on, and finally get a complete route. Among them, the merging method can make the newly generated sub-route also optimal. The application of this method makes multi-objective optimization problems more reliable and feasible when solving TSP problems, which helps to optimize the efficiency of air logistics business and help air logistics companies increase profits.

[0013] Advantages of the present invention:

[0014] The intelligent cargo collection system for air logistics has significant advantages over traditional cargo collection methods. Compared with traditional transportation weight calculation and TSP solution methods, the system quickly generates flexible and feasible access sequences based on existing order conditions and transportation data, thereby maximizing profits. Secondly, the system uses a decomposition and dimensionality reduction method based on K-means clustering as the core technology to decompose the three-dimensional space, which can improve the quality of the algorithm population, reduce calculations, and quickly and effectively solve the cargo collection traveling salesman problem. In addition, the system is efficient and scalable, and can nest multiple transportation weight calculation strategies to adapt to different air logistics needs and complex business environments. In summary, the advantages of the intelligent cargo collection system for air logistics are flexibility, profit optimization, efficiency and scalability, which can help air logistics companies cope with market challenges, improve operational efficiency and increase profits. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of optimizing the cargo collection process.

[0016] Figure 2 It is a schematic diagram of the modeling process.

[0017] Figure 3 It is a schematic diagram of the solution process. DETAILED DESCRIPTION

[0018] This invention is an intelligent cargo collection system for air logistics. It conducts comprehensive analysis and intelligent optimization of the capacity agreements signed by air logistics companies and existing order information, and can determine the best cargo collection strategy. The system comprehensively considers information such as cargo type, transportation point location, fine amount, air freight cost, minimum cargo capacity, order weight and volume, and special cargo. It is modeled as a multi-objective optimization problem, and uses a decomposition and dimensionality reduction method based on K-means clustering to calculate a suitable cargo collection strategy to help air logistics companies increase profits.

[0019] The detailed steps are as follows:

[0020] Step 1: Input Data

[0021] Convert the relevant data into .mat files in advance and read them into the matlab buffer area.

[0022] Step 2: Problem Modeling

[0023] During the problem modeling phase, we determined the decision variables and objective function. The decision variables include the type of agreed flight, the size and weight limit of the cargo hold, the amount of the penalty, the air freight cost, the minimum cargo volume requirement, the weight and volume information of the current order, and the price per kilogram. Our goal is to achieve the lowest cargo collection cost.

[0024] In addition to determining the objective function, weight calculation is also required. The weight calculation needs to comprehensively consider the type of goods, location of transportation points, amount of fines, air freight costs, minimum cargo volume, and order weight and volume. Comprehensive consideration of multiple factors makes the weight value more reasonable. This model involves two objective functions, and our goal is to find the optimal cargo collection strategy that provides the lowest cost.

[0025] Through problem modeling, we can clearly describe the decision variables and objective functions of the problem, providing a basis for subsequent optimization solutions.

[0026] Step 3: Optimization solution

[0027] Using the decomposition and dimensionality reduction method based on K-means clustering for optimization and solution is an effective method. In the solution process, there are two main problems. First, calculating the entire weight matrix is ​​undoubtedly very time-consuming and computationally resource-intensive, and the path weight used in the end is only a small part of the distance matrix, so a considerable part of the obtained weight information is useless after obtaining the access order. When the demand points increase, the weights that need to be solved also increase significantly. Secondly, the quality of the population generated by the random initialization method is not high. As the iteration proceeds, the algorithm is more likely to fall into the local optimum. To deal with these problems, the decomposition and dimensionality reduction method based on K-means clustering can handle these two difficulties well, using the initialization population mechanism based on K-means clustering to improve the population quality. The decomposition and dimensionality reduction method projects the three-dimensional space where the transportation point is located to three planes for solution, omitting redundant weight calculations and greatly reducing the amount of calculation. Finally, by analyzing the solution set, a suitable cargo collection strategy is generated, which can help aviation logistics companies provide feasible and flexible cargo collection strategies.

Claims

1. A multi-objective aviation logistics intelligent cargo collection system, characterized in that TSP weights are complex and the access sequence is difficult to solve. The system includes: weight calculation module, optimization solution module, and intelligent collection module; The weight calculation module is used to establish the logical association of relevant data, calculate the weight problem of cargo collection, and construct the transportation point access sequence problem into a multi-objective optimization model; The optimization solution module is used to solve multi-objective optimization problems and perform algorithm optimization according to the established model to obtain the optimal solution set; The intelligent collection module is used to generate the best cargo collection strategy, further analyze the optimal solution set obtained in the optimization solution module, and generate a reasonable cargo collection strategy.

2. According to the multi-objective air logistics intelligent cargo collection system described in claim 1, the weight calculation module collects and associates the capacity agreements and existing order information signed by the air logistics company, constructs a model of the multi-objective optimization problem, comprehensively considers the type of cargo, location of the transportation point, amount of fines, air transportation costs, minimum cargo capacity, and order weight and volume and other information, derives the transportation weight and sets the objective function.

3. According to the multi-objective air logistics intelligent cargo collection system described in claim 1, the optimization solution module adopts a decomposition and dimensionality reduction method based on K-means clustering to solve the multi-objective optimization problem described in claim 1, decomposes the three-dimensional space in the solution process to reduce a large amount of calculations; and improves the population quality through the K-means clustering method to solve the established model in a targeted manner.

4. According to the multi-objective air logistics intelligent cargo collection system described in claim 1, the intelligent collection module optimizes the solution set and related data, generates the best cargo collection strategy, considers factors such as transportation weight, route demand, cargo weight and volume, takes into account freight indicators and penalty regulations, and provides a set of flexible and feasible access sequences according to the weight and volume limit range of the order to maximize the profit of the air logistics company.