Material stacking method and system based on multi-target genetic algorithm

Abstract

The invention discloses a material stacking method and system based on a multi-target genetic algorithm. The method comprises the following steps: after material information is obtained, performing one-to-one correspondence on a material stacking scheme and chromosomes in a multi-target genetic algorithm; calculating corresponding fitness for the material stacking scheme of each chromosome; comparing the non-dominated relations among the chromosomes, and selecting individuals superior to other chromosomes on at least one target to carry out crossover and variation; and an optimal material stacking scheme is determined after crossing and variation. The overall efficiency and safety of logistics circulation in the production and manufacturing process are improved, and more efficient and reliable automatic material management is achieved.

Description

Technical Field

[0001] The present invention relates to the field of palletizing, and more specifically, to a material stacking method and system based on a multi-objective genetic algorithm. Background Art

[0002] In the material stacking process of modern manufacturing, traditional automation solutions usually focus on the stacking of materials of the same size in the current operation, and the main consideration is the optimal position of the material on the pallet. Although this method can effectively improve the stacking density of a single pallet, it usually ignores the stacking strategy of materials of different sizes on the entire pallet at the same time, which may result in suboptimal overall utilization of the pallet space.

[0003] Therefore, it is necessary to develop a material stacking method and system based on multi-objective genetic algorithm.

[0004] The information disclosed in the background technology section of the present invention is only intended to deepen the understanding of the general background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0005] The present invention proposes a material stacking method and system based on a multi-objective genetic algorithm, which can improve the overall efficiency and safety of logistics flow in the production process and achieve more efficient and reliable automated material management.

[0006] In a first aspect, an embodiment of the present disclosure provides a material stacking method based on a multi-objective genetic algorithm, comprising:

[0007] After obtaining the material information, the material stacking plan is matched one by one with the chromosomes in the multi-objective genetic algorithm;

[0008] Calculate the corresponding fitness for each chromosome's material stacking scheme;

[0009] Compare the non-dominance relationship between chromosomes, and select individuals that are superior to other chromosomes in at least one goal for crossover and mutation;

[0010] The optimal material stacking plan is determined after crossover and mutation.

[0011] Preferably, the chromosome is encoded in a vector format, each element of which includes the location, direction and size information of the material.

[0012] Preferably, the fitness includes space utilization and stability. The space utilization and stability of the material stacking scheme are calculated, and their weighted sum is the fitness.

[0013] Preferably, the space utilization is:

[0014]

[0015] Among them, l i 、w i 、h i are the length, width and height of the i-th material; L T , W T , H T It is the length, width and height of the pallet.

[0016] Preferably, the stability is:

[0017]

[0018] Among them, z cg is the height of the center of gravity of the material stack, H T is the height of the tray, z i and m i are the center height and mass of the i-th material respectively.

[0019] Preferably, the intersection is:

[0020] Two chromosomes are randomly selected and parts of their genes are exchanged at multiple random positions to generate a new chromosome that contains characteristics of both parents.

[0021] Preferably, the variation is:

[0022] At least one gene in certain chromosomes is randomly selected and adjusted.

[0023] In a second aspect, the embodiment of the present disclosure further provides a material stacking system based on a multi-objective genetic algorithm, comprising:

[0024] Data collection module, used to collect material information;

[0025] The multi-objective genetic algorithm module is used to execute the material stacking method based on the multi-objective genetic algorithm to obtain the optimal material stacking plan;

[0026] The mechanical execution module is used to transport and stack the materials to the designated location according to the material stacking plan.

[0027] Preferably, the data acquisition module comprises a measurement sensor and a barcode scanner,

[0028] The measuring sensor includes a depth camera and a weighing sensor for measuring the size and weight of the material in real time, and the barcode scanner is used to scan the barcode on the material to obtain the identification information of the material.

[0029] Preferably, the mechanical execution module includes a robot arm, an automatic conveying component and a scheduling control component.

[0030] The robot's arm end effector can adapt to materials of different shapes and sizes;

[0031] The scheduling control component receives and initializes the material stacking plan, and the materials are delivered to the robot working area in a predetermined order through the automatic conveying component. At the same time, the scheduling control component adjusts the conveyor belt speed to ensure seamless connection with the operation of the robot arm, and the robot arm places each material.

[0032] Its beneficial effects are:

[0033] (1) Improve space utilization. The present invention effectively improves the space utilization of pallets through multi-objective genetic algorithm optimization, especially the stacking of multiple materials of different sizes and weights on pallets at the same time. Compared with traditional methods, this method can dynamically adapt to materials of various sizes and weights, comprehensively consider the optimal arrangement between various materials, and thus maximize the utilization of pallet space. This strategy not only reduces the waste of storage space, but also adapts to rapidly changing storage needs and improves logistics efficiency;

[0034] (2) Enhanced stacking stability. When calculating the optimal cargo box arrangement, the present invention not only takes into account the maximization of space, but also places special emphasis on stacking stability. By accurately calculating the center of gravity position and the optimal placement angle of the material, especially considering how to stack materials of different weights to maintain the balance of the pallet, the stacking stability is significantly enhanced. This method effectively reduces the risk of material collapse and damage caused by improper stacking, and enhances the safety of stacking operations;

[0035] (3) Automation and efficiency improvement. Combining advanced genetic algorithms and mechanical automation technology, the present invention realizes fully automated processing of material stacking, significantly improving operational efficiency and accuracy. Automated stacking not only reduces dependence on manual operation and reduces labor costs, but also improves response speed and processing capabilities through precise and fast machine operation.

[0036] The methods and systems of the present invention have other features and advantages that will be apparent from, or will be described in detail in, the accompanying drawings and subsequent detailed descriptions incorporated herein, which together serve to explain the specific principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present invention.

[0038] Figure 1 A flow chart showing the steps of a material stacking method based on a multi-objective genetic algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The preferred embodiments of the present invention will be described in more detail below. Although the preferred embodiments of the present invention are described below, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0040] To facilitate understanding of the solutions and effects of the embodiments of the present invention, two specific application examples are given below. Those skilled in the art should understand that the examples are only for facilitating understanding of the present invention, and any specific details thereof are not intended to limit the present invention in any way.

[0041] Example 1

[0042] Figure 1 A flow chart showing the steps of a material stacking method based on a multi-objective genetic algorithm according to an embodiment of the present invention.

[0043] like Figure 1 As shown, the material stacking method based on the multi-objective genetic algorithm includes:

[0044] Step 101, after obtaining material information, the material stacking plan is matched one by one with the chromosomes in the multi-objective genetic algorithm;

[0045] Step 102, calculating the corresponding fitness for the material stacking scheme of each chromosome;

[0046] Step 103, comparing the non-dominance relationships between the chromosomes, and selecting individuals that are superior to other chromosomes in at least one target for crossover and mutation;

[0047] Step 104, determine the optimal material stacking plan after crossover and mutation.

[0048] In one example, the chromosome is encoded in a vector, where each element includes the location, direction, and size information of the material.

[0049] In one example, fitness includes space utilization and stability. The space utilization and stability of the material stacking plan are calculated, and their weighted sum is the fitness.

[0050] In one example, the space utilization is:

[0051]

[0052] Among them, l i 、w i 、h i are the length, width and height of the i-th material; L T , W T , H T It is the length, width and height of the pallet.

[0053] In one example, the stability is:

[0054]

[0055] Among them, z cg is the height of the center of gravity of the material stack, H T is the height of the tray, z i and m i are the center height and mass of the i-th material respectively.

[0056] In one example, the crossover is:

[0057] Two chromosomes are randomly selected and parts of their genes are exchanged at multiple random positions to generate a new chromosome that contains characteristics of both parents.

[0058] In one example, the mutation is:

[0059] At least one gene in certain chromosomes is randomly selected and adjusted.

[0060] Specifically, after obtaining the material information, the material stacking scheme is matched one by one with the chromosomes in the multi-objective genetic algorithm. Each chromosome represents a possible material stacking scheme, which is encoded in the form of a vector, where each element contains the location, direction and size information of the material. For example, considering the case of three materials each time, the chromosome is represented as:

[0061] (x1,y1,z1,o1,x2,y2,z2,o2,x3,y3,z3,o3)

[0062] Among them, (x, y, z) represents the coordinates of the cargo box on the pallet, and o represents the direction of the material.

[0063] In order to evaluate the quality of packaging pallets, a specific metric needs to be introduced. The space utilization and stability of the stacking scheme are comprehensively evaluated to form a fitness score to guide algorithm optimization.

[0064] Space utilization (U): defined as the ratio of the volume occupied by all containers to the total volume of the pallet:

[0065]

[0066] Among them, l i 、w i 、h i are the length, width and height of the i-th material; L T , W T , H T It is the length, width and height of the pallet.

[0067] Stability (S): It is evaluated by considering the center of gravity of the material stack. The lower the center of gravity, the more stable the stack. The calculation formula is as follows:

[0068]

[0069] Among them, z cg is the height of the center of gravity of the material stack. z i and m i are the center height and mass of the i-th material respectively.

[0070] These formulas are combined into a comprehensive fitness function to guide the optimal stacking plan of materials. The fitness function combines the above two indicators:

[0071] F=ω1·U+ω2·S

[0072] Among them, ω1 and ω2 are weight coefficients relative to the operation target and need to be adjusted according to the specific warehouse operation requirements.

[0073] In the multi-objective genetic algorithm of the present invention, the selection mechanism is specially designed to process chromosomes that perform best in multiple evaluation indicators (such as space utilization and stability) for materials of different sizes. This method selects individuals that are superior to other chromosomes in at least one goal by comparing the non-dominant relationship between each chromosome. The result of the selection is a group of elite chromosomes that reflect multiple optimal solutions in the current population, which will be used in subsequent crossover and mutation processes. In this way, the algorithm ensures that the position and stacking effect of each container can be comprehensively considered when processing multiple containers, thereby improving the overall stacking optimization.

[0074] Crossover and mutation are key operations in genetic algorithms for exploring solution space and introducing new genetic mutations. In the multi-objective genetic algorithm of the present invention, the crossover operation is performed by a multi-point crossover technique, in which two excellent chromosomes are randomly selected, and then their partial genes are exchanged at multiple random positions to generate a new chromosome containing the characteristics of both parents. The mutation operation randomly selects one or more genes in certain chromosomes (such as the position or direction of the cargo box) and makes small adjustments to explore new solution spaces that are not covered by the current population. The combination of these two operations not only enhances the diversity of the population, but also improves the overall search capability of the algorithm, so that the optimal solution that meets the multi-objective conditions can be more effectively found in the global optimization process.

[0075] Example 2

[0076] A material stacking system based on a multi-objective genetic algorithm, comprising:

[0077] Data collection module, used to collect material information;

[0078] The multi-objective genetic algorithm module is used to execute the material stacking method based on the multi-objective genetic algorithm to obtain the optimal material stacking plan;

[0079] Mechanical execution module, used to transport and stack materials to designated locations according to the material stacking plan.

[0080] In one example, the data acquisition module includes a measurement sensor and a barcode scanner,

[0081] Among them, the measuring sensors include depth cameras and weighing sensors, which are used to measure the size and weight of materials in real time, and the barcode scanner is used to scan the barcode on the material to obtain the identification information of the material.

[0082] In one example, the mechanical execution module includes a robot arm, an automatic conveying component, and a scheduling control component.

[0083] The robot’s arm end effector adapts to materials of different shapes and sizes;

[0084] The scheduling control component receives and initializes the material stacking plan. The materials are delivered to the robot working area in a predetermined order through the automatic conveying component. At the same time, the scheduling control component adjusts the conveyor belt speed to ensure seamless connection with the operation of the robot arm, and the robot arm places each material.

[0085] Specifically, the data acquisition module is responsible for collecting all necessary input data, including the physical characteristics of the cargo box, such as size, weight, shape, and the supplier code of the cargo box. Data acquisition is achieved through measurement sensors and barcode scanners to ensure data accuracy and real-time updates. The measurement sensors are depth cameras and weighing sensors, which are used to measure the size and weight of materials in real time. The barcode scanner is used to scan the barcode on the material to obtain the material's identification information.

[0086] The multi-objective genetic algorithm module is the core component used to optimize the material stacking strategy. It is used to execute the material stacking method based on the multi-objective genetic algorithm to obtain the optimal material stacking plan.

[0087] The mechanical execution module includes a multi-degree-of-freedom industrial robot arm, an automatic conveying component and its dispatching control component. These components work together to ensure that materials are accurately conveyed and stacked from the storage area to the specified location according to the instructions of the optimization algorithm. The end effector of the robot arm is designed to adapt to materials of different shapes and sizes, and the fixture it is equipped with can be flexibly adjusted to suit different operating requirements.

[0088] At the beginning of the operation, the dispatch control component receives and initializes the stacking plan from the genetic algorithm optimization module. The materials are delivered to the robot operation area in a predetermined order through the automatic conveying component, and the dispatch control component adjusts the conveyor belt speed to ensure seamless connection with the robot arm's operation steps. The robot arm accurately places each material according to the plan, and the position sensor and data acquisition module continuously provide feedback to ensure accurate execution.

[0089] Those skilled in the art should understand that the purpose of the above description of the embodiments of the present invention is only to exemplarily illustrate the beneficial effects of the embodiments of the present invention, and is not intended to limit the embodiments of the present invention to any given examples.

[0090] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A material stacking method based on a multi-objective genetic algorithm, characterized in that: include: After obtaining the material information, the material stacking plan is matched one by one with the chromosomes in the multi-objective genetic algorithm; Calculate the corresponding fitness for each chromosome's material stacking scheme; Compare the non-dominance relationship between chromosomes, and select individuals that are superior to other chromosomes in at least one goal for crossover and mutation; The optimal material stacking plan is determined after crossover and mutation.

2. The material stacking method based on multi-objective genetic algorithm according to claim 1, wherein: The encoding form of the chromosome is a vector, each element of which includes the position, direction and size information of the material.

3. The material stacking method based on multi-objective genetic algorithm according to claim 1, wherein: The fitness includes space utilization and stability. The space utilization and stability of the material stacking plan are calculated, and the weighted sum thereof is the fitness.

4. The material stacking method based on multi-objective genetic algorithm according to claim 3, wherein: The space utilization is: Among them, l i 、w i 、h i are the length, width and height of the i-th material; L T , W T , H T It is the length, width and height of the pallet.

5. The material stacking method based on multi-objective genetic algorithm according to claim 3, wherein: The stability is: Among them, z cg is the height of the center of gravity of the material stack, H T is the height of the tray, z i and m i are the center height and mass of the i-th material respectively.

6. The material stacking method based on multi-objective genetic algorithm according to claim 1, wherein: The intersection is: Two chromosomes are randomly selected and parts of their genes are exchanged at multiple random positions to generate a new chromosome that contains characteristics of both parents.

7. The material stacking method based on multi-objective genetic algorithm according to claim 1, wherein: The variations are: At least one gene in certain chromosomes is randomly selected and adjusted.

8. A material stacking system based on a multi-objective genetic algorithm, characterized in that: include: Data collection module, used to collect material information; A multi-objective genetic algorithm module, used to execute the material stacking method based on the multi-objective genetic algorithm described in any one of claims 1 to 7 to obtain an optimal material stacking plan; The mechanical execution module is used to transport and stack the materials to the designated location according to the material stacking plan.

9. The material stacking system based on multi-objective genetic algorithm according to claim 8, wherein: The data acquisition module includes a measurement sensor and a barcode scanner, The measuring sensor includes a depth camera and a weighing sensor for measuring the size and weight of the material in real time, and the barcode scanner is used to scan the barcode on the material to obtain the identification information of the material.

10. The material stacking system based on multi-objective genetic algorithm according to claim 8, wherein: The mechanical execution module includes a robot arm, an automatic conveying component and a scheduling control component. The robot's arm end effector can adapt to materials of different shapes and sizes; The scheduling control component receives and initializes the material stacking plan, and the materials are delivered to the robot working area in a predetermined order through the automatic conveying component. At the same time, the scheduling control component adjusts the conveyor belt speed to ensure seamless connection with the operation of the robot arm, and the robot arm places each material.

Images