Carton mixed stacking method based on genotype genetic algorithm

Abstract

The application discloses a carton mixed stacking method based on a genotype genetic algorithm, which is based on a standard genetic algorithm and proposes a genotype genetic algorithm suitable for a mixed stacking algorithm to obtain optimal solutions of the stacking order, position and posture of each carton in carton mixed stacking. The method inherits the characteristics of the genetic algorithm in quickly solving optimal solutions, regards each carton as a genetic factor for genetic, and adopts a self-intersection mode for genetic optimization according to the characteristics of the quantity and type requirements of orders. The method can solve the problem that a robot cannot automatically plan the stacking position of cartons according to order information in an unmanned warehouse, and greatly improves the intelligent degree of the robot.

Description

Technical Field

[0001] This invention belongs to the field of palletizing technology, specifically relating to a mixed palletizing method for cartons based on a genotype genetic algorithm. Background Technology

[0002] Currently, in warehousing and logistics order-based outbound operations, manual or robotic palletizing is generally used. In logistics and warehousing scenarios, there is a significant demand for mixed-box palletizing robots, which can replace manual handling and greatly improve production efficiency. However, how to achieve automatic and efficient palletizing of boxes of various sizes and specifications arriving out of order, saving manpower while improving logistics turnover efficiency, is a challenging problem in logistics and warehousing automation. The core issue is solving the classic NP-hard problem of the Bin Packing Problem (BPP), which involves planning the placement of each box within a container to maximize space utilization. Since each order requires different types and quantities of goods, mixed palletizing cannot be accomplished using a teaching method.

[0003] To address the aforementioned issues, an algorithm is needed that can automatically plan the outbound order and palletizing strategy of goods based on information such as the size, quantity, weight, and load-bearing capacity of the goods in an order. This algorithm would guide robots to automatically palletize the goods, thereby achieving truly unmanned warehousing. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of the prior art by providing a carton hybrid palletizing method based on a genotype genetic algorithm to solve the problem of outbound and stacking of various goods when unmanned warehouses issue goods according to orders.

[0005] To solve the above-mentioned technical problems, one technical solution adopted by the present invention is: to provide a carton mixed palletizing method based on genotype genetic algorithm, comprising the following steps:

[0006] S1. Based on the order information, each cardboard box is represented by a gene I, and the linear arrangement of all cardboard boxes is represented by the genotype of the genetic algorithm P. Then the initial generation individuals are: n is the number of cardboard boxes;

[0007] The above genes Where: L represents the length of the carton; W represents the width of the carton; H represents the height of the carton; T represents the weight of the carton; Wt represents the weight the carton can withstand; M represents the placement orientation of the carton M={0 or 1}, where 0 indicates that the length direction of the carton is parallel to the X direction of the pallet coordinate system, and 1 indicates that the length direction of the carton is perpendicular to the X direction of the pallet coordinate system;

[0008] S2, I of each gene in P(0) xRandom crossover is used to generate a sufficient number of offspring individuals P(1). m m is a set value, representing the number of offspring individuals;

[0009] S3. Using the placement posture M of the cardboard boxes as the mutation term, and taking the maximum pallet utilization rate U as the evaluation criterion for genetic individuals, genetic operations are performed with the set termination judgment conditions to finally obtain the optimal cardboard box picking order;

[0010] S4. The robot picks up the corresponding cardboard boxes in the optimal cardboard box picking order described above, and places them in the corresponding positions on the pallet according to the set placement rules.

[0011] In another embodiment of the present invention, the termination judgment condition set in step S3 is: the set tray utilization rate U or the set genetic generation.

[0012] In another embodiment of the present invention, the formula for calculating the pallet utilization rate U is: ,

[0013] in, S represents the volume of each carton; S represents the maximum volume of cartons that can be placed on the pallet; N represents the total number of pallets used in this order.

[0014] In another embodiment of the present invention, the placement rules set in step S4 are as follows:

[0015] S31. Establish a rectangular coordinate system with one corner of the pallet as the starting point for stacking cartons. Set a placement reference point Q for each carton. Place the first carton at the starting point of the coordinate system according to the rules and generate 3 new candidate placement points.

[0016] S32. Grab the next carton in sequence and compare its placement reference point Q with the candidate placement points on the pallet according to the set comparison principle to determine whether the placement requirements are met. If they are met, place the carton on the corresponding position on the pallet and generate 3 new candidate placement points. If they are not met, continue to search for the next placement point until they are met, or until all placement points are not met. If all placement points are not met, stop stacking the current pallet, issue a new pallet and place the current carton on the new pallet, generating 3 new placement points.

[0017] S33. Repeat the previous step until all the cartons are stacked on the pallet.

[0018] In another embodiment of the present invention, the comparison principle in step S32 is set as follows: the carton is judged in turn according to the principle of from low to high and from far to near to determine whether it can be placed at the candidate placement point.

[0019] In another embodiment of the present invention, the placement requirements in step S32 are as follows:

[0020] (1) The suspension rate K of the carton shall not be less than the set value: K = bottom support area of ​​the carton / bottom area of ​​the carton;

[0021] (2) Whether it interferes with other cardboard boxes: When a cardboard box is placed at this placement point, it should not interfere with other cardboard boxes that have already been placed;

[0022] (3) Whether the weight of the cardboard box below is exceeded: When the cardboard box is placed at this placement point, the weight of the cardboard box below it must not exceed the maximum weight it can bear.

[0023] (4) Whether it exceeds the pallet range: When the carton is placed at the selected placement point, it must not exceed the length, width and height range of the pallet.

[0024] In another embodiment of the invention, the set value of the carton suspension rate is 0.8.

[0025] The beneficial effects of this invention are as follows: Based on the standard genetic algorithm, this invention proposes a genotype genetic algorithm suitable for hybrid palletizing algorithms to obtain the optimal solution for the stacking order, position, and orientation of each carton in hybrid palletizing. This method inherits the characteristic of genetic algorithms to quickly find the optimal solution, treating each carton as a genetic factor for inheritance, and using a self-intersection method for genetic optimization based on the quantity and type requirements of orders. This method can solve the problem that robots in unmanned warehouses cannot automatically plan the carton stacking position based on order information, greatly improving the intelligence level of robots. Attached Figure Description

[0026] Figure 1 This is a flowchart of the carton hybrid palletizing method based on genotype genetic algorithm of the present invention;

[0027] Figure 2 This is a flowchart of the genotype genetic algorithm of the present invention;

[0028] Figure 3 It is a rectangular coordinate system diagram established by the corner points of the tray;

[0029] Figure 4 This is a diagram showing the reference points for placing cardboard boxes and the resulting candidate placement points. Detailed Implementation

[0030] To facilitate understanding of the present invention, a more detailed description is provided below with reference to the accompanying drawings and specific embodiments. Preferred embodiments of the invention are shown in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the invention.

[0031] It should be noted that, unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items. Terms such as "center," "bottom," "top," "inner," and "outer," indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are merely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the referred component must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the scope of protection of this invention.

[0032] like Figure 1 The flowchart shown is a process for a mixed palletizing method for cardboard boxes based on a genotype genetic algorithm according to the present invention. As can be seen from the figure, the method includes the following steps:

[0033] S1. Based on the order information, each cardboard box is considered as an individual. Each individual contains information including length, width, height, weight, load-bearing capacity, and placement orientation. In this embodiment, each cardboard box is represented by a gene, denoted as I. ,

[0034] Where: L represents the length of the carton; W represents the width of the carton; H represents the height of the carton; T represents the weight of the carton; Wt represents the weight the carton can withstand; M represents the placement orientation of the carton M={0 or 1}, where 0 indicates that the length direction of the carton is parallel to the X direction of the pallet coordinate system, and 1 indicates that the length direction of the carton is perpendicular to the X direction of the pallet coordinate system;

[0035] Let P represent the genotype of all the cardboard boxes in a linear arrangement as the genetic algorithm. Then the first generation individuals are: n is the number of cardboard boxes;

[0036] S2. According to the standard genetic algorithm, I of each gene in P(0) x Random crossover is used to generate a sufficient number of offspring individuals P(1). m m is a set value, representing the number of offspring individuals;

[0037] S3. The placement posture M of the cardboard boxes is used as the mutation term. The maximum pallet utilization rate U is used as the evaluation standard for genetic individuals. Genetic operations are performed with the set termination judgment conditions to finally obtain the optimal cardboard box picking order.

[0038] S4. The robot picks up the corresponding cardboard boxes in the optimal cardboard box picking order described above, and places them in the corresponding positions on the pallet according to the set placement rules.

[0039] The flowchart of the genotype genetic algorithm in this embodiment is as follows: Figure 2 As shown, the process is as follows: the cardboard boxes are arranged linearly according to the order, each cardboard box is treated as a gene, and the inheritance is carried out in a self-crossing manner. The placement posture of the cardboard boxes is used as a mutation term. Each time, the individual with the highest pallet utilization rate is found from the offspring and parents. When the specified number of generations is reached or the maximum set pallet utilization rate is reached, the process stops and the result is output to guide the robot to complete the mixed palletizing.

[0040] Preferably, the present invention uses tray utilization rate as a method for assessing individual fitness, and selects the individual with the highest tray utilization rate for genetic testing each time.

[0041] The termination condition set in step S3 is either the set tray utilization rate U or the set number of generations, where the formula for calculating the tray utilization rate U is: ;

[0042] in,

[0043] S represents the volume of each carton; S represents the maximum volume of cartons that can be placed on the pallet; N represents the total number of pallets used in this order.

[0044] Preferably, the placement rules set in step S4 are as follows:

[0045] S31. Establish a rectangular coordinate system using one corner point of the tray, such as... Figure 3 As shown, with corner point O as the starting point for stacking cartons, each carton is assigned a placement reference point Q, as follows. Figure 4 As shown, the first cardboard box is placed at the starting point of the coordinate system according to the rules, generating 3 new candidate placement points, such as... Figure 4 Points 1, 2, 3 shown;

[0046] S32. Grab the next carton in sequence and compare its placement reference point Q with the candidate placement points on the pallet according to the set comparison principle to determine whether the placement requirements are met. If they are met, place the carton on the corresponding position on the pallet and generate 3 new candidate placement points. If they are not met, continue to search for the next placement point until they are met, or until all placement points are not met. If all placement points are not met, stop stacking the current pallet, issue a new pallet and place the current carton on the new pallet, generating 3 new placement points.

[0047] Preferably, in this embodiment, the comparison principle is set as follows: judging whether the carton can be placed at the candidate placement point in order from low to high and from far to near.

[0048] The placement requirements set in this embodiment are as follows:

[0049] (1) The suspension rate K of the carton shall not be less than the set value of 0.8, that is, K = bottom support area of ​​the carton / bottom area of ​​the carton > 0.8;

[0050] (2) Whether it interferes with other cardboard boxes: When a cardboard box is placed at this placement point, it should not interfere with other cardboard boxes that have already been placed;

[0051] (3) Whether the weight of the cardboard box below is exceeded: When the cardboard box is placed at this placement point, the weight of the cardboard box below it must not exceed the maximum weight it can bear.

[0052] (4) Whether it exceeds the pallet range: When the carton is placed at the selected placement point, it must not exceed the length, width and height range of the pallet.

[0053] S33. Repeat the previous step until all the cartons are stacked on the pallet.

[0054] This method can automatically calculate the stacking position and posture of various cartons when they are automatically generated and mixed and stacked on a pallet. It is mainly used to solve the problem of outbound and stacking of various goods when unmanned warehouses are outbound according to orders. It is used to guide robots to achieve automatic palletizing. It can automatically guide robots to achieve mixed palletizing tasks when goods with outer packaging in cartons are outbound according to orders in logistics warehousing.

[0055] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for mixed case palletizing of cartons based on a genotype genetic algorithm, characterized by, Comprising the following steps: S1, according to order information, each carton is represented as a gene I, and the linear arrangement of all cartons is represented as the genotype P of genetic algorithm, then the initial individual is: P(0)={I0, I1, I2, …, In}, n is the number of cartons; n} The above gene I={L, W, H, T, Wt, M}, wherein: L represents the length of the carton; W represents the width of the carton; H represents the height of the carton; T represents the weight of the carton; Wt represents the weight that the carton can bear; M represents the placement posture of the carton M={0 or 1}, 0 represents that the length direction of the carton is parallel to the X direction of the pallet coordinate system, and 1 represents that the length direction of the carton is perpendicular to the X direction of the pallet coordinate system; S2, each gene I in P(0) is crossed x Randomly crossing to generate enough offspring P(1) m m is a set value, i.e. the number of offspring S3, taking the placement posture M of the carton as a mutation item, taking the maximum utilization rate U of the pallet as the evaluation standard of the genetic individual, and performing genetic operation on the set termination judgment condition to finally obtain the optimal carton grabbing sequence; S4, the robot sequentially grabs the corresponding carton according to the above optimal carton grabbing sequence, and places it at the corresponding position of the pallet according to the set placement rule; The placement rule set in the step S4 is as follows: S31, a rectangular coordinate system is established with a corner point of the pallet as the starting point of the carton stacking, and a placement reference point Q is set for each carton, the first carton is placed at the starting point of the coordinate system according to the rule and three new candidate placement points are generated; S32, the next carton is sequentially grabbed, and the placement reference point Q is sequentially compared with the candidate placement points on the pallet according to the set comparison principle to judge whether the placement requirement is met; if met, the carton is placed on the corresponding position of the pallet and three new candidate placement points are generated; if not met, the next placement point is continuously searched until met, or all placement points are not met; if all placement points are not met, the stacking of the current pallet is stopped, a new pallet is provided, and the current carton is placed on the new pallet, and three new placement points are generated; S33, repeat the above step until all cartons are stacked on the pallet.

2. The genotype genetic algorithm based case mixed palletizing method of claim 1, wherein, The termination judgment condition set in the step S3 is: the set utilization rate U of the pallet or the set number of generations.

3. The genotype genetic algorithm based case mixed palletizing method of claim 2, wherein, The formula for calculating the utilization of the pallets U is: ; wherein, V is the volume of each carton; S is the maximum volume of the pallet that can be occupied by cartons; N is the total number of pallets used for the current order.

4. The genotype-based genetic algorithm based carton mixed palletizing method according to claim 3, characterized in that, The comparison principle set in the step S32 is: the carton is sequentially judged whether it can be placed at the candidate placement point according to the principle from low to high and from far to near.

5. The genotype-based genetic algorithm based carton mixed palletizing method according to claim 4, wherein, The placement requirement in the step S32 is as follows: (1) the carton overhang rate K cannot be less than the set value: K=carton bottom support area / carton bottom area; (2) whether to interfere with other cartons: when the carton is placed at the placement point, it cannot interfere with other cartons that have been placed; (3) whether it exceeds the bearing capacity of the lower carton: when the carton is placed at the placement point, the bearing capacity of the lower carton cannot exceed the maximum bearing capacity; (4) whether it exceeds the range of the pallet: when the carton is placed at the candidate placement point, it cannot exceed the length, width and height range of the pallet.

6. The genotype-based genetic algorithm based carton hybrid palletizing method according to claim 5, wherein, The set value of the carton overhang rate is 0.8.

Images