Optimization control method and system for filling filler during loading of van

Abstract

The invention relates to a van truck loading filler filling optimization control method and system, and the method comprises the steps: R1, building an overall stacking model of goods based on order data information of the goods, carrying out the representation of the stacking size of the goods, obtaining the first stacking size data information of the goods, and obtaining a second stacking size data information of the goods; comprehensively scanning the whole stacked materials based on a scanning 3D camera to obtain 3D scanning image data information of the stacked materials; and R2, based on the 3D scanning image data information of the stacked materials, calculating the stacking size of the stacked materials by using an improved SAM image segmentation algorithm. According to the invention, the fillers can be added among the box bodies to prevent goods from colliding with the box bodies due to bumping in the transportation process to cause goods damage and appearance scratch, and the filling of the fillers is optimally controlled according to the change of the stacking size of the goods, so that the energy consumption is reduced, the transportation cost is reduced, and the transportation efficiency is improved. The transportation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of van loading, and in particular to an optimization control method and system for loading a van with a filler. Background Art

[0002] The freight industry is a key economic sector responsible for the transportation and distribution of goods. It plays an important role in the development and operation of the global economy. The freight industry not only covers multiple fields such as roads, railways, aviation and shipping, but also includes related industries such as warehousing, logistics, and supply chain management. With the continuous development of the global economy, the demand for the transportation of goods and goods continues to develop. The freight industry has become a link between production and consumption, and has promoted the circulation and exchange of various products and services. Among them, during the transportation of freight, because there are gaps between the boxes, the bumps cause the goods to collide with the boxes, which will cause damage to the goods and scratches on the appearance. Summary of the invention

[0003] In view of the above problems, the present invention provides an optimization control method and system for filling fillers in a van, which can not only add fillers between each box to prevent the goods from colliding with the box due to bumps during transportation, causing damage to the goods and scratches on the appearance, but also optimize the filling of fillers according to changes in the size of the cargo stacking, thereby reducing energy consumption, thereby reducing transportation costs and improving transportation efficiency.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0005] An optimization control method for loading a van with a filling material, the method comprising:

[0006] R1. Based on the order data information of the goods, an overall stacking model of the goods is constructed, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained. The overall stacking material is comprehensively scanned based on the scanning 3D camera to obtain the 3D scanning image data information of the stacking material;

[0007] R2. Based on the 3D scanning image data information of the stacking material, the stacking size of the stacking material is calculated using the improved SAM image segmentation algorithm to obtain the second stacking size data information of the goods;

[0008] R3. Based on the second stacking size data information of the goods and the first stacking size data information of the goods, the deviation value of the stacking size of the goods is calculated by using a cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function to obtain the deviation value data information of the stacking size of the goods;

[0009] R4. Based on the data information of the deviation value of the cargo stacking size, a filling model of the truck loading filler is constructed, and the filling position point of the filler is predicted to obtain the predicted filling position point matrix data information of the filler;

[0010] R5. Based on the predicted filling position point matrix data information of the filler, the filling position points of the filler are optimized using a particle swarm optimization algorithm based on adaptive weights to obtain the optimized filling position point data information of the filler.

[0011] Furthermore, the method further comprises:

[0012] R6. Based on the optimized filling position point data information of the filler, establish an optimized control function F for filling the filler,

[0013]

[0014] Among them, x is the filling position point data information of the optimized filler, α1, α2 and α3 are the optimization control factors of the filling of the filler, and the filling of the filler is optimized and controlled to obtain the optimized control data information of the filling of the truck loading filler.

[0015] Furthermore, the optimization control factors α1, α2 and α3 of the filler filling are:

[0016]

[0017]

[0018]

[0019] Wherein, x is the filling position point data information of the optimized filler.

[0020] Furthermore, in step R1, constructing the overall stacking model of the goods and characterizing the size of the goods includes:

[0021] R11. Based on the order data information of the goods, establish the goods stacking function Q,

[0022]

[0023] Among them, y is the order data information of the goods, σ1 and σ2 are the goods stacking conversion factors, and the goods stacking data set is characterized to obtain the data information of the goods stacking data set;

[0024] R12. Input the cargo stacking data set into the overall cargo stacking model for training and learning, and determine the cargo stacking size characterization function W,

[0025]

[0026] Among them, z is the data information of the cargo stacking data set, β1, β2 and β3 are the size conversion factors of the overall cargo stacking, and the trained overall cargo stacking model is obtained;

[0027] R13. Based on the trained overall stacking model of the goods, the order data information of the goods is input, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained.

[0028] Furthermore, the constraint function f of the size conversion factors β1, β2 and β3 of the overall stacking of the goods is,

[0029]

[0030] The value range of the constraint function f is (0,1).

[0031] Furthermore, in step R2, the use of the improved SAM image segmentation algorithm to estimate the stacking size of the stacked materials includes:

[0032] R21. Based on the 3D scanning image data information of the stacked material, a pixel matrix of the stacked material is constructed to obtain pixel matrix data information of the stacked material;

[0033] R22. Based on the pixel matrix data information of the stacked material, a characteristic pixel extraction function U of the stacked material is constructed.

[0034]

[0035] Wherein, a is the pixel matrix data information of the stacked material, δ1, δ2 and δ3 are the characteristic pixel extraction factors of the stacked material, and the characteristic pixel points of the stacked material are extracted to obtain the extracted characteristic pixel matrix data information of the stacked material;

[0036] R23. Based on the extracted characteristic pixel matrix data information of the stacked material, an image segmentation function P of the stacked material is established.

[0037]

[0038] Among them, b is the characteristic pixel matrix data information of the stacked material after extraction, γ1 and γ2 are the image segmentation determining factors, and the image of the stacked material is segmented to obtain the image data information of the segmented stacked material;

[0039] R24. Based on the image data information of the segmented stacked material, a stacking size characterization function S of the stacked material is established.

[0040]

[0041] Among them, c is the image data information of the segmented stacking material, η1, η2 and η3 are the stacking size covariance constant parameters of the stacking material, and the stacking size of the stacking material is calculated to obtain the second stacking size data information of the goods.

[0042] Furthermore, in step R3, the use of a cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function to calculate the deviation value of the cargo stacking size includes:

[0043] R31. Based on the second stacking size data information of the goods, establish a Fourier series fitting one-dimensional probability density function g1 of the second stacking size of the goods,

[0044]

[0045] Among them, r2 is the data information of the second stacking size of the goods, λ1 and λ2 are the probability density distribution factors of the second stacking size of the goods, and the probability distribution of the second stacking size of the goods is characterized to obtain the probability distribution data information of the second stacking size of the goods;

[0046] R32. Based on the first stacking size data information of the goods, establish a Fourier series fitting one-dimensional probability density function g2 of the first stacking size of the goods,

[0047]

[0048] Among them, r1 is the data information of the first stacking size of the goods, μ1, μ2 and μ3 are the probability density distribution factors of the first stacking size of the goods, and the probability distribution of the first stacking size of the goods is characterized to obtain the probability distribution data information of the first stacking size of the goods;

[0049] R33. Based on the probability distribution data information of the first stacking size of the goods and the probability distribution data information of the second stacking size of the goods, a difference function G of the stacking size of the goods is established,

[0050]

[0051]

[0052] Among them, m1 is the probability distribution data information of the first stacking size of the goods, m2 is the probability distribution data information of the second stacking size of the goods, θ1, θ2 and θ3 are the penalty weights of the stacking size of the goods, and the deviation value of the stacking size of the goods is calculated to obtain the deviation value data information of the stacking size of the goods.

[0053] Furthermore, in step R4, the construction of a filling model for loading a truck with a filler and the prediction of a filling position of the filler include:

[0054] R41. Based on the deviation value data information of the cargo stacking size, a deviation value data set of the cargo stacking size is constructed to obtain a deviation value data set of the cargo stacking size;

[0055] R42. Input the deviation value data set of the cargo stacking size into the filling model of the truck loading filler for training and learning, and determine the filling position point prediction function H of the filler,

[0056] Among them, h is the deviation value data set of the cargo stacking size, ρ1, ρ2 and ρ3 are the bias constant parameters of the model, and the trained filling model of the truck loading filler is obtained;

[0057] R43. Based on the trained filling model of the truck loading fillers, the deviation value data information of the truck stacking size is input, the filling position points of the fillers are predicted, and the predicted filling position point matrix data information of the fillers is obtained.

[0058] Furthermore, in step R5, the optimization of the filling position of the filler by using the particle swarm optimization algorithm based on adaptive weights includes:

[0059] R51. Based on the predicted filling position point matrix data information of the filler, the population parameters of the particle population are initialized, the maximum number of iterations is determined, and the initialized particle population data information is obtained;

[0060] R52. Based on the initialized particle population data information, establish the fitness function J of the population individuals,

[0061]

[0062] Among them, q is the data information of the particle population after initialization, ω1 and ω2 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the fitness value data information of the population individuals;

[0063] R53. Based on the fitness value data information of the population individuals, establish the target optimization function Z,

[0064]

[0065] Among them, v is the fitness value data information of the population individual, ε1, ε2 and ε3 are the adaptive weights of the population individual, and the filling position points of the filler are optimized to obtain the optimized filling position point data information of the filler.

[0066] In order to achieve the above-mentioned and other related purposes, the present invention also provides an optimization control system for filling a van with fillers, including a computer device, which is programmed or configured to execute the steps of any one of the optimization control methods for filling a van with fillers.

[0067] The present invention has the following positive effects:

[0068] 1. The present invention characterizes the stacking size of the goods by constructing an overall stacking model of the goods, and uses an improved SAM image segmentation algorithm to calculate the stacking size of the stacking materials. This can not only accurately analyze the stacking size of the stacking materials, but also provide accurate data support for the subsequent filling of the gaps of the stacking materials.

[0069] 2. The present invention calculates the deviation value of the cargo stacking size by adopting a cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function, and combines the construction of a filling model for truck loading fillers to predict the filling position points of the fillers and optimize the filling position points of the fillers by adopting a particle swarm optimization algorithm based on adaptive weights. This method can not only add fillers between each box to prevent the cargo from colliding with the box due to bumps during transportation, causing damage to the cargo and scratches on the appearance, but also optimize the filling of the fillers according to the changes in the size of the cargo stacking, thereby reducing energy consumption, thereby reducing transportation costs and improving transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a schematic diagram of the loading distribution structure of a van of the present invention;

[0071] Figure 2 It is a schematic diagram of the method flow of the present invention;

[0072] Figure 3 A schematic diagram of the process of constructing an overall stacking model of goods according to the present invention;

[0073] Figure 4 It is a schematic flow chart of the improved SAM image segmentation algorithm of the present invention;

[0074] Figure 5 It is a flow chart of the cargo stacking size difference algorithm based on Fourier series fitting of one-dimensional probability density function of the present invention;

[0075] Figure 6 A schematic diagram of the process of constructing a filling model for loading a truck with a filling object according to the present invention;

[0076] Figure 7The figure is a flow chart of the particle swarm optimization algorithm based on adaptive weights of the present invention. The numbering in the figure is as follows: 1-van, 2-integral stacking platform, 3-scanning 3D camera, 4-palletizing robot arm, 5-filling robot arm. DETAILED DESCRIPTION

[0077] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0078] Example 1: Figure 1 or Figure 2 As shown, a van 1 is parked on one side of the overall stacking platform 2, the goods are stacked by a stacking robot arm 4, and then the gaps between the goods are filled with fillers by a filler robot arm 5. An optimization control method for loading fillers on a van includes:

[0079] R1. Based on the order data information of the goods, the overall stacking model of the goods is constructed, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained. Based on the scanning 3D camera 3, the overall stacking material is comprehensively scanned to obtain the 3D scanning image data information of the stacking material;

[0080] R2. Based on the 3D scanning image data information of the stacking material, the stacking size of the stacking material is calculated using the improved SAM image segmentation algorithm to obtain the second stacking size data information of the goods;

[0081] R3. Based on the second stacking size data information of the goods and the first stacking size data information of the goods, the deviation value of the stacking size of the goods is calculated by using a cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function to obtain the deviation value data information of the stacking size of the goods;

[0082] R4. Based on the data information of the deviation value of the cargo stacking size, a filling model of the truck loading filler is constructed, and the filling position point of the filler is predicted to obtain the predicted filling position point matrix data information of the filler;

[0083] R5. Based on the predicted filling position point matrix data information of the filler, the filling position points of the filler are optimized using a particle swarm optimization algorithm based on adaptive weights to obtain the optimized filling position point data information of the filler.

[0084] In this embodiment, the method further includes:

[0085] R6. Based on the optimized filling position point data information of the filler, establish an optimized control function F for filling the filler,

[0086]

[0087] Among them, x is the filling position point data information of the optimized filler, α1, α2 and α3 are the optimization control factors of the filling of the filler, and the filling of the filler is optimized and controlled to obtain the optimized control data information of the filling of the truck loading filler.

[0088] In this embodiment, the optimization control factors α1, α2 and α3 of the filler filling are:

[0089]

[0090]

[0091]

[0092] Wherein, x is the filling position point data information of the optimized filler.

[0093] In this embodiment, if Figure 3 As shown, in step R1, the construction of the overall stacking model of the goods and the characterization of the size of the goods include:

[0094] R11. Based on the order data information of the goods, establish the goods stacking function Q,

[0095]

[0096] Among them, y is the order data information of the goods, σ1 and σ2 are the goods stacking conversion factors, and the goods stacking data set is characterized to obtain the data information of the goods stacking data set;

[0097] R12. Input the cargo stacking data set into the overall cargo stacking model for training and learning, and determine the cargo stacking size characterization function W,

[0098]

[0099] Among them, z is the data information of the cargo stacking data set, β1, β2 and β3 are the size conversion factors of the overall cargo stacking, and the trained overall cargo stacking model is obtained;

[0100] R13. Based on the trained overall stacking model of the goods, the order data information of the goods is input, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained.

[0101] In this embodiment, the constraint function f of the size conversion factors β1, β2 and β3 of the overall stacking of goods is,

[0102]

[0103] The value range of the constraint function f is (0,1).

[0104] In this embodiment, if Figure 4 As shown, in step R2, the use of the improved SAM image segmentation algorithm to estimate the stacking size of the stacked materials includes:

[0105] R21. Based on the 3D scanning image data information of the stacked material, a pixel matrix of the stacked material is constructed to obtain pixel matrix data information of the stacked material;

[0106] R22. Based on the pixel matrix data information of the stacked material, a characteristic pixel extraction function U of the stacked material is constructed.

[0107]

[0108] Wherein, a is the pixel matrix data information of the stacked material, δ1, δ2 and δ3 are the characteristic pixel extraction factors of the stacked material, and the characteristic pixel points of the stacked material are extracted to obtain the extracted characteristic pixel matrix data information of the stacked material;

[0109] R23. Based on the extracted characteristic pixel matrix data information of the stacked material, an image segmentation function P of the stacked material is established.

[0110]

[0111] Among them, b is the characteristic pixel matrix data information of the stacked material after extraction, γ1 and γ2 are the image segmentation determining factors, and the image of the stacked material is segmented to obtain the image data information of the segmented stacked material;

[0112] R24. Based on the image data information of the segmented stacked material, a stacking size characterization function S of the stacked material is established.

[0113]

[0114] Among them, c is the image data information of the segmented stacking material, η1, η2 and η3 are the stacking size covariance constant parameters of the stacking material, and the stacking size of the stacking material is calculated to obtain the second stacking size data information of the goods.

[0115] Embodiment 2: Based on the optimization control method for filling a van with a filling material in Embodiment 1, the present invention is further illustrated and described below.

[0116] like Figure 1 or Figure 2 As shown, a van 1 is parked on one side of the overall stacking platform 2, the goods are stacked by a stacking robot arm 4, and then the gaps between the goods are filled with fillers by a filler robot arm 5. An optimization control method for loading fillers on a van includes:

[0117] R1. Based on the order data information of the goods, the overall stacking model of the goods is constructed, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained. Based on the scanning 3D camera 3, the overall stacking material is comprehensively scanned to obtain the 3D scanning image data information of the stacking material;

[0118] R2. Based on the 3D scanning image data information of the stacking material, the stacking size of the stacking material is calculated using the improved SAM image segmentation algorithm to obtain the second stacking size data information of the goods;

[0119] R3. Based on the second stacking size data information of the goods and the first stacking size data information of the goods, the deviation value of the stacking size of the goods is calculated by using a cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function to obtain the deviation value data information of the stacking size of the goods;

[0120] R4. Based on the data information of the deviation value of the cargo stacking size, a filling model of the truck loading filler is constructed, and the filling position point of the filler is predicted to obtain the predicted filling position point matrix data information of the filler;

[0121] R5. Based on the predicted filling position point matrix data information of the filler, the filling position points of the filler are optimized using a particle swarm optimization algorithm based on adaptive weights to obtain the optimized filling position point data information of the filler.

[0122] In this embodiment, if Figure 5 As shown, in step R3, the method of calculating the deviation value of the cargo stacking size by using the cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function includes:

[0123] R31. Based on the second stacking size data information of the goods, establish a Fourier series fitting one-dimensional probability density function g1 of the second stacking size of the goods,

[0124]

[0125] Among them, r2 is the data information of the second stacking size of the goods, λ1 and λ2 are the probability density distribution factors of the second stacking size of the goods, and the probability distribution of the second stacking size of the goods is characterized to obtain the probability distribution data information of the second stacking size of the goods;

[0126] R32. Based on the first stacking size data information of the goods, establish a Fourier series fitting one-dimensional probability density function g2 of the first stacking size of the goods,

[0127]

[0128] Among them, r1 is the data information of the first stacking size of the goods, μ1, μ2 and μ3 are the probability density distribution factors of the first stacking size of the goods, and the probability distribution of the first stacking size of the goods is characterized to obtain the probability distribution data information of the first stacking size of the goods;

[0129] R33. Based on the probability distribution data information of the first stacking size of the goods and the probability distribution data information of the second stacking size of the goods, a difference function G of the stacking size of the goods is established,

[0130]

[0131]

[0132] Among them, m1 is the probability distribution data information of the first stacking size of the goods, m2 is the probability distribution data information of the second stacking size of the goods, θ1, θ2 and θ3 are the penalty weights of the stacking size of the goods, and the deviation value of the stacking size of the goods is calculated to obtain the deviation value data information of the stacking size of the goods.

[0133] In this embodiment, if Figure 6 As shown, in step R4, the construction of a filling model for loading a truck with fillers and the prediction of the filling position of the fillers include:

[0134] R41. Based on the deviation value data information of the cargo stacking size, a deviation value data set of the cargo stacking size is constructed to obtain a deviation value data set of the cargo stacking size;

[0135] R42. Input the deviation value data set of the cargo stacking size into the filling model of the truck loading filler for training and learning, and determine the filling position point prediction function H of the filler,

[0136] Among them, h is the deviation value data set of the cargo stacking size, ρ1, ρ2 and ρ3 are the bias constant parameters of the model, and the trained filling model of the truck loading filler is obtained;

[0137] R43. Based on the trained filling model of the truck loading fillers, the deviation value data information of the truck stacking size is input, the filling position points of the fillers are predicted, and the predicted filling position point matrix data information of the fillers is obtained.

[0138] In this embodiment, if Figure 7 As shown, in step R5, the optimization of the filling position points of the filler by using the particle swarm optimization algorithm based on adaptive weights includes:

[0139] R51. Based on the predicted filling position point matrix data information of the filler, the population parameters of the particle population are initialized, the maximum number of iterations is determined, and the initialized particle population data information is obtained;

[0140] R52. Based on the initialized particle population data information, establish the fitness function J of the population individuals,

[0141]

[0142] Among them, q is the data information of the particle population after initialization, ω1 and ω2 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the fitness value data information of the population individuals;

[0143] R53. Based on the fitness value data information of the population individuals, establish the target optimization function Z,

[0144]

[0145] Among them, v is the fitness value data information of the population individual, ε1, ε2 and ε3 are the adaptive weights of the population individual, and the filling position points of the filler are optimized to obtain the optimized filling position point data information of the filler.

[0146] In this embodiment, the present invention provides an optimization control system for filling a van with a filler, including a computer device that is programmed or configured to execute the steps of any one of the optimization control methods for filling a van with a filler.

[0147] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the above-described methods for optimizing control of loading a van with a filler.

[0148] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0149] In summary, the present invention can not only add fillers between each box to prevent the goods from colliding with the box due to bumps during transportation, causing damage to the goods and scratches on the appearance, but also optimize the filling of the fillers according to the changes in the size of the stacking of goods, thereby reducing energy consumption, thereby reducing transportation costs and improving transportation efficiency.

[0150] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An optimization control method for loading a van with a filling material, characterized in that: The method comprises: R1. Based on the order data information of the goods, an overall stacking model of the goods is constructed, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained. The overall stacking material is comprehensively scanned based on the scanning 3D camera to obtain the 3D scanning image data information of the stacking material; R2. Based on the 3D scanning image data information of the stacking material, the stacking size of the stacking material is calculated using the improved SAM image segmentation algorithm to obtain the second stacking size data information of the goods; R3. Based on the second stacking size data information of the goods and the first stacking size data information of the goods, the deviation value of the stacking size of the goods is calculated by using a cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function to obtain the deviation value data information of the stacking size of the goods; R4. Based on the data information of the deviation value of the cargo stacking size, a filling model of the truck loading filler is constructed, and the filling position point of the filler is predicted to obtain the predicted filling position point matrix data information of the filler; R5. Based on the predicted filling position point matrix data information of the filler, the filling position points of the filler are optimized using a particle swarm optimization algorithm based on adaptive weights to obtain the optimized filling position point data information of the filler.

2. The optimization control method for filling a van with a filling material according to claim 1, characterized in that: The method further comprises: R6. Based on the optimized filling position point data information of the filler, establish an optimized control function F for filling the filler, Among them, x is the filling position point data information of the optimized filler, α1, α2 and α3 are the optimization control factors of the filling of the filler, and the filling of the filler is optimized and controlled to obtain the optimized control data information of the filling of the truck loading filler.

3. The optimization control method for loading a van with a filling material according to claim 2, characterized in that: The optimization control factors α1, α2 and α3 of the filler filling are, Wherein, x is the filling position point data information of the optimized filler.

4. The optimization control method for loading a van with a filling material according to claim 1, characterized in that: In step R1, the construction of the overall stacking model of the goods and characterization of the size of the goods includes: R11. Based on the order data information of the goods, establish the goods stacking function Q, Among them, y is the order data information of the goods, σ1 and σ2 are the goods stacking conversion factors, and the goods stacking data set is characterized to obtain the data information of the goods stacking data set; R12. Input the cargo stacking data set into the overall cargo stacking model for training and learning, and determine the cargo stacking size characterization function W, Among them, z is the data information of the cargo stacking data set, β1, β2 and β3 are the size conversion factors of the overall cargo stacking, and the trained overall cargo stacking model is obtained; R13. Based on the trained overall stacking model of the goods, the order data information of the goods is input, the stacking size of the goods is characterized, and the first stacking size data information of the goods is obtained.

5. The optimization control method for loading a van with a filling material according to claim 4, characterized in that: The constraint function f of the size conversion factors β1, β2 and β3 of the overall stacking of the goods is, The value range of the constraint function f is (0,1).

6. The optimization control method for loading a van with a filling material according to claim 1, characterized in that: In step R2, the use of the improved SAM image segmentation algorithm to estimate the stacking size of the stacked materials includes: R21. Based on the 3D scanning image data information of the stacked material, a pixel matrix of the stacked material is constructed to obtain pixel matrix data information of the stacked material; R22. Based on the pixel matrix data information of the stacked material, a characteristic pixel extraction function U of the stacked material is constructed. Wherein, a is the pixel matrix data information of the stacked material, δ1, δ2 and δ3 are the characteristic pixel extraction factors of the stacked material, and the characteristic pixel points of the stacked material are extracted to obtain the extracted characteristic pixel matrix data information of the stacked material; R23. Based on the extracted characteristic pixel matrix data information of the stacked material, an image segmentation function P of the stacked material is established. Among them, b is the characteristic pixel matrix data information of the stacked material after extraction, γ1 and γ2 are the image segmentation determining factors, and the image of the stacked material is segmented to obtain the image data information of the segmented stacked material; R24. Based on the image data information of the segmented stacked material, a stacking size characterization function S of the stacked material is established. Among them, c is the image data information of the segmented stacking material, η1, η2 and η3 are the stacking size covariance constant parameters of the stacking material, and the stacking size of the stacking material is calculated to obtain the second stacking size data information of the goods.

7. The optimization control method for loading a van with a filling material according to claim 1, characterized in that: In step R3, the method of calculating the deviation value of the cargo stacking size by using the cargo stacking size difference algorithm based on Fourier series fitting of a one-dimensional probability density function includes: R31. Based on the second stacking size data information of the goods, establish a Fourier series fitting one-dimensional probability density function g1 of the second stacking size of the goods, Among them, r2 is the data information of the second stacking size of the goods, λ1 and λ2 are the probability density distribution factors of the second stacking size of the goods, and the probability distribution of the second stacking size of the goods is characterized to obtain the probability distribution data information of the second stacking size of the goods; R32. Based on the first stacking size data information of the goods, establish a Fourier series fitting one-dimensional probability density function g2 of the first stacking size of the goods, Among them, r1 is the data information of the first stacking size of the goods, μ1, μ2 and μ3 are the probability density distribution factors of the first stacking size of the goods, and the probability distribution of the first stacking size of the goods is characterized to obtain the probability distribution data information of the first stacking size of the goods; R33. Based on the probability distribution data information of the first stacking size of the goods and the probability distribution data information of the second stacking size of the goods, a difference function G of the stacking size of the goods is established, Among them, m1 is the probability distribution data information of the first stacking size of the goods, m2 is the probability distribution data information of the second stacking size of the goods, θ1, θ2 and θ3 are the penalty weights of the stacking size of the goods, and the deviation value of the stacking size of the goods is calculated to obtain the deviation value data information of the stacking size of the goods.

8. The optimization control method for loading a van with a filling material according to claim 1, characterized in that: In step R4, the construction of a filling model for loading a truck with fillers and prediction of the filling position of the fillers include: R41. Based on the deviation value data information of the cargo stacking size, a deviation value data set of the cargo stacking size is constructed to obtain a deviation value data set of the cargo stacking size; R42. Input the deviation value data set of the cargo stacking size into the filling model of the truck loading filler for training and learning, and determine the filling position point prediction function H of the filler, Among them, h is the deviation value data set of the cargo stacking size, ρ1, ρ2 and ρ3 are the bias constant parameters of the model, and the trained filling model of the truck loading filler is obtained; R43. Based on the trained filling model of the truck loading fillers, the deviation value data information of the truck stacking size is input, the filling position points of the fillers are predicted, and the predicted filling position point matrix data information of the fillers is obtained.

9. The optimization control method for loading a van with a filling material according to claim 1, characterized in that: In step R5, the optimization of the filling position points of the filler using the particle swarm optimization algorithm based on adaptive weights includes: R51. Based on the predicted filling position point matrix data information of the filler, the population parameters of the particle population are initialized, the maximum number of iterations is determined, and the initialized particle population data information is obtained; R52. Based on the initialized particle population data information, establish the fitness function J of the population individuals, Among them, q is the data information of the particle population after initialization, ω1 and ω2 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the fitness value data information of the population individuals; R53. Based on the fitness value data information of the population individuals, establish the target optimization function Z, Among them, v is the fitness value data information of the population individual, ε1, ε2 and ε3 are the adaptive weights of the population individual, and the filling position points of the filler are optimized to obtain the optimized filling position point data information of the filler.

10. An optimization control system for loading a van with a filling material, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the method for optimizing the filling of a van loading filler as claimed in any one of claims 1 to 9.

Images