CN114067048A - Material transfer visual intelligent system and construction method - Google Patents

Abstract

The invention discloses a material transfer visual intelligent system and a construction method, wherein the construction method comprises the following steps: building a three-dimensional frame; building a model; 3D modeling and visual scene construction, so far, a material transfer visual intelligent system is formed, and the system comprises a task module, a manual input module, a material scanning module, a scheme downloading module, an intelligent generation module and a scheme checking module. According to the invention, a feasible loading mode can be determined according to the specification of the transport vehicle and the information such as the shape, the size, the quantity, the weight and the like of the goods, so that under the condition of meeting the given constraints such as volume constraint, bearing capacity constraint, stability constraint, loading sequence and the like, the total volume of the goods contained in the container is as large as possible, namely the filling rate of the container is as large as possible, thereby more effectively utilizing the space of the transport container in the transport process and reducing the transport cost.

Description

Material transfer visual intelligent system and construction method

Technical Field

The invention belongs to the technical field of material transfer, and particularly relates to a material transfer visual intelligent system and a construction method.

Background

The current forces face significant challenges in the transfer of materials:

(1) the requirement of the whole territory operation requires that the guarantee equipment can be quickly transferred to the field and loaded flexibly, and higher requirements are provided for quickly checking and examining materials.

(2) The loaded materials are various in types and complex in sequential arrangement, specific materials are not easy to find during unloading, a missing tool is not searched by an effective means, a large amount of manpower and time can be spent for slow searching, and the efficiency is extremely low.

(3) The goods and materials label can not satisfy the management and control of current goods and materials location. The material label is easy to damage, drop and pollute; the goods and materials information can not be transmitted in a narrow space, so that the relevant personnel can not be effectively positioned and collected.

(4) The material management work can not be responsible for people, and when the material is lost, the situation that the responsibility is mutually pushed and removed by operating personnel easily occurs. The imperfect material management responsibility system directly causes the low utilization rate of material loading and unloading, and causes the problems of asset loss, tool loss, potential safety hazard and the like.

The traditional material transferring method for troops is an artificial experience operation method (as the name suggests), and a logistics platform related to transfer in the market does not have three functions of visualization, intelligent generation and human-computer interaction modification (or only satisfies one of the three functions), so that the efficiency of the material transferring working process is influenced.

Disclosure of Invention

Aiming at the existing problems, the invention provides a method for building a visual intelligent system for material transfer, which solves the problem of large-scale material transfer and can quickly, systematically and automatically generate a transfer scheme for large-scale materials.

The technical scheme adopted by the invention is as follows:

the method for building the material transfer visual intelligent system comprises the following steps:

building a three-dimensional frame: the application front-end main body uses a Vue.js framework, and on the basis, a WebGL function packaged by a three.js framework is used for realizing a three-dimensional part main body;

model: building an object model through blend modeling software, loading the model by using a three.js loader, and converting a text/binary model file into a three.js object structure;

3D modeling and visualization scene construction:

a home. Constructing a page layout through a plurality of components, wherein the components comprise a view component, a text component, a block component and an input component;

firstly, an array containing a plurality of objects is established in a database, and different elements in the objects are displayed by using a block component above a page through indexes of each array object, namely, the array comprises a task module, a manual input module, a scanning material module, a scheme downloading module, an intelligent generation module and a scheme checking module;

setting up respective interface layouts in a task module, a manual input module, a scanning material module, a scheme downloading module, an intelligent generation module and a scheme checking module, writing a click event click module (index) function in a view in a method, changing a current index into an index of a current click item, judging whether the current index is a self object index or not in different views, and obtaining a judgment result through v-show so as to realize the function of switching different interfaces;

after the page is built, the function is built in the method, the function is uniformly written in the js file, and the js file is stored in each module so as to call the function.

Preferably, different rendering styles in the imported files of free.

Preferably, in the building of the interface layout, Python language is used for realizing 3D animation modeling, and the method comprises the steps of realizing visual images and three-dimensional shapes by using a Matplotlib drawing library, a NumPy tool and a 3D drawing library, and realizing 3D dynamic visual operation by using a mayavi library.

Visual intelligent system is transported to goods and materials includes:

the task module is used for checking a task list, newly building a daily task and determining a carrier;

the manual input module is used for inputting material data;

the scanning material module is used for scanning material data and automatically generating a material transferring scheme after the material data is imported;

the intelligent generation module is used for receiving the material transfer scheme and displaying the material transfer method in a three-view mode;

the scheme viewing module is used for viewing the historical scheme and displaying the position of the goods and materials in the delivery vehicle cabin;

and the scheme downloading module is used for downloading and storing the material transferring scheme, generating an electronic table scheme list and calibrating the coordinate position determined by each material.

Preferably, a space planning model algorithm is stored in the scanned material module, the space planning model algorithm is programmed by using VC + +6.0, the data processing process is linked with a database, and a standard data communication interface is used for connecting the database with the uni-app at the front end of the system development platform.

Preferably, the space planning model algorithm comprises the following steps:

step 1: according to the space size of the imported transport means, the unit is meter; recording the length as x, the width as y and the height as h;

step 1: the size and length of each material are respectively recorded as: x is the number of₁ x₂ x₃ …… x_n(ii) a The widths are respectively noted as: y is₁ y₂ y₃…… y_n(ii) a High is respectively noted as: h is₁ h₂ h₃ …… h_n(ii) a Taking the maximum value of three groups of numbers:

X＝max(x₁ x₂ x₃ …… x_n)

Y＝max(y₁ y₂ y₃ …… y_n)

H＝max(h₁ h₂ h₃ …… h_n)

dividing the space of the transportation platform into (X/X) X (Y/Y) X (H/H) subspaces, marking, starting from an origin, wherein the space coordinates of grids are (0, 0, 0) to ((X/X), (Y/Y), (H/H)), the sequence number of each grid is (n) ═ H '· 3+ Y'. 1+ X '. 1, and X' Y 'H' is the coordinate of each grid, the sequence numbers of each grid are arranged from large to small, and the larger the sequence number of the grid space is, the more important the placed articles are;

step 2: calculating the importance degree of each material, namely W, wherein the importance degree of the material comprises material attributes, a gravity center position and material weight, and the material attributes are endowed with importance degree scores of different materials through an expert scoring method; the function for calculating the importance of the materials is obtained as follows:

W＝α·W-β·m+Z

in the formula, the larger W is, the larger the sequence number of the corresponding spatial position is, and W represents the attribute score of the material; m represents the weight of the material; alpha and beta are constant values; z is a modified regulation coefficient, and the assignment conditions are as follows: (1) for any material, the initial value is 0; (2) if the material scheme generated for the first time does not meet the following constraint conditions, introducing a Z value, wherein the constraint conditions are as follows:

in the formula, X "y" h "is the center of gravity of the total material, and the center of the X YH cabin;

and step 3: generating the placing position of the material in the platform space according to the calculated importance degree, wherein the larger the W value is, the larger the sequence number of the corresponding space position is, and then generating a loading scheme;

and 4, step 4: carrying out height correction on the loading scheme;

and 5: carrying out depth correction on the loading scheme;

step 6: judging whether the corrected loading scheme meets constraint conditions or not, and if so, generating a final scheme; otherwise, introducing the adjustment correction coefficient and returning to the step 2.

Preferably, in step 2, the value processes of α and β are as follows:

adopting a BP neural network model, firstly setting an objective function:

in the formula, Σ v_iRepresents the total volume of loaded materials, V represents the total space for transportation, and mu represents the space utilization rate; the input layer of the BP neural network model is represented by (alpha, beta, Z, w, m) through vectors, the output layer is (mu), the weight set of the hidden layer performs self-repairing and updating according to a Hebb rule, three layers of hidden layers are set for perception training, results are output, and the end condition is as follows: mu is more than or equal to 90 percent; record the α, β values.

Preferably, in step 4, the loading solution height correction algorithm:

(1) judging whether all the subspaces are labeled, if so, continuing the step (2);

(2) selecting the unmarked subspace, judging the h' coordinate of the subspace is larger than 1, if so, continuing the step (3), otherwise, reaching the step (1)

(3) And (3) searching a subspace which is equal to the x ', y' coordinates of the subspace in the labeled subspace and has the H-coordinate of H '-1, if the subspace which meets the condition exists, adjusting a position of the material corresponding to the subspace downwards, placing the material on the subspace with the coordinates of (x', y ', H' -1), marking the subspace, returning to the step (1) until all the subspaces are marked, and ending.

Preferably, in step 4, the loading scheme depth correction algorithm:

(1) judging whether all the subspaces are labeled, if so, continuing the step (2);

(2) selecting the unmarked subspace, judging the x' coordinate of the subspace is larger than 1, if so, continuing the step (3), otherwise, reaching the step (1)

(3) And (3) searching a subspace which is equal to the y ', h' coordinates of the subspace in the labeled subspace and has the X coordinate of X '-1, if the subspace which meets the condition exists, adjusting a position of the material corresponding to the subspace downwards, placing the material on the subspace with the coordinates of (X' -1, y ', h'), marking the subspace, returning to the step (1) until all the subspaces are marked, and ending.

The invention has the beneficial effects that: according to the invention, a feasible loading mode can be determined according to the specification of the transport vehicle and the information such as the shape, the size, the quantity, the weight and the like of the goods, so that under the condition of meeting the given constraints such as volume constraint, bearing capacity constraint, stability constraint, loading sequence and the like, the total volume of the goods contained in the container is as large as possible, namely the filling rate of the container is as large as possible, thereby more effectively utilizing the space of the transport container in the transport process and reducing the transport cost.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a diagram illustrating a display interface of a manual input module according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating a display interface of the intelligent generation module according to this embodiment;

FIG. 3 is a diagram illustrating a display interface of the plan view module in the present embodiment;

FIG. 4 is a flow chart of the spatial programming model algorithm in this embodiment;

FIG. 5 is a flow chart illustrating the height correction of the material scheme in the present embodiment;

fig. 6 is a flowchart illustrating the material scheme depth correction in the present embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The embodiment specifically provides a method for building a material transfer visual intelligent system, which comprises the following steps:

three-dimensional frame

The application front-end main body uses a Vue.js framework, and on the basis, the WebGL function packaged by the three.js framework is used for realizing the three-dimensional part main body, so that the cross-platform use of the program can be facilitated. WebGL requires graphical knowledge, and if used directly, must have full knowledge of shader syntax and write the vertex shader itself. Js solves the complex problem of WebGL development, and encapsulates concepts such as scenes, cameras, geometry, 3D model loaders, light, materials, shaders, animations, particles, mathematical tools and the like. Js can be used for conveniently skipping the bottom layers, so that developers can write graphic applications by writing conventional js.

Model (model)

The method comprises the steps of constructing an object model through modeling software such as a blender and the like, loading the model by using a three. Such as JSON/OBJ/MTL/STL, etc. Json can be exported through blend or 3DsMax, each Json has a respective export Json plug-in, and after model maps and animations are processed in software, Json files and corresponding map files are exported to the front end.

3D modeling and visualization scene construction

The interface display and function implementation of the material visualization intelligent system are developed based on a uni-app front-end framework. The uni-app is a front-end framework for developing cross-platform application by using Vue. js, a set of codes is compiled, and the set of codes can be compiled into a plurality of platforms such as Android, iOS, H5 and applets. The material visualization intelligent system is compiled to the platform of H5 and finally displayed on a webpage. And the mode development of HTML5+ CSS + JavaScript is adopted in the program writing process.

According to a UI design draft obtained through design, a home. Firstly, an array containing a plurality of objects is created in data, and different elements in the objects are displayed at the top of a page through indexes of each array object by using a block component, wherein the method comprises the following steps: the task bar is formed by six parts, namely a task module, a manual input module, a scanning material module, a scheme downloading module, an intelligent generation module and a scheme checking module. Different interface layouts can be set up in each module, the current index is changed into the index of the current click item by compiling the @ click event click module (index) function in the view in the method, whether the current index is the self object index is judged by different views, and the judgment result is obtained by v-show, so that the function of switching different interfaces is realized.

And in the building of the lower half part of the page, page rendering is carried out by using different rendering styles in the imported file of free. Cs is a customized rendering file, which contains a large number of rendering styles, including layout styles, colors, fonts, spacing, click animations, etc., and can also obtain various icons which are required to be satisfied from the cs file, i.e., iconfont. By continuously improving the cs file, more required rendering styles are added, the effect required to be realized can be achieved, and the establishment of the next page is simpler and more convenient along with the continuous improvement of the cs file. Various network data on the official network of the uni-app comprise a large amount of cs libraries for reference, and documents are quite rich.

After the whole page construction is completed, the software implementation function and algorithm need to be further improved. There are many buttons in the interface, including new data, scan import data, create spreadsheet, load scenario. The method relates to the storage export of data, the life cycle of a page, the use of hooks for monitoring the page and the like. It also relates to the writing of multi-button event implementation function functions. We can construct the function in method. The functions can also be uniformly written in js files. The js file can call functions in the js file, so that some common functions can be called more conveniently. Meanwhile, when a large number of data formats need to be called for use, in order to enable the display of the page to be smoother, data can be stored in a js file and called by reference.

In the wuzi uni-app project, the frame advantages of the uni-app are well utilized, the vue file, the css file and the js file are separated, and page building and function realization of the whole software system are completed by respectively calling and introducing the three files.

In the aspect of realizing the 3D animation realization technology, the Python language is mainly used for programming. It has the characteristics of easy expansion, glue language and open source. Two three-dimensional visualization and 3D painting libraries, Matplotlib and NumPy, are mainly used for realizing the visualization of images and three-dimensional shapes. And 3d dynamic visualization operation is realized by using a mayavi library.

1. 3D movement

translate3d (x, y, z), which moves elements in these three dimensions, can also be written separately.

translateX(x),translateY(y),translateZ(z).

transform: TranslateX (100 px); // X-axis movement

2. 3D scaling

scale3d (number, number, number), which can also be written separately: scaleX (), scaleY (), scaleZ ().

3. 3D rotation

rotate3D (x, y, z, angle), specifies the coordinate axes that need to be rotated

rotax (angle) is the rotation of an element along the X-axis.

rotatey (angle) is the rotation of an element along the y-axis.

rotatez (angle) is the rotation of an element along the z-axis.

This embodiment still provides a visual intelligent system of material transportation, includes:

the task module is used for checking a task list, newly building a daily task and determining a carrier;

a manual input module for inputting material data, as shown in fig. 1;

the scanning material module is used for scanning material data and automatically generating a material transferring scheme after the material data is imported;

the intelligent generation module is used for receiving the material transfer scheme and displaying the material transfer method in a three-view mode, as shown in fig. 2;

a scenario viewing module for viewing historical scenarios and displaying the locations of the materials in the vehicle bay, as shown in FIG. 3;

and the scheme downloading module is used for downloading and storing the material transferring scheme, generating an electronic table scheme list and calibrating the coordinate position determined by each material.

A space planning model algorithm is stored in the scanning material module, the space planning model algorithm is programmed by using VC + +6.0, the data processing process is linked with a database, and a standard data communication interface is used for connecting the database with the uni-app at the front end of the system development platform.

The space planning model algorithm, as shown in fig. 4, includes the following steps:

step 1: according to the space size of the imported transport means, the unit is meter; recording the length as x, the width as y and the height as h;

step 1: the size and length of each material are respectively recorded as: x is the number of₁ x₂ x₃ …… x_n(ii) a The widths are respectively noted as: y is₁ y₂ y₃…… y_n(ii) a High is respectively noted as: h is₁ h₂ h₃ …… h_n(ii) a Taking the maximum value of three groups of numbers:

X＝max(x₁ x₂ x₃ …… x_n)

Y＝max(y₁ y₂ y₃ …… y_n)

H＝max(h₁ h₂ h₃ …… h_n)

dividing the space of the transportation platform into (X/X) X (Y/Y) X (H/H) subspaces, marking, starting from an origin, wherein the space coordinates of grids are (0, 0, 0) to ((X/X), (Y/Y), (H/H)), the sequence number of each grid is (n) ═ H '· 3+ Y'. 1+ X '. 1, and X' Y 'H' is the coordinate of each grid, the sequence numbers of each grid are arranged from large to small, and the larger the sequence number of the grid space is, the more important the placed articles are;

step 2: calculating the importance degree of each material, namely W, wherein the importance degree of the material comprises material attributes, gravity center positions and material weights, the material attributes are endowed with importance degree scores of different materials by an expert scoring method, and the importance degree scores are specifically shown in the following table:

properties of material	Score of
		Weapon ammunition	5
Precision machine	4
		Aeronautical material equipment	3
Pod rack	2
		Carrying material	1
Others	Self-defining

Centre of gravity position (for airplane only when the transport means is)

Load balancing is carried out, the center of gravity of the total materials is ensured to be close to the center of the cabin of the airplane, the center of gravity calculation method of the total materials can be obtained through the center of gravity calculation formula of the center of gravity of each material (the center of gravity of each material is considered to be the center of the geometric solid of the material), and the difference between the center of gravity of the total materials and the center of the cabin cannot exceed 1 meter.

The larger the weight is, the more the material is placed inwards, namely the sequence number of the corresponding space position is smaller.

The function for calculating the importance of the materials is obtained as follows:

W＝α·w-β·m+z

in the formula, the larger W is, the larger the sequence number of the corresponding spatial position is, and W represents the attribute score of the material; m represents the weight of the material; alpha and beta are constant values; z is a modified regulation coefficient, and the assignment conditions are as follows: (1) for any material, the initial value is 0; (2) if the material scheme generated for the first time does not meet the following constraint conditions, introducing a z value, wherein the z value is defined as:

the materials with the maximum material importance degree correspond to the z value of 1, the material importance degree is the second, the z value is 2, and the ranking is performed sequentially, namely the z value is the sequence number of the ranking of the material importance degree.

The constraint conditions are as follows:

in the formula, X "y" h "is the center of gravity of the total material, and the center of the X YH cabin;

and step 3: generating the placing position of the material in the platform space according to the calculated importance degree, wherein the larger the W value is, the larger the sequence number of the corresponding space position is, and then generating a loading scheme;

and 4, step 4: carrying out height correction on the loading scheme;

and 5: carrying out depth correction on the loading scheme;

step 6: judging whether the corrected loading scheme meets constraint conditions or not, and if so, generating a final scheme; otherwise, introducing the adjustment correction coefficient and returning to the step 2.

The value processes of alpha and beta are as follows:

for the values of alpha and beta, a simple expert scoring method is not adopted any more, because the types of the materials are different and are difficult to be uniformly measured by a constant value, and the properties of the materials are different from the weight of the materials under different conditions, for example, in the case of taking a train as a main transport means, the properties of the materials can determine the importance degree of the materials, but in the case of air transportation, the weight of the materials is more important because the load balancing of an airplane is considered.

In order to solve the problem, I jump out of the field of the traditional method, adopt a neural network algorithm with strong self-adaptation, and the neural network algorithm aims at different environments, uses big data to carry out mass calculation, and finds out the optimal values suitable for different situations through one iteration. Computer technology may be a reality for this algorithm.

Adopting a BP neural network model, firstly setting an objective function:

in the formula, Σ v_iRepresents the total volume of loaded materials, V represents the total space for transportation, and mu represents the space utilization rate; the input layer of the BP neural network model is represented by (alpha, beta, z, w, m) through vectors, the output layer is (mu), the weight set of the hidden layer performs self-repairing and updating according to a Hebb rule, three layers of hidden layers are set for perception training, results are output, and the end condition is as follows: mu is more than or equal to 90 percent; the values of alpha and beta are recorded, and after the space of each material is calculated on the basis of the values, the position of the material is in a high-altitude state, which is not in line with the actual situation, so that the calculation process needs to be corrected once.

The loading solution height correction algorithm, as shown in FIG. 5, includes:

(1) judging whether all the subspaces are labeled, if so, continuing the step (2);

(2) selecting the unmarked subspace, judging the h' coordinate of the subspace is larger than 1, if so, continuing the step (3), otherwise, reaching the step (1)

(3) And (3) searching a subspace which is equal to the x ', y' coordinates of the subspace in the labeled subspace and has the H-coordinate of H '-1, if the subspace which meets the condition exists, adjusting a position of the material corresponding to the subspace downwards, placing the material on the subspace with the coordinates of (x', y ', H' -1), marking the subspace, returning to the step (1) until all the subspaces are marked, and ending.

The loading scheme depth correction algorithm, as shown in fig. 6, includes:

(1) judging whether all the subspaces are labeled, if so, continuing the step (2);

(2) selecting the unmarked subspace, judging the x' coordinate of the subspace is larger than 1, if so, continuing the step (3), otherwise, reaching the step (1)

(3) And (3) searching a subspace which is equal to the y ', h' coordinates of the subspace in the labeled subspace and has the X coordinate of X '-1, if the subspace which meets the condition exists, adjusting a position of the material corresponding to the subspace downwards, placing the material on the subspace with the coordinates of (X' -1, y ', h'), marking the subspace, returning to the step (1) until all the subspaces are marked, and ending.

According to the invention, a feasible loading mode can be determined according to the specification of the transport vehicle and the information such as the shape, the size, the quantity, the weight and the like of the goods, so that under the condition of meeting the given constraints such as volume constraint, bearing capacity constraint, stability constraint, loading sequence and the like, the total volume of the goods contained in the container is as large as possible, namely the filling rate of the container is as large as possible, thereby more effectively utilizing the space of the transport container in the transport process and reducing the transport cost.

The above description is only for the purpose of illustrating the technical solutions of the present invention and not for the purpose of limiting the same, and other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention should be covered within the scope of the claims of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (9)

1. A method for building a material transfer visual intelligent system is characterized by comprising the following steps:

building a three-dimensional frame: the application front-end main body uses a Vue.js framework, and on the basis, a WebGL function packaged by a three.js framework is used for realizing a three-dimensional part main body;

model: building an object model through blend modeling software, loading the model by using a three.js loader, and converting a text/binary model file into a three.js object structure;

3D modeling and visualization scene construction:

a home. Constructing a page layout through a plurality of components, wherein the components comprise a view component, a text component, a block component and an input component;

firstly, an array containing a plurality of objects is established in a database, and different elements in the objects are displayed by using a block component above a page through indexes of each array object, namely, the array comprises a task module, a manual input module, a scanning material module, a scheme downloading module, an intelligent generation module and a scheme checking module;

setting up respective interface layouts in a task module, a manual input module, a scanning material module, a scheme downloading module, an intelligent generation module and a scheme checking module, writing a click event click module (index) function in a view in a method, changing a current index into an index of a current click item, judging whether the current index is a self object index or not in different views, and obtaining a judgment result through v-show so as to realize the function of switching different interfaces;

after the page is built, the function is built in the method, the function is uniformly written in the js file, and the js file is stored in each module so as to call the function.

2. The material transfer visualization intelligent system building method according to claim 1, wherein different rendering styles in imported files of free.

3. The method for building the material transfer visualization intelligent system according to claim 1, wherein in the building of the interface layout, Python language is used for realizing 3D animation modeling, and the method comprises the steps of using Matplotlib drawing library, a NumPy tool and a 3D drawing library to realize visualization images and three-dimensional shapes, and using mayavi library to realize 3D dynamic visualization operation.

4. A material transfer visualization intelligent system built according to any one of claims 1-3, comprising:

the task module is used for checking a task list, newly building a daily task and determining a carrier;

the manual input module is used for inputting material data;

the scanning material module is used for scanning material data and automatically generating a material transferring scheme after the material data is imported;

the intelligent generation module is used for receiving the material transfer scheme and displaying the material transfer method in a three-view mode;

the scheme viewing module is used for viewing the historical scheme and displaying the position of the goods and materials in the delivery vehicle cabin;

and the scheme downloading module is used for downloading and storing the material transferring scheme, generating an electronic table scheme list and calibrating the coordinate position determined by each material.

5. The material transfer visualization intelligent system according to claim 4, wherein a space planning model algorithm is stored in the material scanning module, the space planning model algorithm is programmed by using VC + +6.0, the data processing process is linked with a database, and the database is connected with a system development platform front end uni-app by using a standard data communication interface.

6. The material transfer visualization intelligent system building method according to claim 5, wherein the space planning model algorithm comprises the following steps:

step 1: according to the space size of the imported transport means, the unit is meter; recording the length as x, the width as y and the height as h;

step 1: the size and length of each material are respectively recorded as: x is the number of₁x₂x₃……x_n(ii) a The widths are respectively noted as: y is₁y₂y₃……y_n(ii) a High is respectively noted as: h is₁h₂h₃……h_n(ii) a Taking the maximum value of three groups of numbers:

X＝max(x₁x₂x₃……x_n)

Y＝max(y₁y₂y₃……y_n)

H＝max(h₁h₂h₃……h_n)

dividing the space of the transportation platform into (X/X) X (Y/Y) X (H/H) subspaces, marking, starting from an origin, wherein the space coordinates of grids are (0, 0, 0) to ((X/X), (Y/Y), (H/H)), the sequence number of each grid is (n) ═ H '· 3+ Y'. 1+ X '. 1, and X' Y 'H' is the coordinate of each grid, the sequence numbers of each grid are arranged from large to small, and the larger the sequence number of the grid space is, the more important the placed articles are;

step 2: calculating the importance degree of each material, namely W, wherein the importance degree of the material comprises material attributes, a gravity center position and material weight, and the material attributes are endowed with importance degree scores of different materials through an expert scoring method; w ═ α · W- β · m + Z

In the formula, the larger W is, the larger the sequence number of the corresponding spatial position is, and W represents the attribute score of the material; m represents the weight of the material; alpha and beta are constant values; z is a modified regulation coefficient, and the assignment conditions are as follows: (1) for any material, the initial value is 0; (2) if the material scheme generated for the first time does not meet the following constraint conditions, introducing a Z value, wherein the constraint conditions are as follows:

in the formula, x "y" h "is the center of gravity of the total material, the center of the XYH cabin;

and step 3: generating the placing position of the material in the platform space according to the calculated importance degree, wherein the larger the W value is, the larger the sequence number of the corresponding space position is, and then generating a loading scheme;

and 4, step 4: carrying out height correction on the loading scheme;

and 5: carrying out depth correction on the loading scheme;

step 6: judging whether the corrected loading scheme meets constraint conditions or not, and if so, generating a final scheme; otherwise, introducing the adjustment correction coefficient and returning to the step 2.

7. The method for building the material transfer visualization intelligent system according to claim 5, wherein in the step 2, the value processes of α and β are as follows:

adopting a BP neural network model, firstly setting an objective function:

in the formula, Σ v_iRepresents the total volume of loaded materials, V represents the total space for transportation, and mu represents the space utilization rate; the input layer of the BP neural network model is represented by (alpha, beta, Z, w, m) through vectors, the output layer is (mu), the weight set of the hidden layer performs self-repairing and updating according to a Hebb rule, three layers of hidden layers are set for perception training, results are output, and the end condition is as follows: mu is more than or equal to 90 percent; record the α, β values.

8. The material transfer visualization intelligent system building method according to claim 5, wherein in step 4, a loading scheme height correction algorithm:

(1) judging whether all the subspaces are labeled, if so, continuing the step (2);

(2) selecting the unmarked subspace, judging the h' coordinate of the subspace is larger than 1, if so, continuing the step (3), otherwise, reaching the step (1)

(3) And (3) searching a subspace which is equal to the x ', y' coordinates of the subspace in the labeled subspace and has the H-coordinate of H '-1, if the subspace which meets the condition exists, adjusting a position of the material corresponding to the subspace downwards, placing the material on the subspace with the coordinates of (x', y ', H' -1), marking the subspace, returning to the step (1) until all the subspaces are marked, and ending.

9. The material transfer visualization intelligent system building method according to claim 5, wherein in step 4, a loading scheme depth correction algorithm:

(1) judging whether all the subspaces are labeled, if so, continuing the step (2);

(2) selecting the unmarked subspace, judging the x' coordinate of the subspace is larger than 1, if so, continuing the step (3), otherwise, reaching the step (1)

(3) And (3) searching a subspace which is equal to the y ', h' coordinates of the subspace in the labeled subspace and has the X coordinate of X '-1, if the subspace which meets the condition exists, adjusting a position of the material corresponding to the subspace downwards, placing the material on the subspace with the coordinates of (X' -1, y ', h'), marking the subspace, returning to the step (1) until all the subspaces are marked, and ending.

Images