CN110288704B - Intelligent design method and system for three-dimensional industrial product - Google Patents
Intelligent design method and system for three-dimensional industrial product Download PDFInfo
- Publication number
- CN110288704B CN110288704B CN201910582878.3A CN201910582878A CN110288704B CN 110288704 B CN110288704 B CN 110288704B CN 201910582878 A CN201910582878 A CN 201910582878A CN 110288704 B CN110288704 B CN 110288704B
- Authority
- CN
- China
- Prior art keywords
- model
- module
- effect
- dimensional
- decomposition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent design method and system of three-dimensional industrial products, belonging to the field of industrial design, by directly inputting the specification parameters and the functional effect parameters, the final three-dimensional industrial product model can be directly output, and simultaneously, the material list of each part of the three-dimensional model is also output, thereby the efficiency of the design is higher, and meanwhile, the method passes the verification of the function effect and the feasibility for three times during the design, so that the designed product is more accurate and better meets the requirements of users, meanwhile, the condition of rework can be greatly reduced, and through the initial formation of the early-stage model, then the comparison of the functional effect parameters is corrected, and then the decomposition and recombination are carried out for the second time, so that the design precision is more accurate, moreover, the material is richer, the designed three-dimensional product is very good, and the three-dimensional product has more outstanding aesthetic effect compared with the three-dimensional product designed by artificial limited materials.
Description
Technical Field
The invention relates to the field of decoration design, in particular to an intelligent design method and system for a three-dimensional industrial product.
Background
The existing mold design technology needs to make an integral 3D model (local parts may be parameterized and associated), project a 2D engineering drawing, edit a material list table, and perform interference check, and the work of each link is discontinuous, so that the problems of long design period, more interference errors and great reworking brought to manufacturing exist. For example, an automobile mold usually needs 7 to 60 days in design according to the ease and difficulty, and rework is often generated due to design problems during debugging of the mold, which results in a long debugging period. Therefore, it is necessary to design a method for automatically generating a three-dimensional model, a two-dimensional engineering drawing, and a bill of materials (BOM) table, so as to greatly improve the efficiency of mold design and manufacture and significantly reduce the rework amount in the manufacturing process. However, the existing generated three-dimensional model map has many requirements which cannot meet the design of people, so that the method needs to be designed for efficient and accurate intelligent design of three-dimensional products by frequent rework, manual design is reduced, and the efficiency of factories is greatly improved
Disclosure of Invention
The invention aims to provide an intelligent design method and system for a three-dimensional industrial product, and aims to solve the technical problems of low three-dimensional design efficiency and poor effect of the existing factory product.
An intelligent design method of a three-dimensional industrial product, comprising the following steps:
step 1: inputting specification parameters and functional effect parameters of a three-dimensional product to be designed;
step 2: positioning and transforming the specification parameters to obtain standard coordinate data, and decomposing and transforming the functional effect parameters to obtain decomposed functional effect parameters;
and step 3: establishing a three-dimensional coordinate, mapping the transformed specification parameters into the three-dimensional coordinate, and then connecting every three or more coordinates with each other and rendering to generate a preliminary three-dimensional model;
and 4, step 4: acquiring a primary three-dimensional model hexahedron, comparing the hexahedron with the decomposed functional effect, reversely translating the plane graph according to the decomposed functional effect when a difference exists between the functional effect to be realized by each surface and the decomposed functional effect, and comparing and correcting the reversely translated plane graph and the hexahedron one by one to obtain a corrected hexahedron;
and 5: recombining the corrected hexahedron to generate a corrected three-dimensional model, and comparing the coordinates of the corrected three-dimensional model with the coordinates of the primary three-dimensional model, wherein the comparison process comprises the following steps: calculating a coordinate data mean value, endowing polarity according to the original coordinate, and regenerating a three-dimensional model;
step 6: decomposing the regenerated three-dimensional model into a plurality of decomposition modules by function and effect;
and 7: collecting the functional effects of all the decomposition modules to obtain a decomposition module functional effect set;
and 8: decomposing the functional effect set to obtain independent functional effect elements;
and step 9: semantic retrieval is carried out on each independent function effect element to summarize all the semantic identical function effect elements, and an independent function effect element model is established;
step 10: the independent function effect meta-model interprets the model component elements which can be realized by each independent function effect element and establishes a model component meta-model;
step 11: the model component meta-model generates a functional effect model decomposition module;
step 12: judging the feasibility of each decomposition module by using big data comparison, and comparing the feasibility with the function effect parameters after initial input transformation to select the decomposition module of the optimal model;
step 13: and recombining the decomposition modules of the optimal model into a final three-dimensional model, and outputting a material list of the decomposition modules of the optimal model.
Further, the specific process of step 2 is as follows:
when the specification parameters are converted, the length, width and height values are subjected to same-unit data conversion, one point is selected as an original point, three-dimensional coordinate data of each point is determined according to the distance relation between the length, width and height values and the coordinate points, then the number set of each coordinate point is summarized, and the functional effect parameter decomposition and conversion process is that functional effect semantics are searched in an existing Chinese dictionary to break words, and a plurality of decomposition functional effect parameters are obtained.
Further, in the step 3, every three or more coordinates are connected with each other by a line, the line is a straight line, and the straight lines are connected in parallel by a transverse line during rendering and rendered into a three-dimensional body.
Further, the decomposition process of step 6 is as follows: and searching a corresponding component module for the regenerated three-dimensional model by taking the decomposed functional effect parameters as a unit and the functions and effects, and then decomposing the corresponding component module to obtain a decomposed module of the regenerated three-dimensional model.
Further, in the step 7, the function and effect collection process is to decompose the achievable functions and effects based on the decomposition module, then search the same or similar function and effect parameters in the network based on the achievable functions and effects as a secondary reference, and collect all the parameters to obtain the function and effect set of the decomposition module.
Further, the specific process of step 8 is as follows: decomposing each decomposed functional effect parameter in the functional effect set into functional effect elements with minimum granularity, describing the decomposed functional effect parameters based on the use case diagram of the UML, decomposing each decomposed functional effect parameter into the functional effect elements with minimum granularity until the functional effects of all the decomposed functional effect parameters are not subdivided, obtaining the functional effect elements which are independent from each other, and obtaining the functional effect elements which cannot have the same effect information and semantic overlapping effect,
the following relations are satisfied between the functional effect elements:
wherein R represents an upper level functional effect to be divided, R1，r2，r3，···，ri，···，rnRepresenting n functional effect elements obtained after decomposition, and obtaining an initial personalized initial functional effect model according to the n functional effect elements.
Further, the specific process of step 9 is as follows:
using a word segmentation tool to segment words of the independent function effect elements, and obtaining binary linguistic training data by using a window with the size of 3 and the step length of 1; carrying out Word2Vec model training on binary linguistic training data to obtain Word vector representation; calculating the residual value of an included angle between every two word vectors vi and vj to serve as the similarity of two words, and obtaining a similarity measurement matrix; and obtaining 3 words which are most adjacent to the word vi through measurement, namely obtaining a synonym table of the independent functional effect elements by the 3 synonyms of the vi, and then searching the synonyms through the network.
Further, the process of the reverse translation in step 10 is to search, according to each independent function effect element, a mechanical component that realizes the independent function effect element, and combine all the mechanical components together to obtain a model component meta-model.
Further, in step 11, each component element is combined with each other, and the combination of the combined decomposition module, the combined component element and the corresponding effect element becomes a combined model decomposition module, the combined model decomposition module and the corresponding functional effect parameter are input into the existing internet mechanical module database for feasibility verification, and the feasible decomposition modules are collected.
A system of an intelligent design method of a three-dimensional industrial product comprises a parameter input summarizing module, a parameter transformation module, a coordinate establishment model generation module, a plan view acquisition-function comparison module, a correction module, a first model component decomposition module, a component function effect collection module, a function effect decomposition module, an independent function effect element model establishment module, a model component element model establishment module, a second model component decomposition module, a model component feasibility judgment module and a model generation-material sheet output module;
the parameter input summarizing module is connected with the parameter transformation module and is used for inputting specification parameters and functional effect parameters of a three-dimensional product to be designed;
the parameter transformation module is connected with the coordinate establishment model generation module and used for positioning and transforming the specification parameters to obtain standard coordinate data and decomposing and transforming the functional effect parameters to obtain decomposed functional effect parameters;
the coordinate establishing model generating module is connected with the plan view acquiring-function comparing module and used for establishing three-dimensional coordinates, mapping the transformed specification parameters into the three-dimensional coordinates, and then connecting lines among every three or more coordinates and rendering to generate a preliminary three-dimensional model;
the plan obtaining-function comparing module is connected with the correcting module and is used for obtaining a primary three-dimensional model six-face image, comparing the six-face image with the decomposed function effect, reversely translating the plan image according to the decomposed function effect when there is a difference, and comparing and correcting the reversely translated plan image and the six-face image one by one to obtain a corrected six-face image;
the correction module is connected with the first model component decomposition module and used for recombining the corrected hexahedron to generate a corrected three-dimensional model and comparing the coordinates of the corrected three-dimensional model with the coordinates of the primary three-dimensional model, and the comparison process is as follows: calculating a coordinate data mean value, endowing polarity according to the original coordinate, and regenerating a three-dimensional model;
the first model component decomposition module is connected with the component function and effect collection module and is used for decomposing functions and effects of the regenerated three-dimensional model to obtain a plurality of decomposition modules;
the component function effect collection module is connected with the function effect decomposition module and is used for collecting the function effects of all the decomposition modules to obtain a decomposition module function effect set;
the function effect decomposition module is connected with the independent function effect element model building module and is used for decomposing the function effect set to obtain independent function effect elements;
the model building module for building the independent function effect elements is connected with the model building component element model module and is used for performing semantic retrieval on each independent function effect element, summarizing all function effect elements with the same semantic meaning and building an independent function effect element model;
the model component meta-model building module is connected with the second model component decomposition module and is used for the independent function effect meta-model to decipher the model component elements which can be realized by each independent function effect element and build a model component meta-model;
the second model component decomposition module is connected with the model component feasibility judgment module and is used for generating a functional effect model decomposition module by the model component meta-model;
the model component feasibility judgment module is connected with the model generation-material bill output module and used for judging the feasibility of each decomposition module by using big data comparison and selecting the decomposition module of the optimal model by comparing with the function effect parameters after initial input transformation;
and the model generation-material bill output module is used for recombining the decomposition modules of the optimal model into a final three-dimensional model and outputting the material bill of the decomposition module of the optimal model.
By adopting the technical scheme, the invention has the following technical effects:
according to the method, after specification parameters and functional effect parameters are directly input, a final three-dimensional industrial product model can be directly output finally, and simultaneously material lists of all parts of the three-dimensional model are output, so that the design efficiency is higher.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a block diagram of the system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings by way of examples of preferred embodiments. It should be noted, however, that the numerous details set forth in the description are merely for the purpose of providing the reader with a thorough understanding of one or more aspects of the present invention, which may be practiced without these specific details.
Referring to fig. 1, the present invention provides an intelligent design method for a three-dimensional industrial product, which includes the following steps:
step 1: inputting specification parameters and functional effect parameters of a three-dimensional product to be designed. The specification parameters generally include data information such as length, width and the like of the product, or further include information such as color and the like, and the specific data information is set when a user starts inputting the specific data information by himself. The functional effect parameters comprise functional parameters and effect parameters, and the functional parameters are which functions the product needs to realize, such as a stool, the required functions are stable, a person can sit on the stool, and then the stool can have the functions of sliding and the like. The effect parameter needs including this stool is stable that the tripod is stable or the stable advantage that realizes in four corners, uses the scene at what, if for student's stool or give staff's stool, student's stool needs stability good, and is durable, and staff's removal is convenient, makes things convenient for work and handles affairs etc. realizes reaching an effect such as how convenient to use or place convenience.
Step 2: and positioning and transforming the specification parameters to obtain standard coordinate data, and decomposing and transforming the functional effect parameters to obtain decomposed functional effect parameters. When the specification parameters are converted, the length, width and height values are subjected to same-unit data conversion, then one point is selected as an original point, three-dimensional coordinate data of each point is determined according to the distance relation between the length, width and height values and the coordinate points, then the number set of each coordinate point is summarized, and the functional effect parameter decomposition and conversion process is that functional effect semantics are searched for the existing Chinese dictionary semantics to perform word segmentation, and a plurality of decomposition functional effect parameters are obtained. In the specification parameter positioning transformation, for example, a stool needs to be set, the height of the stool given by a user is h, the width is F, the length is L, the height of a stool plate of the stool is h1, one point is set or selected as an origin, and an angle between the stool plate and a backrest is selected as the origin, so that other three points of the stool plate come out, namely (L, 0, 0), (0, F, 0) and (L, F, 0), if the thickness of the stool plate is set by the user, coordinates of several points at the bottom of other stool plates, namely the thickness of the stool plate in the vertical direction can be calculated, or the thickness of the stool plate is subtracted, and if the thickness is not set, the system automatically selects the thickness according to the existing stool. The coordinates of the top point of the backrest are (0, 0, h-h1), the coordinates of the other point are (L, 0, h-h1) or (0, F, h-h1), the thickness and the like are the same as the above, and the coordinates of the bottom foot are the same as the above, so that the parameter (length, width and height) positioning transformation can be realized and transformed into the required coordinate parameters.
And step 3: and establishing a three-dimensional coordinate, mapping the transformed specification parameters into the three-dimensional coordinate, and then connecting every three or more coordinates with each other and rendering to generate a preliminary three-dimensional model. And connecting lines among every three or more than three coordinates, wherein the connecting lines are straight lines, and the straight lines are connected in parallel through transverse lines during rendering and are rendered into a three-dimensional body.
And 4, step 4: and acquiring a primary three-dimensional model hexahedron, comparing the hexahedron with the decomposed functional effect, reversely translating the plane graph according to the decomposed functional effect when there is a difference according to the functional effect to be realized by each plane and the decomposed functional effect, and then comparing and correcting the reversely translated plane graph and the hexahedron one by one to obtain a corrected hexahedron. When the six-side diagram is compared with the decomposed functional effect, the characteristics of the six-side diagram are firstly identified through the existing image identification algorithm, for example, if the stool identifies that the stool legs have four or six heights, and meanwhile, the pulley is arranged at the bottom, the stool can be known to be movable according to the six-side diagram and can be moved with the specific function or not, if the stool can be moved in the function, the stool is in accordance with the function, and the change is not needed. But if can not remove in the function, only have the function of stable support, not conform to with the functional effect, need to carry out the back translation to the parameter of functional effect, then be the function of support for the stool function, have stable fixed function, the environment of use is school, can conveniently folding effect, then according to this effect, according to the size of original six pictures, revise the stool foot, for example remove the bottom wheel, the stool foot quantity is three or four, then the stool foot is not fixed with being connected of bench, be a structure that can buckle or rotatory structure, then change the junction into rotatory or the structure of buckling at the stool foot department of original six pictures, realize six pictures and functional effect contrast, discover the difference simultaneously and revise.
And 5: recombining the corrected hexahedron to generate a corrected three-dimensional model, and comparing the coordinates of the corrected three-dimensional model with the coordinates of the primary three-dimensional model, wherein the comparison process comprises the following steps: and solving the mean value of the coordinate data, and then endowing polarity according to the original coordinates to regenerate the three-dimensional model.
Step 6: and performing function and effect decomposition on the regenerated three-dimensional model to obtain a plurality of decomposition modules. And searching the corresponding component module for the regenerated three-dimensional model by taking the decomposed function effect parameters as a unit and the functions and effects, and then decomposing the corresponding component module to obtain the decomposed module of the regenerated three-dimensional model.
And 7: and collecting the functional effects of all the decomposition modules to obtain a decomposition module functional effect set. The function and effect collection process comprises the steps of taking the decomposition module as a reference to decompose the functions and effects which can be realized, taking the functions and effects which can be realized as a secondary reference to retrieve the same or similar function and effect parameters in the network, and then summarizing all the parameters to obtain the function and effect set of the decomposition module.
And 8: and decomposing the functional effect set to obtain independent functional effect elements. Decomposing each decomposed functional effect parameter in the functional effect set into functional effect elements with minimum granularity, describing the decomposed functional effect parameters based on the use case diagram of the UML, decomposing each decomposed functional effect parameter into the functional effect elements with minimum granularity until the functional effects of all the decomposed functional effect parameters are not subdivided, obtaining the functional effect elements which are independent from each other, and obtaining the functional effect elements which cannot have the same effect information and semantic overlapping effect,
the following relations are satisfied between the functional effect elements:
wherein R represents an upper level functional effect to be divided, R1，r2，r3，···，ri，···，rnRepresenting n functional effect elements obtained after decomposition, and obtaining an initial personalized initial functional effect model according to the n functional effect elements.
And step 9: and carrying out semantic retrieval on each independent function effect element to summarize all the semantic identical function effect elements, and establishing an independent function effect element model. Using a word segmentation tool to segment words of the independent function effect elements, and obtaining binary linguistic training data by using a window with the size of 3 and the step length of 1; carrying out Word2Vec model training on binary linguistic training data to obtain Word vector representation; calculating the residual value of an included angle between every two word vectors vi and vj to serve as the similarity of two words, and obtaining a similarity measurement matrix; and obtaining 3 words which are most adjacent to the word vi, namely 3 synonyms of the word vi, through measurement to obtain a synonym table of the independent functional effect element, and then searching the synonyms through the network.
Step 10: the independent function effect meta-model interprets the model component elements that can be realized by each independent function effect element and establishes a model component meta-model. According to each independent function effect element, mechanical components realizing the independent function effect are searched, and then all the mechanical components are combined together to obtain the model component meta-model.
Step 11: and the model component meta-model generates a functional effect model decomposition module. And combining each component element, and combining the combined decomposition module with the effect element corresponding to the combined component element to form the combined model decomposition module.
Step 12: and judging the feasibility of each decomposition module by using big data comparison, and comparing the feasibility with the function effect parameters after initial input transformation to select the decomposition module of the optimal model. And inputting the combined decomposition module and the corresponding functional effect parameter into the existing mechanical module database of the Internet to verify the feasibility, and summarizing the feasible decomposition modules.
Step 13: and recombining the decomposition modules of the optimal model into a final three-dimensional model, and outputting a material list of the decomposition modules of the optimal model.
A system of an intelligent design method of a three-dimensional industrial product comprises a parameter input summarizing module, a parameter transformation module, a coordinate establishment model generation module, a plan view acquisition-function comparison module, a correction module, a first model component decomposition module, a component function effect collection module, a function effect decomposition module, an independent function effect element model establishment module, a model component element model establishment module, a second model component decomposition module, a model component feasibility judgment module and a model generation-material sheet output module;
the parameter input summarizing module is connected with the parameter transformation module and is used for inputting specification parameters and functional effect parameters of a three-dimensional product to be designed;
the parameter transformation module is connected with the coordinate establishment model generation module and used for positioning and transforming the specification parameters to obtain standard coordinate data and decomposing and transforming the functional effect parameters to obtain decomposed functional effect parameters;
the coordinate establishing model generating module is connected with the plan view acquiring-function comparing module and used for establishing three-dimensional coordinates, mapping the transformed specification parameters into the three-dimensional coordinates, and then connecting lines among every three or more coordinates and rendering to generate a preliminary three-dimensional model;
the plan obtaining-function comparing module is connected with the correcting module and is used for obtaining a primary three-dimensional model six-face image, comparing the six-face image with the decomposed function effect, reversely translating the plan image according to the decomposed function effect when there is a difference, and comparing and correcting the reversely translated plan image and the six-face image one by one to obtain a corrected six-face image;
the correction module is connected with the first model component decomposition module and used for recombining the corrected hexahedron to generate a corrected three-dimensional model and comparing the coordinates of the corrected three-dimensional model with the coordinates of the primary three-dimensional model, and the comparison process is as follows: calculating a coordinate data mean value, endowing polarity according to the original coordinate, and regenerating a three-dimensional model;
the first model component decomposition module is connected with the component function and effect collection module and is used for decomposing functions and effects of the regenerated three-dimensional model to obtain a plurality of decomposition modules;
the component function effect collection module is connected with the function effect decomposition module and is used for collecting the function effects of all the decomposition modules to obtain a decomposition module function effect set;
the function effect decomposition module is connected with the independent function effect element model building module and is used for decomposing the function effect set to obtain independent function effect elements;
the model building module for building the independent function effect elements is connected with the model building component element model module and is used for performing semantic retrieval on each independent function effect element, summarizing all function effect elements with the same semantic meaning and building an independent function effect element model;
the model component meta-model building module is connected with the second model component decomposition module and is used for the independent function effect meta-model to decipher the model component elements which can be realized by each independent function effect element and build a model component meta-model;
the second model component decomposition module is connected with the model component feasibility judgment module and is used for generating a functional effect model decomposition module by the model component meta-model;
the model component feasibility judgment module is connected with the model generation-material bill output module and used for judging the feasibility of each decomposition module by using big data comparison and selecting the decomposition module of the optimal model by comparing with the function effect parameters after initial input transformation;
and the model generation-material bill output module is used for recombining the decomposition modules of the optimal model into a final three-dimensional model and outputting the material bill of the decomposition module of the optimal model.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.
Claims (7)
1. An intelligent design method for three-dimensional industrial products is characterized by comprising the following steps:
step 1: inputting specification parameters and functional effect parameters of a three-dimensional product to be designed;
step 2: positioning and transforming the specification parameters to obtain standard coordinate data, and decomposing and transforming the functional effect parameters to obtain decomposed functional effect parameters;
and step 3: establishing a three-dimensional coordinate, mapping the transformed specification parameters into the three-dimensional coordinate, and then connecting every three or more coordinates with each other and rendering to generate a preliminary three-dimensional model;
and 4, step 4: acquiring a primary three-dimensional model hexahedron, comparing the hexahedron with the decomposed functional effect, reversely translating the plane graph according to the decomposed functional effect when a difference exists between the functional effect to be realized by each surface and the decomposed functional effect, and comparing and correcting the reversely translated plane graph and the hexahedron one by one to obtain a corrected hexahedron;
and 5: recombining the corrected hexahedron to generate a corrected three-dimensional model, and comparing the coordinates of the corrected three-dimensional model with the coordinates of the primary three-dimensional model, wherein the comparison process comprises the following steps: calculating a coordinate data mean value, endowing polarity according to the original coordinate, and regenerating a three-dimensional model;
step 6: decomposing the regenerated three-dimensional model into a plurality of decomposition modules by function and effect;
and 7: collecting the functional effects of all the decomposition modules to obtain a decomposition module functional effect set;
and 8: decomposing the functional effect set to obtain independent functional effect elements;
and step 9: semantic retrieval is carried out on each independent function effect element, all the semantic same function effect elements are collected, and an independent function effect element model is established, wherein the specific process is as follows:
using a word segmentation tool to segment words of the independent function effect elements, and obtaining binary linguistic training data by using a window with the size of 3 and the step length of 1; carrying out Word2Vec model training on binary linguistic training data to obtain Word vector representation; calculating the residual value of an included angle between every two word vectors vi and vj to serve as the similarity of two words, and obtaining a similarity measurement matrix; obtaining 3 words nearest to the word vi through measurement, namely obtaining a synonym table of independent functional effect elements by the 3 synonyms of the vi, and then searching the synonyms through a network;
step 10: the independent function effect meta-model inversely translates the model component elements which can be realized by each independent function effect element and establishes a model component meta-model, wherein the inversely translating process comprises the steps of searching the mechanical components for realizing the independent function effect elements according to each independent function effect element and combining all the mechanical components together to obtain the model component meta-model;
step 11: the method comprises the steps that a model component meta-model generates a functional effect model decomposition module, each component element is combined with each other, the combination of the decomposition module obtained after combination, the combined component elements and corresponding effect elements becomes a combined model decomposition module, the combined model decomposition module and corresponding functional effect parameters are input into an internet existing mechanical module database for feasibility verification, and feasible decomposition modules are collected;
step 12: judging the feasibility of each decomposition module by using big data comparison, and comparing the feasibility with the function effect parameters after initial input transformation to select the decomposition module of the optimal model;
step 13: and recombining the decomposition modules of the optimal model into a final three-dimensional model, and outputting a material list of the decomposition modules of the optimal model.
2. The intelligent design method of three-dimensional industrial products according to claim 1, characterized in that: the specific process of the step 2 is as follows:
when the specification parameters are converted, the length, width and height values are subjected to same-unit data conversion, one point is selected as an original point, three-dimensional coordinate data of each point is determined according to the distance relation between the length, width and height values and the coordinate points, then the number set of each coordinate point is summarized, and the functional effect parameter decomposition and conversion process is that functional effect semantics are searched in an existing Chinese dictionary to break words, and a plurality of decomposition functional effect parameters are obtained.
3. The intelligent design method of three-dimensional industrial products according to claim 1, characterized in that: in the step 3, every three or more coordinates are connected with each other, the connection line is a straight line, and the straight lines are connected in parallel through transverse lines during rendering and rendered into a three-dimensional body.
4. The intelligent design method of three-dimensional industrial products according to claim 1, characterized in that: the decomposition process of the step 6 comprises the following steps: and searching a corresponding component module for the regenerated three-dimensional model by taking the decomposed functional effect parameters as a unit and the functions and effects, and then decomposing the corresponding component module to obtain a decomposed module of the regenerated three-dimensional model.
5. The intelligent design method of three-dimensional industrial products according to claim 1, characterized in that: in the step 7, the function and effect collection process includes decomposing the achievable functions and effects based on the decomposition module, searching the same or similar function and effect parameters in the network based on the achievable functions and effects as a secondary reference, and summarizing all the parameters to obtain the function and effect set of the decomposition module.
6. The intelligent design method of three-dimensional industrial products according to claim 1, characterized in that: the specific process of the step 8 is as follows: decomposing each decomposed functional effect parameter in the functional effect set into functional effect elements with minimum granularity, describing the decomposed functional effect parameters based on the use case diagram of the UML, decomposing each decomposed functional effect parameter into the functional effect elements with minimum granularity until the functional effects of all the decomposed functional effect parameters are not subdivided, obtaining the functional effect elements which are independent from each other, and obtaining the functional effect elements which cannot have the same effect information and semantic overlapping effect,
the following relations are satisfied between the functional effect elements:
wherein R represents an upper level functional effect to be divided, R1，r2，r3，···，ri，···，rnRepresenting n functional effect elements obtained after decomposition, and obtaining an initial personalized initial functional effect model according to the n functional effect elements.
7. The system of intelligent design method of three-dimensional industrial products according to any one of claims 1-6, characterized in that: the system comprises a parameter input summarizing module, a parameter transformation module, a coordinate establishing model generating module, a plan view obtaining-function comparison module, a correction module, a first model component decomposition module, a component function effect collecting module, a function effect decomposition module, an independent function effect element model establishing module, a model component element model establishing module, a second model component decomposition module, a model component feasibility judgment module and a model generating-material list output module;
the parameter input summarizing module is connected with the parameter transformation module and is used for inputting specification parameters and functional effect parameters of a three-dimensional product to be designed;
the parameter transformation module is connected with the coordinate establishment model generation module and used for positioning and transforming the specification parameters to obtain standard coordinate data and decomposing and transforming the functional effect parameters to obtain decomposed functional effect parameters;
the coordinate establishing model generating module is connected with the plan view acquiring-function comparing module and used for establishing three-dimensional coordinates, mapping the transformed specification parameters into the three-dimensional coordinates, and then connecting lines among every three or more coordinates and rendering to generate a preliminary three-dimensional model;
the plan obtaining-function comparing module is connected with the correcting module and is used for obtaining a primary three-dimensional model six-face image, comparing the six-face image with the decomposed function effect, reversely translating the plan image according to the decomposed function effect when there is a difference, and comparing and correcting the reversely translated plan image and the six-face image one by one to obtain a corrected six-face image;
the correction module is connected with the first model component decomposition module and used for recombining the corrected hexahedron to generate a corrected three-dimensional model and comparing the coordinates of the corrected three-dimensional model with the coordinates of the primary three-dimensional model, and the comparison process is as follows: calculating a coordinate data mean value, endowing polarity according to the original coordinate, and regenerating a three-dimensional model;
the first model component decomposition module is connected with the component function and effect collection module and is used for decomposing functions and effects of the regenerated three-dimensional model to obtain a plurality of decomposition modules;
the component function effect collection module is connected with the function effect decomposition module and is used for collecting the function effects of all the decomposition modules to obtain a decomposition module function effect set;
the function effect decomposition module is connected with the independent function effect element model building module and is used for decomposing the function effect set to obtain independent function effect elements;
the model building module for building the independent function effect elements is connected with the model building component element model module and is used for performing semantic retrieval on each independent function effect element, summarizing all function effect elements with the same semantic meaning and building an independent function effect element model;
the model component meta-model building module is connected with the second model component decomposition module and is used for the independent function effect meta-model to decipher the model component elements which can be realized by each independent function effect element and build a model component meta-model;
the second model component decomposition module is connected with the model component feasibility judgment module and is used for generating a functional effect model decomposition module by the model component meta-model;
the model component feasibility judgment module is connected with the model generation-material bill output module and used for judging the feasibility of each decomposition module by using big data comparison and selecting the decomposition module of the optimal model by comparing with the function effect parameters after initial input transformation;
and the model generation-material bill output module is used for recombining the decomposition modules of the optimal model into a final three-dimensional model and outputting the material bill of the decomposition module of the optimal model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910582878.3A CN110288704B (en) | 2019-07-01 | 2019-07-01 | Intelligent design method and system for three-dimensional industrial product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910582878.3A CN110288704B (en) | 2019-07-01 | 2019-07-01 | Intelligent design method and system for three-dimensional industrial product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288704A CN110288704A (en) | 2019-09-27 |
| CN110288704B true CN110288704B (en) | 2021-03-12 |
Family
ID=68021441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910582878.3A Expired - Fee Related CN110288704B (en) | 2019-07-01 | 2019-07-01 | Intelligent design method and system for three-dimensional industrial product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288704B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491610A (en) * | 2017-08-22 | 2017-12-19 | 重庆创速工业有限公司 | Car panel die intelligent design system and design method |
| CN109344495A (en) * | 2018-09-05 | 2019-02-15 | 重庆创速工业有限公司 | A kind of Intelligentized design method and its system of 3 D stereo industrial products |
| CN109376399A (en) * | 2018-09-05 | 2019-02-22 | 重庆创速工业有限公司 | A kind of Intelligentized design method and its system of three-dimensional building |
| CN109376397A (en) * | 2018-09-05 | 2019-02-22 | 重庆创速工业有限公司 | A kind of Intelligentized design method and its system of three-dimensional mould |
| CN109858185A (en) * | 2019-03-08 | 2019-06-07 | 广东岭南职业技术学院 | A kind of interior decoration design method based on AR virtual reality technology |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150363513A1 (en) * | 2014-06-13 | 2015-12-17 | Wolfram Alpha Llc | Method and system for designing products |
-
2019
- 2019-07-01 CN CN201910582878.3A patent/CN110288704B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491610A (en) * | 2017-08-22 | 2017-12-19 | 重庆创速工业有限公司 | Car panel die intelligent design system and design method |
| CN109344495A (en) * | 2018-09-05 | 2019-02-15 | 重庆创速工业有限公司 | A kind of Intelligentized design method and its system of 3 D stereo industrial products |
| CN109376399A (en) * | 2018-09-05 | 2019-02-22 | 重庆创速工业有限公司 | A kind of Intelligentized design method and its system of three-dimensional building |
| CN109376397A (en) * | 2018-09-05 | 2019-02-22 | 重庆创速工业有限公司 | A kind of Intelligentized design method and its system of three-dimensional mould |
| CN109858185A (en) * | 2019-03-08 | 2019-06-07 | 广东岭南职业技术学院 | A kind of interior decoration design method based on AR virtual reality technology |
Non-Patent Citations (1)
| Title |
|---|
| 基于FCA和Word2vec的异构资源本体构建研究;李端明等;《情报科学》;20170305;第35卷(第3期);参见第2.2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288704A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583474A (en) | A kind of training sample generation method for the processing of industrial big data | |
| Wagner et al. | Representing construction-related geometry in a semantic web context: A review of approaches | |
| CN108021547A (en) | A kind of generation method of natural language, spatial term device and electronic equipment | |
| CN110827398A (en) | Indoor three-dimensional point cloud automatic semantic segmentation algorithm based on deep neural network | |
| Brenner | Convergence of the multigrid 𝑉-cycle algorithm for second-order boundary value problems without full elliptic regularity | |
| CN114419642A (en) | Method, device and system for extracting key value pair information in document image | |
| CN115344905A (en) | Method and system for automatically generating two-dimensional engineering drawing based on three-dimensional model | |
| CN110288704B (en) | Intelligent design method and system for three-dimensional industrial product | |
| CN114048282A (en) | Text tree local matching-based image-text cross-modal retrieval method and system | |
| Donagi et al. | Global aspects of (0, 2) moduli space: toric varieties and tangent bundles | |
| CN117290478A (en) | Knowledge graph question-answering method, device, equipment and storage medium | |
| US10521955B2 (en) | Posture-guided method and device for combination modeling of cross-category three-dimensional models | |
| Orbay et al. | Shape design from exemplar sketches using graph-based sketch analysis | |
| CN115169448A (en) | Three-dimensional description generation and visual positioning unified method based on deep learning | |
| CN114692495A (en) | Efficient complex system reliability evaluation method based on reliability block diagram | |
| CN113722514A (en) | Internet education video image screening and extracting method based on deep learning | |
| CN111539485A (en) | Assembly model similarity retrieval method based on space point set matching | |
| Falkowski et al. | Semiautomatic generation of full CityGML models from images | |
| CN110675488A (en) | Construction method of creative three-dimensional voxel model modeling system based on deep learning | |
| CN118132686B (en) | Service robot problem matching method and system for multi-service scene | |
| CN109800394A (en) | Method and tool for converting IETM data packet into SCORM standard packet | |
| CN114494813B (en) | Dense cross attention-based index expression generation method | |
| CN117764563B (en) | Equipment maintenance time prediction method, system, electronic equipment and medium | |
| Chen et al. | Quality inspection and quality improvement of large spatial datasets | |
| Liu et al. | An enhanced grammatical approach for graph drawing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210312 Termination date: 20210701 |