[go: up one dir, main page]

CN111815409A - Pattern matching method for personalized design of mechanical products for "Internet +" environment - Google Patents

Pattern matching method for personalized design of mechanical products for "Internet +" environment Download PDF

Info

Publication number
CN111815409A
CN111815409A CN202010640643.8A CN202010640643A CN111815409A CN 111815409 A CN111815409 A CN 111815409A CN 202010640643 A CN202010640643 A CN 202010640643A CN 111815409 A CN111815409 A CN 111815409A
Authority
CN
China
Prior art keywords
design
order
module
personalized
design pattern
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.)
Granted
Application number
CN202010640643.8A
Other languages
Chinese (zh)
Other versions
CN111815409B (en
Inventor
张树有
顾叶
裘乐淼
王阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202010640643.8A priority Critical patent/CN111815409B/en
Publication of CN111815409A publication Critical patent/CN111815409A/en
Priority to JP2021544343A priority patent/JP7171094B2/en
Priority to PCT/CN2021/070982 priority patent/WO2022007380A1/en
Application granted granted Critical
Publication of CN111815409B publication Critical patent/CN111815409B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0621Electronic shopping [e-shopping] by configuring or customising goods or services
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开一种面向“互联网+”环境机械产品个性化设计模式匹配方法,该方法将用户订单量化为特征向量,将机械产品分解成模块,并构建历史案例库,根据机械产品各模块采用不同设计模式时用户满意的概率得到根据用户订单匹配的设计模式方案。本发明从概率学角度出发,依据贝叶斯定理研究产品定制设计中各个设计模块的个性化设计模式匹配方法;通过计算不同设计模块采用不同设计模式的用户满意概率值,匹配出各个设计模块对应的设计模式,减少设计人员靠设计经验选择设计模式时的试错情况,提高设计效率;提高了个性化设计模式匹配过程中的智能性与操作性。

Figure 202010640643

The invention discloses a pattern matching method for the personalized design of mechanical products facing the "Internet +" environment. The method quantifies user orders into feature vectors, decomposes mechanical products into modules, and builds a historical case database. The probability of user satisfaction when designing a pattern is obtained by matching the design pattern scheme according to the user's order. From the perspective of probability, the present invention studies the individualized design pattern matching method of each design module in the product customization design according to Bayes'theorem; by calculating the user satisfaction probability values of different design modules adopting different design patterns, the corresponding design modules are matched. It reduces the trial-and-error situation when designers rely on design experience to select design patterns, improves design efficiency, and improves the intelligence and operability in the matching process of personalized design patterns.

Figure 202010640643

Description

Internet plus environment-oriented personalized design mode matching method for mechanical product
Technical Field
The invention belongs to the field of customized design of mechanical products, and particularly relates to a matching method for an 'internet +' environment-oriented personalized design mode of a mechanical product.
Background
Experts predict that more than half of the future will be custom personalized products. With the continuous improvement of industrial technology and people living standard, the material needs are more and more extensive, and the traditional single product does not meet the individual requirements of people any more. The traditional product customization design mode and the batch production line no longer meet the design and production requirements of the customized product. The large-scale customized design mode is used for configuring product modules according to user requirements by presetting product modules and module families, and combining products meeting the user requirements. However, as the demand is more personalized, the source of the product order is gradually changed from the group to the single user, and the large-scale customized design mode can hardly meet the demand of the user. Existing product modules and module families cannot completely cover personalized requirements of users, and the module library cannot be updated in advance due to the fact that the future requirement trend cannot be accurately predicted. Meanwhile, for complex customized mechanical products or equipment, the design mode of large-scale customization cannot be adapted.
Disclosure of Invention
The invention aims to provide an 'internet +' environment-oriented personalized design mode matching method for mechanical products, aiming at the defects of the prior art.
The purpose of the invention is realized by the following technical scheme: an 'internet +' environment-oriented mechanical product personalized design pattern matching method comprises the following steps:
(1) constructing an order characteristic vector order of the user personalized demand:
order={(req1,r1),(req2,r2),...,(reqi,ri),...,(reqn,rn)}
wherein reqiDenotes the ith requirement characteristic, riExpressing the normalized demand value of the ith demand characteristic, wherein n is the number of the demand characteristics;
(2) decomposing a mechanical product into m modules d1~dmBuilding a product decomposition module set D ═ D1,d2,...,dm};
(3) According to the historical order records of the design pattern scheme meeting the user requirements, constructing a design pattern matching case library X:
Figure BDA0002570952170000011
patternj={p1j,p2j,...,pkj,...,pmj}
wherein M represents the number of historical orders in the design pattern matching case base, orderjAn order feature vector representing a jth order; p is a radical ofkjRepresents the design pattern, adopted by the kth module in the jth orderjRepresenting the matching result of each module design pattern in the jth order, wherein k is more than or equal to 1 and less than or equal to m;
(4) aiming at new order feature vector order*The user satisfaction probability P (when the kth module of the mechanical product adopts different design modes)k|order*)(k1,2,3) is:
Figure BDA0002570952170000021
wherein,k1 means that the kth module adopts the design mode of configuration according to orders,k2 means that the kth module adopts the design mode of deformation according to orders,k3 represents that the kth module adopts a design mode generated according to an order; 0<P(order*) A constant is not more than 1; p: (k) Representing the adoption of the kth module in the design pattern matching case library XkProbability of design pattern:
Figure BDA0002570952170000022
wherein X: (k) Indicating the k-th module adoption in XkOrder set of design patterns, | X: (k) I is X: (k) The number of elements in (1); p (order)*|k) According to the new order feature vector order for the kth module*Conditional probabilities of selecting different design modes:
Figure BDA0002570952170000023
wherein r isi *Express order*The normalized demand value of the ith demand characteristic is that i is more than or equal to 1 and less than or equal to n; x (k)iIs adopted by the kth module in XkNormalized demand value r for ith demand feature in order for design patterniThe set of (a) and (b),
Figure BDA0002570952170000024
respectively, the set X: (k)iThe mean and variance of;
(5) a reaction of P: (k|order*) The design mode corresponding to the maximum probability value is used as the design mode matching result p of the kth modulek *(ii) a Due to P (order)*) Is a constant, compare { P: (k|order*)|kComparison of the sizes of 1,2,3 { P (P) ((P))k)P(order*|k)|k1,2,3 };
(6) obtaining the design pattern matching results of all modules of the mechanical product to form the final design pattern matching result
Figure BDA0002570952170000025
Further, the design mode k1,2, 3; wherein,k1 means that the kth module adopts the design mode of configuration according to orders,k2 means that the kth module adopts the design mode of deformation according to orders,kthe kth module is designed in the order generation mode indicated by 3.
The invention has the beneficial effects that:
1. the method is based on the Bayesian theorem to research the personalized design pattern matching method of each design module in the product custom design from the aspect of the probability. By calculating the user satisfaction probability values of different design modules in different design modes, the design modes corresponding to the design modules are matched, the trial and error condition when the designer selects the design modes by design experience is reduced, and the design efficiency is improved.
2. The invention improves the intelligence and operability in the process of matching the personalized design mode.
Drawings
FIG. 1 is a flow chart of the personalized design of an Internet + "environment mechanical product;
FIG. 2 is a flow chart of Internet + "environment machine product personalized design pattern matching;
fig. 3 is a personalized design implementation process diagram of an elevator car system in an "internet +" environment.
Detailed Description
The invention is described in further detail below with reference to the figures and examples.
As shown in fig. 1, it is a flow chart of personalized design of mechanical products in "internet +" environment according to the present invention, and the steps are as follows:
(1.1) the user puts forward the personalized requirements of the user on mechanical products through an 'internet +' environment constructed by the multi-source terminal. The Internet + design platform converts the user requirements into product orders, and transmits the product orders to designers through the network server.
And (1.2) matching the design mode of each module of the product by the designer according to the user satisfaction probability matching method of the personalized design mode based on the electronic order. The personalized design mode of the Internet +' environment mechanical product comprises the following steps: configuring a design mode according to an order, deforming the design mode according to the order and generating the design mode according to the order, wherein the method comprises the following steps of:
(1) the complex products are decomposed according to design modules and are designed one by one according to the modules. The design mode of each module is obtained by matching the order content with the product module library.
(2) And selecting a design mode configured according to the order, and matching a module meeting the design requirement from the module library according to the product design parameters, the configuration rules and the configuration template.
(3) Selecting a design mode deformed according to an order, positioning a module to be deformed, retrieving a similar configuration module from a module library, selecting an optimal transplantation mother board and a transplantation alternative module, carrying out structural feature segmentation on an available structure meeting design requirements, extracting performance parameter difference of the mother board, transplanting (replacing) the available structure to the mother board, reconstructing constraint, reconstructing a standard interface of an adjacent module under the condition of meeting the performance requirements, and forming a module design scheme deformed according to the order.
(4) Selecting a design mode of generating a formula according to an order, designing the module generating formula which is completely unmatched in a module library, setting constraint conditions, boundary conditions and load conditions, generating a plurality of generating formula design results meeting the conditions, performing performance simulation on the generated module, and selecting the module meeting the requirement of the order as a module design scheme.
(5) And (3) designing each module one by one, designing by adopting the design modes from (2) to (4), fusing the module schemes of the complex products after completing all the designs, and generating a customized design scheme of the mechanical product.
(1.3) after the designer finishes the design scheme, the users feed back each other in real time through an Internet plus platform, and the designer modifies the design scheme until the requirement of the users is met; in addition, the user can directly participate in the whole design process, and change opinions can be proposed in the module successive design process for the modification of designers. The final design scheme should fully meet the personalized requirements of the user.
The Internet + design platform is a design platform provided for the personalized design of Internet +' environment mechanical products, users and designers participate in the product customized design together, generally, the users propose or modify requirements, the designers carry out the customized design according to orders converted by the requirements, the users participate in the whole design process, and the users and the designers feed back each other in real time to complete products meeting the requirements of the users. Specifically, the invention relates to an Internet plus environment-oriented personalized design pattern matching method for mechanical products, which comprises the following steps:
the method includes the steps that 1, a user submits a demand according to own personalized demand in an Internet +' environment and generates an order according to a preset template;
2. the customized design process of the mechanical product is completed on an Internet + design platform, and three design modes are provided, namely a design mode configured according to an order, a design mode deformed according to the order and a design mode generated according to the order. And matching the design mode with the existing product modules according to the order content, and designing the product modules one by a designer according to the matching result.
The steps for configuring the design pattern in order are as follows,
A1. inputting personalized order parameters and converting the personalized order parameters into mechanical product design parameters;
A2. matching a proper module from a configuration module library according to the design parameters, the configuration structure, the configuration rules and the configuration module to form a mechanical product customized design scheme configured according to the order;
A3. and (3) transmitting the design scheme to a user side, evaluating whether the scheme meets the requirements of the user side, outputting the customized design scheme of the mechanical product to finish the design if the scheme meets the requirements, and returning to the step 2 for reconfiguration or replacing another two design modes if the scheme does not meet the requirements.
The steps of the design mode according to the order deformation are as follows,
B1. inputting personalized order parameters and converting the personalized order parameters into mechanical product design parameters;
B2. under the conditions that the configuration design according to the order can not meet the order requirement, a user feeds back and evaluates a design scheme needing to be modified in real time, and only product modules partially meeting the design requirement exist in a module library, a design mode of deforming according to the order can be adopted;
B3. positioning a product module to be deformed, and searching similar modules in a module library;
B4. similar module evaluation, selecting an optimal transplantation module mother board and a transplantation alternative module;
B5. analyzing the performance difference between the master plate of the optimal transplantation module and the design parameters, extracting and segmenting the available structure in the alternative transplantation module;
B6. transplanting or replacing the available structure segmented in the transplanting alternative module into the optimal transplanting module mother board, and reconstructing the structural constraint;
B7. and (4) firstly, judging whether the new module meets the performance, if not, structural optimization is required or the step 5-6 is carried out, if so, feeding back with the user, and repeating the step 4-6 so as to completely meet the user requirement.
B8. Standardizing an interface between a new module and an adjacent module which are designed according to order deformation;
B9. and repeating the steps 3-8, completing the deformation design of other modules, and outputting a mechanical product customized design scheme deformed according to the order.
The steps of the design by order form mode are as follows,
C1. inputting personalized order parameters and converting the personalized order parameters into mechanical product design parameters;
C2. under the conditions that the configuration design according to the order and the deformation design according to the order cannot meet the order requirement, a user feeds back and evaluates the requirement of modifying a design scheme in real time, a product module meeting the design requirement does not exist in a module library, and the like, the module can be designed by adopting a design mode according to an order generation mode;
C3. positioning the module or part to be changed, updating the product order library according to the order requirement, and facilitating the storage of the subsequent generation type module;
C4. utilizing a product design resource library to assist in generating a design mode according to an order, setting constraint requirements, boundary conditions, load conditions and the like, and generating a massive module generating design result;
C5. a designer selects a module meeting the product performance from the mass generation type design modules, transmits the module to a user for evaluation, and cooperatively selects a module completely meeting the user requirement; if the user changes the demand in the process, turning to the step 4;
C6. repeating the steps 3-5, completing the generation type design of other modules, and forming a mechanical product customized design scheme according to the generation type of the order;
C7. the generating module carries out model, document, structure and rule modeling and is integrated into a product design resource library.
Fig. 2 is a flow chart of a user satisfaction probability matching method in the personalized design mode of the invention. The user satisfaction probability matching method adopting the personalized design mode according to the matching design mode of the order content and the existing product module comprises the following steps:
2.1. constructing order characteristic vector order { (req) of user personalized demand1,r1),(req2,r2),...,(reqi,ri),...,(reqn,rn) }; wherein reqiIndicating order featuresThe ith demand feature, r, in the eigenvectoriRepresentation reqiAnd (4) corresponding normalized user personalized demand values, wherein n is a demand characteristic number. For the same type of mechanical products, the requirement characteristics in different order characteristic vectors are the same, but the normalized requirement values r under the same requirement characteristics of different orders are different due to the personalized requirement.
2.2. A product decomposition module set D is constructed, each mechanical product needs to be decomposed before customized design, the product modules are designed one by one according to the module design idea, and the module division results of the same mechanical products are also the same as D (D)1,d2,...,dm}; wherein d iskThe kth module representing the product division is divided into m modules, and k is more than or equal to 1 and less than or equal to m.
2.3. According to a design case library formed by order records meeting the requirements of users, a design pattern matching case library is constructed
Figure BDA0002570952170000051
patternj={p1j,p2j,...,pkj,...,pmj}; wherein M represents the order number recorded in the design pattern matching case library; p is a radical ofkjIndicates the kth module d in the jth order recordkThe design pattern adopted, patternjShowing the design pattern matching result p of each module in the jth order recordkjA collection of (a).
2.4. Inputting new order characteristic vector order*Comparing the user satisfaction probabilities P corresponding to the three design modes of the kth module in D (a)k|order*)(k1,2,3), selecting the design mode with the highest user satisfaction probability, and comprising the following sub-steps:
2.4.1 find the set of design pattern matching results { p ] for the kth Module in Xkj1-M, and dividing X into X (M) according to different design modes in the setk),k1,2, 3; wherein,kindicating the design mode selected by the kth module,k1 means that the kth module adopts the design mode of configuration according to orders,k2 denotes the k-th module using order-based morphingThe design of the mode is as follows,k3 represents that the kth module adopts a design mode generated according to an order; x (k) Indicating the k-th module adoptionkA set of cases of design patterns.
2.4.2 finding a set of normalized user personalized demand values for the ith demand feature in X { rijX (1-M) | j ═ 1 to M }, obtained according to step 2.4.1k) Dividing the set into X: (k)iThen X: (k)iIndicating the k-th module adoptionkAnd when the mode is designed, the set of normalized user personalized demand values of the ith demand characteristic in the corresponding order record.
2.4.3 calculation of the k-th Module in X selects a different design modekProbability P: (1, 2,3)k):
Figure BDA0002570952170000061
Wherein, | X: (k) L represents X: (k) The number of the elements in (B).
2.4.4 computing the set X (k)iMean value of
Figure BDA0002570952170000062
And variance
Figure BDA0002570952170000063
2.4.5 calculating New order feature vector order*Medium demand feature reqi *Corresponding ri *Conditional probability P (r) of selecting different design modes by kth module with different valuesi *|k) Comprises the following steps:
Figure BDA0002570952170000064
in the formula, ri *Express order*The ith requirement characteristic reqi *Normalized user personalized demand value of (2) due to ri *Satisfies the distribution of probability density functionAccording to the rule of the method,
Figure BDA0002570952170000065
2.4.3 the kth Module orders the order according to the new order feature vector*Conditional probability P (order) of selecting different design modes*|k) Comprises the following steps:
Figure BDA0002570952170000066
in the formula, P (order)*|k) By order*N of riThe value union decision is based on the attribute conditional independence assumption.
2.4.4 obtaining the user satisfaction probability P (based on Bayesian theorem) when the kth module adopts different design modesk|order*) Comprises the following steps:
Figure BDA0002570952170000067
in the formula, 0<P(order*) 1 or less represents an evidence factor which is a constant; thus, compare P: (k|order*) The magnitude of (c) is the comparison { P: (k)·P(order*|k) Size of { P: (A) }, selecting { P: (B) }k)·P(order*|k)|k1,2, 3} as a matching result
Figure BDA0002570952170000071
2.5 calculating and matching each order feature vector in turn to form the final design pattern matching result
Figure BDA0002570952170000072
And guiding a designer to design.
3. Designers complete the customized design scheme of mechanical products, and directly feed back to users on the Internet plus a design platform, so that the users can experience the performance of the products and determine whether the requirements are met. If the part does not meet the requirement, the part which does not meet the requirement is fed back to the designer in real time to redesign; if so, determining that the product design scheme shifts to the manufacturing stage.
The invention carries out the customized design of mechanical products based on user orders, drives the design by the requirements of a single user, and the user participates in the whole design process through the Internet and a design platform and feeds back with designers in real time, so that the final design scheme meets the individual requirements of the user. The invention provides three personalized design modes of mechanical products: the design mode is configured according to the order, deformed according to the order and generated according to the order, thereby meeting the customized design requirements of almost all mechanical products. The three design modes effectively relieve the contradiction between demand individuation and production scale. And in the design mode matching stage, a module design mode which meets the order requirement and is judged by a designer according to experience is omitted, and the design efficiency and the user satisfaction of the design result are improved.
As a highly personalized customized mechanical product, an elevator is widely used in life, and elevator systems of different buildings have great difference, so that the demand of a user on the elevator is personalized. The elevator is divided into a plurality of systems such as a driving system, a suspension system, a landing door system, a car system and the like, each system can be independently designed and assembled, and the car system with the highest degree of individuation is selected as a specific embodiment for description.
The implementation of the method is described with reference to a simplified example. Table 1 shows a simplified case base matched with local elevator design patterns and a new personalized order feature vector order*For example, the design pattern matching of the number 24 module is compared with P (0.54), (scene, 0.25), (speed, 0.61), (floor, 0.45), (decoration, 0.14) }24|order*)(241,2,3) the size of the three values, which determines which design mode is selected. The specific calculation steps are as follows:
table 1: elevator design pattern matching case library (simplified local)
Figure BDA0002570952170000073
P(24=1)=0.6,P(24=2)=0.4,P(24=3)=0
Figure BDA0002570952170000081
Figure BDA0002570952170000082
Figure BDA0002570952170000083
Figure BDA0002570952170000084
Figure BDA0002570952170000085
Figure BDA0002570952170000086
Figure BDA0002570952170000087
Figure BDA0002570952170000088
Figure BDA0002570952170000089
Figure BDA00025709521700000810
Let P (order)*) 1, then P: (24=1|order*)=0.574,P(24=2|order*)=3.06×10-84,P(24=3|order*) 0, so the number 24 module should use order matchingAnd (4) setting a design mode. The remaining module design pattern matches are calculated in a similar manner.
Fig. 3 shows a personalized design implementation process diagram of the elevator car system in the "internet +" environment according to the invention.
(1) According to the personalized design mode matching method provided by the invention, the user satisfaction probability of three design modes is calculated one by one according to the divided design modules, the design mode matching is carried out, the result shows that 91% of the modules configure the design mode according to the order, 7% of the modules deform the design mode according to the order, and 2% of the modules generate the design mode according to the order, and the design mode is shown in figure 3 (a).
(2) Design modules such as car frames, cars, protective covers and car walls in the matching result can adopt design modes configured according to orders. The configuration rule base, the configuration module base and the configuration structure of the elevator car system are configured, parts meeting the order requirement are matched from top to bottom in the module base, and a specific design scheme of each module configured according to the order is formed, as shown in fig. 3 (b).
(3) And (4) explaining a design flow by taking a rope pulley as an example according to an order deformation design mode. Firstly, similar configuration modules are retrieved from a module library, after similar configuration scheme evaluation, an optimal transplantation mother set and a transplantation alternative module are selected, an available structure is extracted from the transplantation alternative module, performance parameter difference is extracted from the most transplanted mother set, the available structure is transplanted to the mother set after being divided through structural features, constraint is reestablished, structure optimization is carried out to meet order requirements, interfaces between a new deformation module and an adjacent module are standardized, and a rope wheel specific design scheme designed according to order deformation is formed, wherein the rope wheel specific design scheme is shown in fig. 3 (c).
(4) The design process is described by taking a dial frame as an example according to an order generation type design mode. After constraint conditions, boundary conditions and load conditions are set according to order information about the dial body, multiple generating formula design results meeting the conditions can be obtained according to an order generating formula design mode, performance simulation is carried out on the generating formula design results, and a dial body design scheme meeting order requirements is selected, as shown in fig. 3 (d).
(5) Fig. 3(b) - (d) all take a certain component as an example, the other components are designed one by one according to the matching result of the design pattern, finally, designers integrate the modules, users and designers perform real-time mutual feedback on the internet + design platform, and the designers modify or redesign the design result until the requirements of the users are completely met.

Claims (2)

1. An 'internet +' environment-oriented mechanical product personalized design pattern matching method is characterized by comprising the following steps:
(1) constructing an order characteristic vector order of the user personalized demand:
order={(req1,r1),(req2,r2),...,(reqi,ri),...,(reqn,rn)}
wherein reqiDenotes the ith requirement characteristic, riAnd (3) expressing the normalized demand value of the ith demand characteristic, wherein n is the number of the demand characteristics.
(2) Decomposing a mechanical product into m modules d1~dmAnd constructing a product decomposition module set D ═ D1,d2,...,dm}。
(3) According to the historical order records of the design pattern scheme meeting the user requirements, constructing a design pattern matching case library X:
Figure FDA0002570952160000011
patternj={p1j,p2j,...,pkj,...,pmj}
wherein M represents the number of historical orders in the design pattern matching case base, orderjAn order feature vector representing a jth order; p is a radical ofkjRepresents the design pattern, adopted by the kth module in the jth orderjAnd representing the matching result of each module design mode in the jth order, wherein k is more than or equal to 1 and less than or equal to m.
(4) Aiming at new order feature vector order*The kth module of the mechanical product adopts different design modeskProbability of user satisfaction P, (k|order*) Comprises the following steps:
Figure FDA0002570952160000012
wherein, 0<P(order*) A constant is not more than 1; p: (k) Representing the adoption of the kth module in the design pattern matching case library XkProbability of design pattern:
Figure FDA0002570952160000013
wherein X: (k) Indicating the k-th module adoption in XkOrder set of design patterns, | X: (k) I is X: (k) Number of elements in (1). P (order)*|k) According to the new order feature vector order for the kth module*Conditional probabilities of selecting different design modes:
Figure FDA0002570952160000014
wherein r isi *Express order*The normalized demand value of the ith demand characteristic is that i is more than or equal to 1 and less than or equal to n; x (k)iIs adopted by the kth module in XkNormalized demand value r for ith demand feature in order for design patterniThe set of (a) and (b),
Figure FDA0002570952160000021
respectively, the set X: (k)iThe mean and variance of;
(5) a reaction of P: (k|order*) The design mode corresponding to the maximum probability value is used as the design mode matching result of the kth module
Figure FDA0002570952160000022
Due to P (order)*) Is a constant, compare { P: (k|order*)|kComparison of the sizes of 1,2,3 { P (P) ((P))k)P(order*|k)|k1,2,3 };
(6) obtaining the design pattern matching results of all modules of the mechanical product to form the final design pattern matching result
Figure FDA0002570952160000023
2. The Internet +' environment-oriented mechanical product personalized design pattern matching method according to claim 1, wherein the design pattern isk1,2, 3; wherein,k1 means that the kth module adopts the design mode of configuration according to orders,k2 means that the kth module adopts the design mode of deformation according to orders,kthe kth module is designed in the order generation mode indicated by 3.
CN202010640643.8A 2020-07-06 2020-07-06 Pattern matching method for personalized design of mechanical products facing "Internet +" environment Active CN111815409B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202010640643.8A CN111815409B (en) 2020-07-06 2020-07-06 Pattern matching method for personalized design of mechanical products facing "Internet +" environment
JP2021544343A JP7171094B2 (en) 2020-07-06 2021-01-08 Personalized Design Pattern Matching Method for "Internet +" Environmental Machinery Products
PCT/CN2021/070982 WO2022007380A1 (en) 2020-07-06 2021-01-08 "internet+" environment-oriented mechanical product personalized design pattern matching method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010640643.8A CN111815409B (en) 2020-07-06 2020-07-06 Pattern matching method for personalized design of mechanical products facing "Internet +" environment

Publications (2)

Publication Number Publication Date
CN111815409A true CN111815409A (en) 2020-10-23
CN111815409B CN111815409B (en) 2023-07-21

Family

ID=72841594

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010640643.8A Active CN111815409B (en) 2020-07-06 2020-07-06 Pattern matching method for personalized design of mechanical products facing "Internet +" environment

Country Status (2)

Country Link
CN (1) CN111815409B (en)
WO (1) WO2022007380A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112182406A (en) * 2020-10-27 2021-01-05 上海设序科技有限公司 Recommended method and device for mechanical design scheme
WO2022007380A1 (en) * 2020-07-06 2022-01-13 浙江大学 "internet+" environment-oriented mechanical product personalized design pattern matching method
CN117440553A (en) * 2023-12-20 2024-01-23 上海舒谦智能技术有限公司 A multi-purpose intelligent LED scene light control system and method

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115391745B (en) * 2022-10-27 2023-01-20 国能大渡河大数据服务有限公司 Rainfall forecast correction method and system based on probability matching average method
CN118887199B (en) * 2024-08-15 2025-04-08 桂林澳群彩印有限公司 Demand analysis processing method for customized printed matter

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100145492A1 (en) * 2008-12-09 2010-06-10 The Boeing Company Automated Custom Design Generation
CN109166004A (en) * 2018-08-03 2019-01-08 贵州大学 The product customization method of case-based reasioning
CN109741120A (en) * 2018-08-16 2019-05-10 贵州大学 In-depth product customization method for user needs

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103679334B (en) * 2013-10-14 2016-06-29 浙江工业大学 The method considering life cycle environmental impact factor fixed output quota product platform parameters really
CN110348747B (en) * 2019-07-15 2021-11-26 齐鲁工业大学 Intensive design method and system for product design
CN111815409B (en) * 2020-07-06 2023-07-21 浙江大学 Pattern matching method for personalized design of mechanical products facing "Internet +" environment

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100145492A1 (en) * 2008-12-09 2010-06-10 The Boeing Company Automated Custom Design Generation
CN109166004A (en) * 2018-08-03 2019-01-08 贵州大学 The product customization method of case-based reasioning
CN109741120A (en) * 2018-08-16 2019-05-10 贵州大学 In-depth product customization method for user needs

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
容芷君,等: "基于遗传算法的产品模块化", 机床与液压, no. 7 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022007380A1 (en) * 2020-07-06 2022-01-13 浙江大学 "internet+" environment-oriented mechanical product personalized design pattern matching method
CN112182406A (en) * 2020-10-27 2021-01-05 上海设序科技有限公司 Recommended method and device for mechanical design scheme
CN112182406B (en) * 2020-10-27 2024-09-24 上海设序科技有限公司 Mechanical design scheme recommendation method and device
CN117440553A (en) * 2023-12-20 2024-01-23 上海舒谦智能技术有限公司 A multi-purpose intelligent LED scene light control system and method
CN117440553B (en) * 2023-12-20 2024-03-01 上海舒谦智能技术有限公司 Multipurpose intelligent LED scene lamp control system and method

Also Published As

Publication number Publication date
WO2022007380A1 (en) 2022-01-13
CN111815409B (en) 2023-07-21

Similar Documents

Publication Publication Date Title
CN111815409B (en) Pattern matching method for personalized design of mechanical products facing &#34;Internet +&#34; environment
Marri et al. Computer-aided process planning: a state of art
Yildiz et al. Integrated optimal topology design and shape optimization using neural networks
KR101846793B1 (en) Method of planning a manufacturing process by collecting and analyzing data from machine, and system using the same
CN107491610B (en) Car panel die intelligent design system and design method
CN115688563B (en) A machining parameter optimization method based on multi-agent evolutionary reinforcement learning
CN117150603A (en) Bridge BIM model construction system and method
CN118296165B (en) Method for constructing dynamic process knowledge base of production line and method for generating process scheme
CN112347698A (en) Man-machine hybrid enhanced intelligent design method based on aircraft structural member
CN119068302B (en) Design intent extraction method for large-scale engineering equipment based on multimodal data fusion
CN120162847A (en) A personalized design intelligent interaction method based on topology optimization
CN120406166A (en) Process parameter optimization method, equipment and storage medium
Li et al. Interactive 3D structural design in virtual reality using preference-based topology optimization
CN113190948B (en) Intelligent forming method and system for high-resilience titanium alloy pipe
US20220004677A1 (en) Mechanical product personalized design pattern matching method oriented to internet + environment
JP7807322B2 (en) Design support device and design support method
CN113553667B (en) A design method for aircraft structural parts based on deep learning
Caiyuan et al. HPRODIE: using feature modelling and feature mapping to speed up progressive die design
Binder et al. Utilizing an enterprise architecture framework for model-based industrial systems engineering
CN120373519A (en) Artificial intelligent driven foam special-shaped die cutting optimization system
JP7171094B2 (en) Personalized Design Pattern Matching Method for &#34;Internet +&#34; Environmental Machinery Products
CN114372181B (en) Equipment production intelligent planning method based on multi-mode data
CN114254552B (en) A modular method for deconstructing and reorganizing complex products based on graph neural network
CN116050809A (en) Fault operation planning method and equipment for virtual maintenance
US20230401487A1 (en) Method, system and computer program product for providing insights on user desirability

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