CN110298066B - Intelligent matching method for standard tapered wedge - Google Patents
Intelligent matching method for standard tapered wedge Download PDFInfo
- Publication number
- CN110298066B CN110298066B CN201910400747.9A CN201910400747A CN110298066B CN 110298066 B CN110298066 B CN 110298066B CN 201910400747 A CN201910400747 A CN 201910400747A CN 110298066 B CN110298066 B CN 110298066B
- Authority
- CN
- China
- Prior art keywords
- solution
- constraint
- installation
- standard
- vector
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Complex Calculations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent matching method for a standard wedge, which comprises the following steps: A. inputting functional elements; B. extracting feature element calculation information; C. depth-first search is carried out, and solution vectors are calculated; D. according to the data structure, a vector container is established, the previously searched solution vectors are stored, and the index address of each solution vector is established; E. accessing a current solution feature; F. inputting an installation element, and extracting a constraint condition of an installation environment; G. solving an optimized solution which meets the time step length or the iteration times by using an ant colony algorithm; H. and instantiating the space installation state parameters to obtain a final product scheme. The invention improves the design efficiency and rationality, and simultaneously, the system can carry out learning and knowledge accumulation with extremely high speed and efficiency, and can output the design result more quickly and better.
Description
Technical Field
The invention relates to an intelligent mold design and manufacturing technology, in particular to an intelligent matching method for a standard tapered wedge.
Background
In the existing mold design technology, no specific scheme exists for the mold design of the tapered wedge. 1. Generally, according to the overall condition of the die, designers calculate and match the shape and position sizes of all elements on the wedge through visual observation and subjective judgment, a large amount of similar calculation is needed, and then a reasonable design result is obtained through a large amount of modification. Therefore, the current design of the wedge has high work repeatability and low design efficiency.
Disclosure of Invention
In view of the above, the present invention provides an intelligent matching method for a standard wedge, so as to realize intelligent design of the standard wedge by automatically identifying design elements, automatically calculating form and position dimensions, and automatically interacting relationships between parts.
According to one aspect of the invention, a standard wedge intelligent matching method is provided, which is characterized by comprising the following steps:
A. inputting a functional element;
B. extracting feature element calculation information;
C. depth-first search is carried out, and solution vectors are calculated;
D. according to the data structure, a vector container is established, the previously searched solution vectors are stored, and the index address of each solution vector is established;
E. accessing a current solution feature;
F. inputting an installation element, and extracting a constraint condition of an installation environment;
G. solving an optimized solution which meets the time step length or the iteration times by using an ant colony algorithm;
H. and instantiating the space installation state parameters to obtain a final product scheme.
In some embodiments, the functional input element of step a comprises: the method comprises the steps of upper-level calculation of work characteristic line area constraint, standard CAM orientation constraint, standard CAM external attribute information and installation form of a standard CAM installation surface.
In some embodiments, the extracting feature element calculation information in step B specifically includes: fitting the characteristic line region according to a minimum rectangle; extracting a working direction vector and an installation vector of an installation plane; and extracting width constraint numerical values, height constraint numerical values and force constraint numerical values of the characteristic regions.
In some embodiments, step C said depth-first search, computing a solution vector; the method specifically comprises the following steps: and defining constraint condition variables, setting different weights for each constraint, establishing a matching degree function, and performing matching calculation by using the constraint condition variables and the weights to obtain a solution vector.
In some embodiments, the constraint condition variables include scenario usage constraints, cost constraints, time constraints, installation constraints.
In some embodiments, step E accesses the current solution features; the method specifically comprises the following steps: and finding out the corresponding main key and the virtual model data cloud by solving the vector, preferentially extracting a group of characteristic information corresponding to the virtual model, carrying out screening and interpolation operation on the characteristic information, and fitting each discrete section into a low-order computing geometry by using a least square method, thereby simplifying the characteristics and accelerating the algorithm convergence speed.
In some embodiments, the constraints of the installation environment in step F include a size range, a maximum allowable variation region, a region minimum safety amount, and a characteristic constraint curve.
In some embodiments, the ant colony algorithm in step G solves an optimized solution that satisfies a time step or an iteration number, specifically: and (3) introducing installation environment constraint parameters, solving an installation parallel solution set of key factors through dynamic programming, solving the distribution characteristics of random influence factors through probability statistics, and finding out an optimized solution meeting the time step length or the iteration times from the parallel solutions.
In some embodiments, the standard intelligent tapered wedge matching method further comprises a step I of training a model, recording a current reasonable solution vector, and updating a memory tabu table.
In some embodiments, the instantiating the space installation state parameter in step H to obtain a final product solution specifically includes: and constructing a feature transformation matrix according to the solution vector, instantiating feature data to a space selection position, and establishing index queries such as distribution identifiers, aggregation identifiers, ID (identity) updating and the like.
The intelligent matching method for the standard wedge has the following beneficial effects:
1) Compared with manual design: the repeated labor of designers is largely eliminated, and the design efficiency is improved. The correctness of the product (and the product process) design can be verified more quickly.
2) Compared with the traditional design: the change of the input elements is dragged to move the whole body, and only replacement, calculation and updating are needed, so that an additional stove is not needed, and time and labor are wasted.
3) Ability to learn and upgrade itself: manual trial and error are not needed, design efficiency and reasonableness are improved, and meanwhile the system can learn and accumulate knowledge at extremely high speed and efficiency, so that design results can be output faster and better.
Drawings
Fig. 1 is a schematic flow chart of a standard wedge intelligent matching method according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings.
Fig. 1 schematically illustrates a standard intelligent tapered wedge matching method according to an embodiment of the present invention.
Referring to fig. 1, an intelligent matching method for a standard wedge includes the following steps:
step 101: inputting functional elements; step A the functional input element comprises: the method comprises the following steps of upper-level calculation, working characteristic line area constraint, standard CAM (computer Aided Manufacturing) orientation constraint, standard CAM external attribute information, mounting form of a standard CAM mounting surface and the like.
Step 102: extracting feature element calculation information; the working characteristic line region often contains a plurality of domains, each domain is composed of subdivided curve segments, and the characteristic line region is fitted according to a minimum rectangle; extracting a working orientation vector and an installation vector of an installation plane; and extracting width constraint numerical values, height constraint numerical values and force constraint numerical values of the characteristic regions.
Step 103: depth-first search is carried out, and solution vectors are calculated; defining constraint condition variables Xi, setting different weights for each constraint, establishing a matching degree function, and performing matching calculation by using the constraint condition variables and the weights to obtain a solution vector.
The constraint condition variables comprise an X1 scene use constraint, an X2 cost constraint, an X3 time constraint and an X4 installation constraint. Setting different weights Wi (W1, W2, W3, W4) for each constraint, wherein the initial value of the weights is derived from mathematical statistics, for example, the matching degree function is established by using fluctuation factors such as frequency, real-time price and the like, theta = f (X1, X2, X3, X4, W1, W2, W3, W4, orders)
Orders=f(X,Y)
X = { X1, X2, X3, X4} frequency-dependent parameter
Y = { Y1, Y2, Y3, Y4} price-related parameter
theta-return state variable; orders-current solution vector.
The extremum solution can be obtained by the steepest descent method or the Newton method, and when the solution space has no solution, step 111 can be executed to gradually release the secondary constraint and modify the weight ratio. Returning to step 101 to continue the iteration.
Step 104: according to the data structure, a vector container is established, the previously searched solution vectors are stored, and the index address of each solution vector is established;
step 105: accessing a current solution feature; and finding out the corresponding main key and virtual model data cloud through the solution vector, preferentially extracting a group of characteristic information corresponding to the virtual model, carrying out screening and interpolation operation on the characteristic information, and fitting each discrete section into a low-order computing geometry by using a least square method, thereby simplifying the characteristics and accelerating the algorithm convergence speed. The computational geometry is the inclusion after the simplified model discretization.
Step 106: inputting an installation element, and extracting a constraint condition of an installation environment; the constraint conditions of the installation environment comprise a size range, a maximum allowable variable quantity area, an area minimum safety quantity and a characteristic constraint curve.
Step 107: solving an optimized solution which meets the time step length or the iteration times by using an ant colony algorithm; and introducing an installation element into the model, solving an installation parallel solution set of key factors by the installation environment constraint parameters through dynamic planning, solving the distribution characteristics of random influence factors through probability statistics, and finding out an optimized solution meeting the time step length or the iteration times from the parallel solution.
Setting an initial information amount tau for parallel solution, and constructing a state transition probability formula as follows:
selecting a node in the parallel solution as an initial node training model, and achieving final convergence on the optimal solution through continuous updating of pheromones, wherein the pheromone updating equation is as follows:
m is the number of ants; n is the number of nodes (vertices);
η ij visibility of the side arcs (i, j), or local heuristic factors, typically 1/d ij ,d ij Represents the length between paths (i, j); (the visibility transferred from city i to city j is also called heuristic information)
τ ij -pheromone trace intensity (intensity) of the side arc (i, j);
α -the relative importance of the pheromone track (α ≧ 0);
beta-the relative importance of side arc visibility (beta. Gtoreq.0);
ρ -the persistence of the pheromone track (0. Ltoreq. ρ.ltoreq.1), 1- ρ being understood as the degree of attenuation of the track (evadation);
q-a constant representing the number of traces left by the ant;
u-set of feasible nodes;
tabu (k) -a list to record the cities that the kth ant has visited so far.
An optimal model is obtained through training of an existing labeled training sample, an evaluation mechanism is established under the current use environment, an inference function is generated, and a better solution under the evaluation function is obtained and is a global optimal solution.
Step 108: and instantiating the space installation state parameters to obtain a final product scheme. And instantiating by using the optimal model, constructing a feature transformation matrix according to the solution vector, instantiating feature data to a space selection position, and establishing index queries such as distribution identifiers, aggregation identifiers, ID (identity) updating and the like. And obtaining a visual product model and an optimal product scheme.
According to the method, matching calculation and optimization design are carried out on all parameters in the standard wedge in combination with constraint conditions, and training and optimization of a calculation model are automatically carried out, so that an optimization solution of the standard wedge die is finally obtained. All design processes do not need manual identification and design calculation, can adapt to the complexity of a design environment, and greatly improves the working efficiency and the design accuracy.
What has been described above are merely some embodiments of the present invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept herein, and it is intended to cover all such modifications and variations as fall within the scope of the invention.
Claims (8)
1. An intelligent matching method for a standard wedge is characterized by comprising the following steps: a. Inputting a functional element; the functional elements include: the method comprises the following steps of upper-level calculation of working characteristic line area constraint, standard CAM position constraint, standard CAM external attribute information and installation form of a standard CAM installation surface; b. Extracting feature element calculation information; the extracting of the feature element calculation information specifically includes: fitting the characteristic line region according to a minimum rectangle; extracting a working direction vector and an installation vector of an installation plane; extracting width constraint numerical values, height constraint numerical values and force constraint numerical values of the characteristic regions; c. Depth-first search is carried out, and solution vectors are calculated; D. according to the data structure, a vector container is established, the solution vectors searched previously are stored, and the index addresses of the solution vectors are established; e. Accessing a current solution feature; F. inputting an installation element, and extracting a constraint condition of an installation environment; G. solving an optimized solution which meets the time step length or the iteration times by using an ant colony algorithm; H. and instantiating the space installation state parameters to obtain a final product scheme.
2. The intelligent matching method for standard inclined wedges according to claim 1, wherein, in the step C, the depth-first search is carried out to calculate a solution vector; the method comprises the following specific steps: and defining constraint condition variables, setting different weights for each constraint, establishing a matching degree function, and performing matching calculation by using the constraint condition variables and the weights to obtain a solution vector.
3. The intelligent matching method for the standard tapered wedge as claimed in claim 2, wherein the constraint condition variables comprise scene use constraint, cost constraint, time constraint and installation constraint.
4. The intelligent matching method for standard wedges according to claim 1, wherein step E accesses the current solution features; the method specifically comprises the following steps: and finding out a corresponding main key and a virtual model data cloud through the solution vector, preferentially extracting a group of characteristic information corresponding to the virtual model, carrying out screening and interpolation operation on the characteristic information, and fitting each discrete section into a low-order computational geometry by using a least square method, thereby simplifying the characteristics and accelerating the algorithm convergence speed.
5. The intelligent matching method for standard wedges according to claim 1, wherein the constraints of the installation environment in step F include size range, maximum allowable variation range, minimum safety volume of area, and characteristic constraint curve.
6. The intelligent matching method for the standard tapered wedge according to claim 1, wherein the ant colony algorithm in the step G solves an optimized solution satisfying a time step or an iteration number, specifically: and (3) introducing installation environment constraint parameters, solving an installation parallel solution set of key factors through dynamic programming, solving the distribution characteristics of random influence factors through probability statistics, and finding out an optimized solution meeting the time step length or the iteration times from the parallel solutions.
7. The intelligent matching method for the standard inclined wedge as claimed in claim 1, further comprising a step I of training a model, recording a current reasonable solution vector and updating a memory tabu table.
8. The intelligent matching method for the standard tapered wedge according to claim 1, wherein the instantiation space installation state parameters in the step H are used to obtain a final product scheme, and specifically: and constructing a feature transformation matrix according to the solution vector, instantiating feature data to a space selection position, and establishing index queries such as distribution identifiers, aggregation identifiers, ID (identity) updating and the like.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910400747.9A CN110298066B (en) | 2019-05-15 | 2019-05-15 | Intelligent matching method for standard tapered wedge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910400747.9A CN110298066B (en) | 2019-05-15 | 2019-05-15 | Intelligent matching method for standard tapered wedge |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110298066A CN110298066A (en) | 2019-10-01 |
CN110298066B true CN110298066B (en) | 2023-04-18 |
Family
ID=68026800
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910400747.9A Active CN110298066B (en) | 2019-05-15 | 2019-05-15 | Intelligent matching method for standard tapered wedge |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110298066B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5969973A (en) * | 1994-11-09 | 1999-10-19 | Amada Company, Ltd. | Intelligent system for generating and executing a sheet metal bending plan |
GB2424304A (en) * | 2005-03-18 | 2006-09-20 | Lightuning Tech Inc | Generating non-overlapping partial fingerprints with a sweep sensor |
EP2365440A1 (en) * | 2010-03-12 | 2011-09-14 | Xmos Ltd | Program flow route constructor |
WO2018130820A1 (en) * | 2017-01-12 | 2018-07-19 | University Of Bath | Generating an object representation to be manufactured |
CN108333937A (en) * | 2018-02-02 | 2018-07-27 | 江苏师范大学 | A kind of contour machining method for multi-shaft interlocked lathe |
CN108628260A (en) * | 2017-03-20 | 2018-10-09 | 浙江巨星工具有限公司 | Multi items Tool set equipment based on robot and automatic assembling technique |
CN109164815A (en) * | 2018-09-06 | 2019-01-08 | 中国计量大学 | A kind of Autonomous Underwater Vehicle paths planning method based on improvement ant group algorithm |
CN109388875A (en) * | 2018-09-05 | 2019-02-26 | 重庆创速工业有限公司 | A kind of design implementation method of elastic element module |
CN109597355A (en) * | 2018-11-02 | 2019-04-09 | 南京航空航天大学 | The design method of the micro- texture numerical control processing generating tool axis vector of curved surface |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7328074B2 (en) * | 2002-12-02 | 2008-02-05 | United Technologies Corporation | Real-time quadratic programming for control of dynamical systems |
JP4691158B2 (en) * | 2005-06-16 | 2011-06-01 | ストライダー ラブス,インコーポレイテッド | Recognition system and method for 2D images using 3D class model |
-
2019
- 2019-05-15 CN CN201910400747.9A patent/CN110298066B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5969973A (en) * | 1994-11-09 | 1999-10-19 | Amada Company, Ltd. | Intelligent system for generating and executing a sheet metal bending plan |
GB2424304A (en) * | 2005-03-18 | 2006-09-20 | Lightuning Tech Inc | Generating non-overlapping partial fingerprints with a sweep sensor |
EP2365440A1 (en) * | 2010-03-12 | 2011-09-14 | Xmos Ltd | Program flow route constructor |
WO2018130820A1 (en) * | 2017-01-12 | 2018-07-19 | University Of Bath | Generating an object representation to be manufactured |
CN108628260A (en) * | 2017-03-20 | 2018-10-09 | 浙江巨星工具有限公司 | Multi items Tool set equipment based on robot and automatic assembling technique |
CN108333937A (en) * | 2018-02-02 | 2018-07-27 | 江苏师范大学 | A kind of contour machining method for multi-shaft interlocked lathe |
CN109388875A (en) * | 2018-09-05 | 2019-02-26 | 重庆创速工业有限公司 | A kind of design implementation method of elastic element module |
CN109164815A (en) * | 2018-09-06 | 2019-01-08 | 中国计量大学 | A kind of Autonomous Underwater Vehicle paths planning method based on improvement ant group algorithm |
CN109597355A (en) * | 2018-11-02 | 2019-04-09 | 南京航空航天大学 | The design method of the micro- texture numerical control processing generating tool axis vector of curved surface |
Non-Patent Citations (2)
Title |
---|
Detecting and matching feature points;EtienneVincent,RobertLaganière;《Journal of Visual Communication and Image Representation》;20050228;第16卷(第1期);第38-54页 * |
型腔零件曲面加工特征识别方法;耿维忠 等;《计算机集成制造系统》;20160331;第22卷(第3期);第738-745页 * |
Also Published As
Publication number | Publication date |
---|---|
CN110298066A (en) | 2019-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tanchoco | Material flow systems in manufacturing | |
CN110008259A (en) | The method and terminal device of visualized data analysis | |
CN103778304B (en) | Design method of motor vehicle drive axle | |
Sharda et al. | Robust manufacturing system design using multi objective genetic algorithms, Petri nets and Bayesian uncertainty representation | |
CN105893669A (en) | Global simulation performance predication method based on data digging | |
CN110428015A (en) | A kind of training method and relevant device of model | |
CN112115276A (en) | Intelligent customer service method, device, equipment and storage medium based on knowledge graph | |
Scanlan et al. | Cost modelling for aircraft design optimization | |
CN107102995A (en) | A kind of determination method and device of SQL executive plans | |
CN106295074B (en) | A kind of carrier rocket bay section vibratory response characteristic is quickly analyzed and optimization method | |
Özsoy et al. | Estimating the parameters of nonlinear regression models through particle swarm optimization | |
CN115330357A (en) | Intelligent stereo garage data management method, device, equipment and storage medium | |
CN109285024A (en) | Online feature determines method, apparatus, electronic equipment and storage medium | |
Liu et al. | An obsolescence forecasting method based on improved radial basis function neural network | |
KR101522306B1 (en) | A system and control method for a meta-heuristic algorithm utilizing similarity for performance enhancement | |
CN110298066B (en) | Intelligent matching method for standard tapered wedge | |
CN108182243A (en) | A kind of Distributed evolutionary island model parallel method based on Spark | |
CN102779288B (en) | A kind of ontological analysis method based on field theory | |
Küchenhof et al. | Planning & tracking the changes-matrix mapping of modular product family generations | |
CN109033678A (en) | A kind of aircraft near-optimal design method generated based on virtual sample | |
CN106446382A (en) | Domain-entity oriented graphic modeling and analyzing environment and implementation method thereof | |
Antonova et al. | Frame-based expert system implementation for resource conversion processes analysis | |
KR20190120729A (en) | System Modeling Method by Machine Learning using Big data | |
CN113609631B (en) | Event network topology diagram-based creation method and device and electronic equipment | |
US11709471B2 (en) | Distributed automated synthesis of correct-by-construction controllers |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200114 Address after: 610037 no.36-4, Jinqing Road, Jinniu District, Chengdu, Sichuan Province Applicant after: Chengdu digital analog code technology Co.,Ltd. Address before: Zheng Jie 400050 Xiejiawan Jiulongpo District of Chongqing City No. 49 China Resources Building thirty-seventh room first Applicant before: Chongqing Chuangsu Industrial Technology Research Institute Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |