CN107545105A - A kind of part resilience parameter optimization in forming method based on PSO - Google Patents
A kind of part resilience parameter optimization in forming method based on PSO Download PDFInfo
- Publication number
- CN107545105A CN107545105A CN201710724055.0A CN201710724055A CN107545105A CN 107545105 A CN107545105 A CN 107545105A CN 201710724055 A CN201710724055 A CN 201710724055A CN 107545105 A CN107545105 A CN 107545105A
- Authority
- CN
- China
- Prior art keywords
- resilience
- forming
- optimization
- svm
- optimizing
- 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.)
- Pending
Links
Landscapes
- Bending Of Plates, Rods, And Pipes (AREA)
Abstract
The invention discloses a kind of part resilience parameter optimization in forming method based on PSO, including establish springback Prediction mathematical model, the forming parameters Simulation with particle cluster algorithm in CV SVM approximate models after iteration optimizing, progress optimizing parameter optimization;For the present invention by particle cluster algorithm, it is 0.54mm that can obtain the maximum displacement after part forming resilience, less than the maximum displacement 0.7mm of beginning, meets the use and matching requirements of part, the minimum thickness of part is tmin=0.67mm, reduction 25.6%, preferably Optimize the forming scheme technological parameter, part defect is reduced, theoretical foundation is provided for actual production.
Description
Technical field
The invention belongs to SGCC plate complicated bend forming technologies field, more particularly to a kind of part resilience based on PSO
Parameter optimization in forming method.
Background technology
With automobile in life, the rapid popularization of production field with updating, window lifting plate is as regulation automotive window
The quality of key activities part, its assembly performance and performance directly determines the stationarity and smoothness of vehicle window activity, together
When also largely influence people experience sense by.Due to window lifting plate structure relative to other large-scale coverings and
For structural member, there is the characteristics of complex-shaped, Curvature varying is big, the requirement of component assembly size is high, cause in actual production
In order to obtain the excellent part of quality, it is necessary to reduce part resilience as much as possible in journey, avoid causing under parts size precision
Drop.
At this stage, when carrying out Springback Analysis to stamping parts, there is more ripe analytical solution, but only analyzing
Shape is relatively easy, is easily formed part just useful such as common U-shaped part and V-type part etc..When it come to answered to shape
During shaped piece miscellaneous, feature is more, Analytical Solution rule is lack scope for their abilities.While studies have found that, time under test conditions
Bullet amount calculated value is bigger than normal, and average relative error is up to 88%, so the analytical Calculation for relying solely on theoretical formula is come
Predict that part springback capacity is much infeasible, or even the prediction result to make mistake can be given, mislead practical application.
The content of the invention
The technical problem to be solved in the present invention is:A kind of part resilience parameter optimization in forming side based on PSO is provided
Method, the defects of complicated bend part is present and deficiency can be predicted, in order to reduce the springback capacity of window lifting plate, with meet assembling and
Performance to forming parameters, it is necessary to carry out selection optimization so that springback capacity is minimum, to solve above-mentioned to deposit in the prior art
The problem of.
The technical scheme that the present invention takes is:A kind of part resilience parameter optimization in forming method based on PSO, with
CV-SVM approximate models are main body, using sheet thickness, drawing velocity, three forming parameters of friction factor interval as
Constraints, the least displacement of part resilience is optimization aim, is iterated optimizing using particle cluster algorithm, it is optimal to obtain its
Forming parameters combine, and the forming parameters after optimization are imported numerical simulation and checking are carried out in DYNAFORM softwares,
The effect of optimization of rebound data, this method comprise the following steps before and after contrast:
(1) a kind of automobile abnormity bool part is directed to, establishes springback Prediction mathematical model, first being sent out after part forming
The maximum displacement of raw resilience sets up constraints as optimization aim, while according to part resilience displacement;
(2) particle cluster algorithm iteration optimizing in CV-SVM approximate models is used, optimal punish is obtained with K folding cross-validation methods
Penalty factor C and core width cs, and Support vector regression forecast model CV-SVM approximate models are built with this, use particle cluster algorithm
Carry out parameter optimization;
(3) the forming parameters numerical simulation that the optimizing parameter obtained in CV-SVM approximate models optimizes is tested
Card, the forming parameters of acquisition are inputted into DYNAFORM softwares and carry out resilience numerical simulation, after part forming resilience
Maximum displacement shown with thickness by cloud atlas form, show maximum displacement numerical quantity and minimum thickness.
Preferably, the optimal forming parameters obtained after above-mentioned steps (2) Program iteration optimizing are:Sheet thickness A
=0.900682mm, drawing velocity B=5933.782mm/s, friction factor C=0.143287, the dominant bit of prediction part resilience
Shifting amount is y=0.474205mm.
Maximum displacement maximum in step (3) after part forming resilience is 0.54mm, the thickness minimum thickness of part
For tmin=0.67mm, reduction 25.6%.
Beneficial effects of the present invention:Compared with prior art, effect of the present invention is as follows:
(1) present invention is replaced between window lifting plate forming parameters and part springback capacity by CV-SVM approximate models
Complicated contact, optimizing is iterated using particle cluster algorithm respectively in the constraint section of forming parameters, find so that
The minimum parameter combination of part springback capacity (maximum moving displacement).Tested by carrying out numerical simulation to forming parameters with analysis
Card, show that the technological parameter obtained based on CV-SVM approximate models can largely reduce part springback capacity, lift part
Quality.And recommend one group of optimal forming parameters so that part springback capacity is minimum, and product quality is best.And further
Shorten the construction cycle of product, reduce production cost;
(2) present invention rolls over the optimal penalty factor and core width cs structure SVMs of cross-validation method acquisition by K
Regressive prediction model CV-SVM is research platform, and parameter optimization is carried out with particle cluster algorithm.Optimal shaping in section can be obtained
Technological parameter, and the maximum displacement for predicting part resilience makes that the whole Process planning flow cycle shortens, design efficiency is higher,
Time and materials cost reduces, and reduces die trial number;
(3) by DYNAFORM softwares, the forming parameters of acquisition is subjected to resilience numerical simulation, pass through numerical simulation
Comparative analysis, the maximum displacement obtained after part forming resilience is 0.54mm, full less than the maximum displacement 0.7mm of beginning
The use and matching requirements of sufficient part, the minimum thickness of part is tmin=0.67mm, reduction 25.6%, preferably optimizes
Forming parameters, part defect is reduced, theoretical foundation is provided for actual production.
Brief description of the drawings
Fig. 1 is particle cluster algorithm optimizing under CV-SVM;
Fig. 2 is window lifting plate complicated bend part threedimensional model;
Fig. 3 is part resilience maximum displacement (CV-SVM);
Fig. 4 is part thickness cloud charts (CV-SVM).
Embodiment
Below in conjunction with the accompanying drawings and the present invention is described further specific embodiment.
Embodiment:As Figure 1-Figure 4, the part resilience forming technology ginseng based on PSO in a kind of CV-SVM approximate models
Number optimization method, this method comprise the following steps:
(1) founding mathematical models, optimization aim and constraints are determined:Because the analysis object of this research bends for abnormity
Part window lifting plate, in order to ensure the overall precision that part is assembled in the later stage, the maximum that resilience occurs after part forming
Displacement (blankmovement) is used as optimization aim, is designated as yi=(blank movement)i, according to requirements, not
On the premise of the unrepairable defects such as generation rupture, maximum displacement is less than ymin=0.7mm, you can meet that assembling uses bar
Part, the maximum displacement before and after part forming can be handled upon rebound to be directly displayed under interface.Non-selected part is different herein cuts
Face angle of bend variable quantity (△ θ) is because the part mainly considers overall dimensions, details chi in assembling process as optimization aim
The very little influence degree to assembly precision is little.
Min y=f (A, B, C)=yi
In order to choose optimal forming parameters, it is necessary on the basis of initial formation technological parameter selection parameter value
Constant interval, the section taken herein determine method be to the initial value of each parameter in terms of 80% and 120% ratio
Maximum and minimum value are calculated, as a result as shown in table 1.
The interval of the forming parameters of table 1
Optimized variable | Lower limit | Average value | The upper limit |
Material thickness A/mm | 0.8 | 1.0 | 1.2 |
Drawing velocity B/mms-1 | 4000 | 5000 | 6000 |
Friction factor C | 0.100 | 0.125 | 0.150 |
The beam condition of object function is set according to constraint section.
(2) particle cluster algorithm iteration optimizing in CV-SVM approximate models is used.Obtained with K folding cross-validation methods optimal
Penalty factor and core width cs structure Support vector regression forecast model CV-SVM are research platform, are carried out with particle cluster algorithm
Parameter optimization.The inertia weight ω of particle cluster algorithm is arranged to fixed weight ω=0.7298, Studying factors c1=c2=
1.4692 maximum iteration kCV=100, it is programmed, debugs under MATLAB softwares.
Program iteration searching process is as shown in figure 1, the optimal forming parameters obtained are:Sheet thickness A=
0.900682mm, drawing velocity B=5933.782mm/s, friction factor C=0.143287, predict the maximum displacement of part resilience
Measure as y=0.474205mm.
(3) by DYNAFORM softwares, the forming parameters of acquisition is subjected to resilience numerical simulation, pass through numerical simulation
Comparative analysis, the maximum displacement obtained after part forming resilience is 0.54mm, full less than the maximum displacement 0.7mm of beginning
The use and matching requirements of sufficient part, the minimum thickness of part is tmin=0.67mm, reduction 25.6%, preferably optimizes
Forming parameters, part defect is reduced, theoretical foundation is provided for actual production.
Interpretation of result
(1) present invention is replaced between window lifting plate forming parameters and part springback capacity by CV-SVM approximate models
Complicated contact, optimizing is iterated using particle cluster algorithm respectively in the constraint section of forming parameters, find so that
The minimum parameter combination of part springback capacity (maximum moving displacement).Tested by carrying out numerical simulation to forming parameters with analysis
Card, show that the technological parameter obtained based on CV-SVM approximate models can largely reduce part springback capacity, lift part
Quality.And recommend one group of optimal forming parameters so that part springback capacity is minimum, and product quality is best.And further
Shorten the construction cycle of product, reduce production cost.
(2) present invention rolls over the optimal penalty factor and core width cs structure SVMs of cross-validation method acquisition by K
Regressive prediction model CV-SVM is research platform, and parameter optimization is carried out with particle cluster algorithm.Optimal shaping in section can be obtained
Technological parameter, and the maximum displacement for predicting part resilience makes that the whole Process planning flow cycle shortens, design efficiency is higher,
Time and materials cost reduces, and reduces die trial number;
(3) by DYNAFORM softwares, the forming parameters of acquisition is subjected to resilience numerical simulation, pass through numerical simulation
Comparative analysis, the maximum displacement obtained after part forming resilience is 0.54mm, full less than the maximum displacement 0.7mm of beginning
The use and matching requirements of sufficient part, the minimum thickness of part is tmin=0.67mm, reduction 25.6%, preferably optimizes
Forming parameters, part defect is reduced, theoretical foundation is provided for actual production.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention, therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (2)
- A kind of 1. part resilience parameter optimization in forming method based on PSO, it is characterised in that:Using CV-SVM approximate models as Main body, using the interval in three sheet thickness, drawing velocity, friction factor forming parameters as constraints, part Resilience displacement is minimised as optimization aim, and optimizing is iterated using particle cluster algorithm, obtains its optimal forming parameters Combination, the forming parameters after optimization are imported numerical simulation and checking, resilience before and after contrast are carried out in DYNAFORM softwares The effect of optimization of data, this method comprise the following steps:(1) a kind of automobile abnormity bool part is directed to, establishes springback Prediction mathematical model, first occurring back after part forming The maximum displacement of bullet sets up constraints as optimization aim, while according to part resilience displacement;(2) use particle cluster algorithm iteration optimizing in CV-SVM approximate models, with K folding cross-validation methods obtain optimal punishment because Sub- C and core width cs, and Support vector regression forecast model CV-SVM approximate models are built with this, carried out with particle cluster algorithm Parameter optimization;(3) the forming parameters Simulation for optimizing the optimizing parameter obtained in CV-SVM approximate models, will The forming parameters of acquisition, which are inputted into DYNAFORM softwares, carries out resilience numerical simulation, by the maximum after part forming resilience Displacement is shown with thickness by cloud atlas form, shows maximum displacement numerical quantity and minimum thickness.
- 2. a kind of part resilience parameter optimization in forming method based on PSO according to claim 1, its feature exist In:The optimal forming parameters obtained in step (2) after iteration optimizing are:Sheet thickness A=0.900682mm, drawing velocity B=5933.782mm/s, friction factor C=0.143287, the maximum displacement of prediction part resilience is y=0.474205mm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710724055.0A CN107545105A (en) | 2017-08-22 | 2017-08-22 | A kind of part resilience parameter optimization in forming method based on PSO |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710724055.0A CN107545105A (en) | 2017-08-22 | 2017-08-22 | A kind of part resilience parameter optimization in forming method based on PSO |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107545105A true CN107545105A (en) | 2018-01-05 |
Family
ID=60958907
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710724055.0A Pending CN107545105A (en) | 2017-08-22 | 2017-08-22 | A kind of part resilience parameter optimization in forming method based on PSO |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107545105A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108872241A (en) * | 2018-03-30 | 2018-11-23 | 南京航空航天大学 | A kind of train wheel tread damage detection method based on SVM algorithm |
CN111061219A (en) * | 2019-12-16 | 2020-04-24 | 南京航空航天大学 | Method for rapidly determining forming process parameters |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799735A (en) * | 2012-07-24 | 2012-11-28 | 湖南大学 | Springback compensation method based on technological parameter control |
CN102831269A (en) * | 2012-08-16 | 2012-12-19 | 内蒙古科技大学 | Method for determining technological parameters in flow industrial process |
CN103646280A (en) * | 2013-11-28 | 2014-03-19 | 江苏大学 | Particle swarm algorithm-based vehicle suspension system parameter optimization method |
CN105956235A (en) * | 2016-04-20 | 2016-09-21 | 杭州电子科技大学 | Optimum design method for ultrasonic machining special cutter based on SVR-PSO |
CN107025354A (en) * | 2017-04-15 | 2017-08-08 | 贵州大学 | A kind of window lifting plate forming technology optimization method based on range analysis |
-
2017
- 2017-08-22 CN CN201710724055.0A patent/CN107545105A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799735A (en) * | 2012-07-24 | 2012-11-28 | 湖南大学 | Springback compensation method based on technological parameter control |
CN102831269A (en) * | 2012-08-16 | 2012-12-19 | 内蒙古科技大学 | Method for determining technological parameters in flow industrial process |
CN103646280A (en) * | 2013-11-28 | 2014-03-19 | 江苏大学 | Particle swarm algorithm-based vehicle suspension system parameter optimization method |
CN105956235A (en) * | 2016-04-20 | 2016-09-21 | 杭州电子科技大学 | Optimum design method for ultrasonic machining special cutter based on SVR-PSO |
CN107025354A (en) * | 2017-04-15 | 2017-08-08 | 贵州大学 | A kind of window lifting plate forming technology optimization method based on range analysis |
Non-Patent Citations (7)
Title |
---|
付阳,李昆仑: "支持向量机模型参数选择方法综述", 《电脑知识与技术》 * |
化春键,周海英: "聚类和优化支持向量机的冷轧带钢表面缺陷分类", 《塑性工程学报》 * |
向国齐,殷国富: "基于支持向量机和粒子群算法的稳健优化", 《机械设计与研究》 * |
杨旭静,冯小龙,郑娟,郭水军: "SVM 和改进粒子群算法在冲压成形优化中的应用", 《汽车工程》 * |
王莉媛,梅益,刘闯,杨幸雨: "车窗升降板弯曲成形回弹缺陷的影响因素分析与成形工艺优化", 《锻压技术》 * |
聂立新等: "粒子群算法优化双核支持向量机及应用", 《振动、测试与诊断》 * |
陆梓端; 高茂庭: "基于改进遗传算法的支持向量机参数优化", 《现代计算机(专业版)》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108872241A (en) * | 2018-03-30 | 2018-11-23 | 南京航空航天大学 | A kind of train wheel tread damage detection method based on SVM algorithm |
CN111061219A (en) * | 2019-12-16 | 2020-04-24 | 南京航空航天大学 | Method for rapidly determining forming process parameters |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110378799B (en) | Alumina comprehensive production index decision method based on multi-scale deep convolution network | |
CN103593719B (en) | A kind of rolling power-economizing method based on slab Yu contract Optimized Matching | |
CN103745273A (en) | Semiconductor fabrication process multi-performance prediction method | |
CN104765912A (en) | Robustness optimizing method of aluminum plate punching process | |
CN103543719B (en) | A kind of workflow industry operator scheme self-adapting regulation method based on operating mode | |
CN104375478B (en) | A kind of method and device of Rolling production process product quality on-line prediction and optimization | |
CN104077439A (en) | Numerical simulation method of novel high-strength steel spoke drawing punching combined process | |
CN105740467A (en) | Mining method for C-Mn steel industry big data | |
CN106709654A (en) | Global operating condition evaluating and quality tracing method for hydrocracking process | |
CN107545105A (en) | A kind of part resilience parameter optimization in forming method based on PSO | |
CN106345823A (en) | On-line real-time mechanical property prediction method based on hot rolled steel coil production processes | |
CN107025354A (en) | A kind of window lifting plate forming technology optimization method based on range analysis | |
Feng et al. | Optimization of variable blank holder force in deep drawing based on support vector regression model and trust region | |
CN111651929A (en) | Multi-objective optimization method based on fusion of Dynaform and intelligent algorithm | |
CN107292029A (en) | A kind of determination method that sheet forming technological parameter is predicted based on forming defects | |
CN115169453A (en) | Hot continuous rolling width prediction method based on density clustering and depth residual error network | |
CN107092745A (en) | A kind of window lifting plate forming technology optimization method based on variance analysis | |
CN109948174B (en) | Mass distribution method for calculating natural frequency of frame structure by centralized mass method | |
CN102621953A (en) | Automatic online quality monitoring and prediction model updating method for rubber hardness | |
CN116629059A (en) | Method and device for optimizing multiple-working-procedure forming parameters of rim and readable medium | |
CN103544349A (en) | Optimization method of vibrating stability of automobile disk brake system | |
CN115952597A (en) | Wear simulation method for sharp edge forming die of automobile fender | |
CN106326677A (en) | Soft measurement method of acetic acid consumption in PTA device | |
CN104537167B (en) | Interval type indices prediction method based on Robust Interval extreme learning machine | |
CN107563029A (en) | A kind of SVMs approximate model optimization method based on K folding cross-validation methods |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180105 |
|
RJ01 | Rejection of invention patent application after publication |