[1]王博,蔡安江,孟广慧,等.采用组合算法的注塑制品翘曲变形预测[J].西安交通大学学报,2020,54(08):084-90.[doi:10.7652/xjtuxb202008011]
 WANG Bo,CAI Anjiang,MENG Guanghui,et al.Warpage Deformation Prediction of Injection Products with Combinatorial Algorithm[J].Journal of Xi'an Jiaotong University,2020,54(08):084-90.[doi:10.7652/xjtuxb202008011]
点击复制

采用组合算法的注塑制品翘曲变形预测
分享到:

《西安交通大学学报》[ISSN:0253-987X/CN:61-1069/T]

卷:
54
期数:
2020年第08期
页码:
084-90
栏目:
出版日期:
2020-08-10

文章信息/Info

Title:
Warpage Deformation Prediction of Injection Products with Combinatorial Algorithm
文章编号:
0253-987X(2020)08-0084-07
作者:
王博12 蔡安江1 孟广慧3 李锋2 赵东平2
1.西安建筑科技大学机电工程学院, 710055, 西安; 2.西安航空学院飞行器学院, 710077, 西安; 3.西安航空学院材料工程学院, 710077, 西安
Author(s):
WANG Bo12 CAI Anjiang1 MENG Guanghui3 LI Feng2 ZHAO Dongping2
1. School of Mechanical and Electrical Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China; 2. School of Aircraft, Xi'an Aeronautical University, Xi'an 710077, China; 3. School of Materials Engineering, Xi'an Aeronautical Uni
关键词:
组合算法 翘曲变形 注塑成型
Keywords:
combination algorithm warpage deformation injection molding
分类号:
TH164
DOI:
10.7652/xjtuxb202008011
文献标志码:
A
摘要:
为提高对注塑制品翘曲变形的预测能力,以笔记本电脑电池盖为例,提出采用组合算法对注塑制品翘曲变形进行预测。首先,利用注塑成型模拟软件对电池盖进行9次模拟实验,获得其在工程推荐工艺参数下的翘曲变形量。以此为样本数据,通过最优权值系数将BP神经网络、灰色理论和遗传算法进行有效组合,建立3种组合预测模型,与3种单一预测模型共同对电池盖的翘曲变形量进行预测。其次,根据平方和误差、平均绝对误差和平均相对误差3种预测误差评价指标,对6种预测模型的预测结果进行对比分析。最后,通过电池盖的实际制造验证组合预测方法的准确性。研究结果表明:组合预测模型的准确性优于单一预测模型,其中组合算术平均模型的预测结果与实际测量值最为接近,最大误差不超过5%,能够实现对塑件翘曲变形的准确预测。该预测方法可为注塑制品翘曲变形的预测提供新思路。
Abstract:
To improve the predictive ability of warpage deformation of injection products, a new combination algorithm was proposed taking a notebook battery cover as the example. Simulation experiments were performed nine times on the battery cover using injection molding simulation software to obtain the warpage amount under the recommended engineering process parameters. The sample data, BP neural network, grey theory and genetic algorithm were effectively combined by the optimal weight coefficient to construct three combined forecasting models, together with three single prediction models to predict the warpage amount of the battery cover. Then based on the three kinds of prediction error evaluation indexes, the prediction results of six models were compared and analyzed according to the square sum error, average absolute error and average relative error. Finally, the accuracy of the combinatorial algorithm was verified by the battery cover manufacturing. The results show that the accuracy of the combined prediction model is better than that of single prediction model. The prediction result of the combined arithmetic average model gets the closest to the actual measuring value, and the maximum error is not more than 5%. The proposed combination prediction method can accurately predict the warpage amount of plastic parts.

参考文献/References:

[1] 廖正品. 我国塑料制品行业现状及发展热点分析 [J]. 塑料工业, 2013, 41(S1): 6-15.
LIAO Zhengpin. China's plastic products industry status and development hot spot analysis [J]. China Plastics Industry, 2013, 41(S1): 6-15.
[2] 何芳芳, 周洲, 蒋炳炎. 纤维增强塑料注射成型熔体流动性及纤维取向预测 [J]. 复合材料学报, 2013, 30(S1): 128-133.
HE Fangfang, ZHOU Zhou, JIANG Bingyan. Prediction of melt flowability and fiber orientation for fiber reinforced polymer injection molding [J]. Acta Materiae Compositae Sinica, 2013, 30(S1): 128-133.
[3] 江青松. 纤维增强聚合物复合材料注塑成型理论与实验研究 [D]. 南昌: 南昌大学, 2017: 9-11.
[4] 花少震, 孟凡净. 注塑成型喷射现象的实验及数值研究 [J]. 西安交通大学学报, 2019, 53(9): 88-95.
HUA Shaozhen, MENG Fanjing. Experimental and numerical research on jetting phenomenon during injection molding [J]. Journal of Xi'an Jiaotong University, 2019, 53(9): 88-95.
[5] AHMADI DASTJERDI A, MOVAHHEDY M R, AKBARI J. Optimization of process parameters for reducing warpage in selected laser sintering of polymer parts [J]. Additive Manufacturing, 2017, 18: 285-294.
[6] YIN F, MAO H J, HUA L, et al. Back propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding [J]. Materials & Design, 2011, 32(4): 1844-1850.
[7] SONG Y Y, GANDHI U, PÉREZ C, et al. Method to account for the fiber orientation of the initial charge on the fiber orientation of finished part in compression molding simulation [J]. Composites: Part A Applied Science and Manufacturing, 2017, 100: 244-254.
[8] 唐小我. 组合预测计算方法研究 [J]. 预测, 1991, 10(4): 35-39, 74.
TANG Xiaowo. Study of computing method of combination forecasting [J]. Forecasting, 1991, 10(4): 35-39, 74.
[9] BATES J M, GRANGER C W J. The combination of forecasts [J]. Journal of the Operational Research Society, 1969, 20(4): 451-468.
[10] 杨廷方, 刘沛, 李浙, 等. 应用新型多方法组合预测模型估计变压器油中溶解气体浓度 [J]. 中国电机工程学报, 2008, 28(31): 108-113.
YANG Tingfang, LIU Pei, LI Zhe, et al. A new combination forecasting model for concentration prediction of dissolved gases in transformer oil [J]. Proceedings of the CSEE, 2008, 28(31): 108-113.
[11] 原思聪, 李超, 安峰, 等. 基于组合算法的金属铣削毛刺预测 [J]. 工程设计学报, 2013, 20(1): 39-43.
YUAN Sicong, LI Chao, AN Feng, et al. A metal milling burr prediction based on combination algorithm [J]. Chinese Journal of Engineering Design, 2013, 20(1): 39-43.
[12] 王清洁, 李超, 温强, 等. 组合算法在金属切削力预测中的应用 [J]. 组合机床与自动化加工技术, 2013(12): 14-17.
WANG Qingjie, LI Chao, WEN Qiang, et al. A cutting force prediction based on combination algorithm [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2013(12): 14-17.
[13] PALM F C, ZELLNER A. To combine or not to combine? issues of combining forecasts [J]. Journal of Forecasting, 1992, 11(8): 687-701.
[14] HIBON M, EVGENIOU T. To combine or not to combine: selecting among forecasts and their combinations [J]. International Journal of Forecasting, 2005, 21(1): 15-24.
[15] HE K J, YU L A, LAI K K. Crude oil price analysis and forecasting using wavelet decomposed ensemble model [J]. Energy, 2012, 46(1): 564-574.
[16] 段妮妮. 基于组合预测方法的趋势预测研究与应用 [D]. 成都: 西华大学, 2009: 1-14.
[17] CLAESKENS G, MAGNUS J R, VASNEV A L, et al. The forecast combination puzzle: a simple theoretical explanation [J]. International Journal of Forecasting, 2016, 32(3): 754-762.
[18] 陈华友. 组合预测方法有效性理论及其应用 [M]. 北京: 科学技术出版社, 2008: 126-132.
[19] 钟波, 肖智, 周家启. 组合预测中基于粗糙集理论的权值确定方法 [J]. 重庆大学学报(自然科学版),2002, 25(7): 127-130
ZHONG Bo, XIAO Zhi, ZHOU Jiaqi. Determination to weighting coefficient of combination forecast based on rough set theory [J]. Journal of Chongqing University(Natural Science Edition), 2002, 25(7): 127-130.
[20] 丁智平, 黄达勇, 荣继刚, 等. 长玻纤增强复合材料注塑成型构件强度分析 [J]. 材料工程, 2018, 46(4): 111-119.
DING Zhiping, HUANG Dayong, RONG Jigang, et al. Strength analysis of long glass fiber reinforced composite injection molding components [J]. Journal of Materials Engineering, 2018, 46(4): 111-119.
[21] 马之庚, 陈开来. 工程塑料手册: 材料卷 [M]. 北京: 机械工业出版社, 2004: 111-119.
[22] 张国强. 注塑模设计与生产应用 [M]. 北京: 化学工业出版社, 2007: 29-30.
[23] 王克俭, 曹国荣, 杨光威, 等. 聚碳酸酯光学制品注塑成型的残余应力 [J]. 高分子材料科学与工程, 2018, 34(2): 88-92.
WANG Kejian, CAO Guorong, YANG Guangwei, et al. Residual stress in polycarbonate optical injection molded products [J]. Polymer Materials Science & Engineering, 2018, 34(2): 88-92.

备注/Memo

备注/Memo:
收稿日期: 2020-01-21。作者简介: 王博(1983—),男,讲师,博士生; 蔡安江(通信作者),男,教授。基金项目: 国家自然科学基金资助项目(51475352); 陕西省自然科学基础研究计划资助项目(2019JM-435)。
更新日期/Last Update: 2020-08-10