For the process parameter design problem of an MIMO production process, many researchers have developed and employed different optimization schemes for determining the optimal design and process parameters for polymer processing [18–21]. However, for many MIMO production processes, the researchers usually make the multi-objective problems into single-objective optimization problems and apply ANN and evolutionary algorithms to attain the final optimal process parameter settings. In the studies mentioned above, Deng et al. [18] applied GA to optimize injection molding process conditions with user-definable objective functions. They implemented a modified simple weighting method to deal with multi-objective optimization, in which the objective functions can be defined with different criteria and/or weight vectors according to the designers’ preference. Huang et al. [19] presented an approach for determining parameter values in melt spinning processes to yield optimal qualities of denier and tenacity in as-spun fibers. The experimental data determined by an orthogonal array in the Taguchi method are adopted to train a neural network by an analysis of variance. The genetic algorithm is aimed at finding parameter values in a continuous solution space to optimize a performance measure on denier and tenacity qualities, based on the neural network. Hsu et al. [20] presented an integrated approach using neural networks, exponential desirability functions, and genetic algorithms to optimize parameter design problems with multiple responses. The proposed approach aims to identify the input parameter settings to maximize the overall minimal satisfaction level with respect to all the responses. In their optimization procedure, the trade-off solutions obtained by using the predefined strategy would be sensitive to the weight factors chosen in converting the multi-objective to a single objective function. Castro et al. [21] used an approach comprising computer simulation, ANN, and data envelopment analysis to determine the proper operating conditions for finding the best compromise among several conflicting performance measures. The approach they presented also allowed for the identification of robust variable settings that might help to define a starting point for negotiation between multiple decision makers.
摘要:在塑料注塑行业确定最优工艺参数的设置对生产率、质量和生产成本有重要影响。选择适当的工艺条件进行注塑过程视为一个多目标优化问题,不同的目标,比如减少产品重量,体积收缩,或flash实时交换行为。因此,不同的最适条件可能存在于客观的空间。本文介绍了开发一个基于实验优化系统参数优化过程的多输入多输出塑料注射成型工艺。开发集成了田口方法的参数设计方法,基于PSO(桑昂模型)神经网络,多目标粒子群优化算法、工程优化的概念,并自动搜索的帕累托最优解决方案不同的目标。根据演示应用程序,研究结果表明,该方法能有效地帮助工程师确定最佳工艺条件,实现具有竞争优势的产品质量和小的成本。
关键词塑料注射成型，bp神经网络，粒子群算法，多目标，优化。 塑料注塑工艺英文文献和翻译(3):http://www.youerw.com/fanyi/lunwen_3625.html