论文部分内容阅读
涤纶纺丝生产过程中熔体输送环节具有机理复杂、受诸多因素影响、拥有多种产品性能指标等特点,对其进行工艺优化较为困难,目前往往凭借生产经验,缺乏一定的理论指导。熔体输送环节工艺优化是1个多目标优化问题,为此提出了1种智能多目标工艺优化方法:。该方法:采用以Pareto多目标最优理论为优化导向的带精英策略非支配排序遗传算法(NSGA-Ⅱ),并对其进行了一定的改进。改进之处在于,传统的NSGA-Ⅱ算法选择用于计算个体拥挤度的参考点是按各个目标分别进行选择,本文采用了多个目标综合选择法,使拥挤度的计算与筛选更为准确。本文以熔体出口处压强、温度、特性粘度3个指标为优化目标,依据工业现场数据,进行了仿真实验。实验结果:表明,该方法:运算速度较快,优化结果:准确,分布均匀,能够对实际生产的工艺优化起到一定的指导作用。
Due to the complicated mechanism of melt conveying in polyester spinning process, it is affected by many factors and has the characteristics of many kinds of products. It is difficult to optimize its process. Currently, it is lack of theoretical guidance for its production experience. Process optimization of melt transfer is a multi - objective optimization problem, and an intelligent multi - objective process optimization method is proposed. The method adopts the elitist strategy non-dominated ranking genetic algorithm (NSGA-Ⅱ) which is guided by Pareto multi-objective optimization theory and is improved to some extent. The improvement lies in that the traditional NSGA-Ⅱ algorithm selects the reference point for calculating the degree of individual crowding according to each target. In this paper, multiple target comprehensive selection methods are adopted to make the calculation and screening of crowding degree more accurate. In this paper, three indicators of pressure, temperature and intrinsic viscosity at the outlet of the melt are taken as the optimization objectives. According to the industrial field data, the simulation experiments are carried out. The experimental results show that the proposed method has the advantages of fast computing speed, accurate results and even distribution, which can guide the process optimization in practical production.