金镖,潘毅峰,姚涵非,等.注射成形中的工艺参数自适应优化方法[J].精密成形工程,2025,17(5):220-228.
JIN Biao,PAN Yifeng,YAO Hanfei,et al.A Self-learning Optimization Method for Process Parameters in Electric Driven Injection Molding[J].Journal of Netshape Forming Engineering,2025,17(5):220-228. |
| 注射成形中的工艺参数自适应优化方法 |
| A Self-learning Optimization Method for Process Parameters in Electric Driven Injection Molding |
| 投稿时间：2024-11-20 |
| DOI：10.3969/j.issn.1674-6457.2025.05.024 |
| 中文关键词: 注射成形 工艺优化 梯度估计 自适应优化 |
| 英文关键词: injection molding process optimization gradient estimate adaptive optimization |
| 基金项目:宁波市科技创新2025重大专项(2023Z029);浙江省“尖兵”“领雁”研发攻关计划(2023C01170) |
|
| 摘要点击次数: 48 |
| 全文下载次数: 8 |
| 中文摘要: |
| 目的 针对传统试凑法过于依赖经验、效率低、难以高质量成形的问题，提出工艺参数的自适应优化方法。方法 提出了注射成形初始工艺参数生成方法，包括机器动作参数设定、初步工艺参数设定和优化的初始工艺参数设定。随后，建立了基于梯度估计与优化步长自适应调整的工艺参数自适应优化方法，利用历史批次信息进行了工艺参数优化。以产品质量作为主要评价指标，通过扰动参数实验和迭代优化实验，采集数据并进行分析。结果 初始工艺参数下的产品平均质量为6.178 g，经过优化后，产品质量稳定在5.910 g，相比于初始质量，减轻了4.34%。在迭代优化过程中，产品质量逐渐趋近目标质量，且在优化后的工艺参数下，产品质量保持一致，误差仅为0.010 g。结论 提出的方法能够有效实现注射成形工艺参数的优化，在保证产品充型完整且无缺陷的情况下实现了节约原材料、降低了生产成本。 |
| 英文摘要: |
| The work aims to establish a self-learning optimization method for process parameters in order to solve the problem that the traditional trial-and-error approach relies heavily on experience, has low efficiency and fails to meet the requirements of high-quality molding. A method for generating initial process parameters of injection molding was proposed, including machine parameter setting, preliminary process parameter setting, and initial optimization parameter setting. Furthermore, a self-learning optimization method based on gradient estimation and adaptive adjustment of optimization step size was established. Historical batch information was employed to optimize process parameters. In the experiments, product mass served as the primary evaluation metric. Data were collected and analyzed through perturbation parameter experiments and iterative optimization experiments. The average product weight under the initial process parameters was 6.178 g. After optimization, the mass stabilized at 5.910 g, representing a 4.34% reduction. During the iterative process, the product weight gradually converged to the target value. Under optimized process parameters, the product mass remained consistent with a minimal error of 0.010 g. The proposed method effectively optimizes injection molding process parameters, conserves raw materials, and reduces production costs while ensuring that products are fully filled and defect-free. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501719号