摘要
辊压成形是一种通过顺序排布的成形模具渐近横向弯曲金属带材和板材的塑性加工工艺.由于其低成本、高效率、柔性化的特点,已成为中国新能源、航空航天、轨道交通等多个领域实现轻量化、节能、减排和安全性提升的重要技术之一.但是,该工艺的工序复杂性和离散性、材料厚向性能的不均匀性、设备信息化和柔性化自动化的低水平等问题,导致了它类似于"黑匣子",使得产品质量难以预测,调试生产高度依赖人工经验,可成形截面受限,成品率不稳定.为此,本文提出了一种数据驱动的智能辊压成形装备(系统),并介绍了该装备(系统)的技术架构和特点.通过搭建基于人工智能的数据架构,该系统将传统辊压成形中的离散数据进行采集、筛选、集成、储存和分析.同时融合数字孪生、人工智能、轮廓检测技术和多智能体协同控制等来构建可以替代人工经验的自纠偏的生产模式.针对新能源汽车行业,本文给出了利用该系统解决的一个辊压成形的动力电池包结构件的回弹控制案例,并对该系统的发展给出了建议和展望.
Abstract
Roll forming is a plastic processing technology that gradually bends metal strips and sheets laterally using sequentially arranged forming dies.Due to its low cost,high efficiency,and flexibility,it has become one of the important technologies for lightweighting,energy saving,emission reduction,and safety improvement in various fields such as new energy,aerospace,and rail transportation in China.However,the complexity and discreteness of the process,uneven material thickness properties,and low level of equipment informatization and flexibility automation have made it similar to a"black box",making it difficult to predict product quality,highly dependent on manual experience for production debugging,limited in formable cross-sections,and unstable in yield.Therefore,this paper proposes a data-driven intelligent roll forming equipment(system)and introduces in detail its technical architecture and characteristics.By building a data architecture based on artificial intelligence,this system collects,screens,integrates,stores,and analyzes discrete data in traditional roll forming.Meanwhile,it integrates digital twins,artificial intelligence,contour detection technology,and multi-agent collaborative control to construct a self-correcting production mode that can replace manual experience.For the new energy vehicle industry,this paper provides a case study of using this system to solve springback control of structural components of roll-formed battery packs.Finally,suggestions and prospects for the development of this system are given.
基金项目
深圳市科技创新计划(ZDSYS20210813095534001)
深圳市科技创新计划(JCYJ20210324123202008)
深圳市科技创新计划(JCYJ20210324115412035)
广东省基础与应用基础研究基金(2022A1515010363)
高性能复杂制造国家重点实验室开放课题(Kfkt2021-05)
维普
万方数据