无芯模旋压成形旋轮加载路径智能优化方法

• Format: Patent
• Language: Chinese
• Published: 19.04.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVINGMATERIAL; PERFORMING OPERATIONS; PHYSICS; PUNCHING METAL; TRANSPORTING; WORKING OR PROCESSING OF SHEET METAL OR METAL TUBES, RODS ORPROFILES WITHOUT ESSENTIALLY REMOVING MATERIAL

本发明属于零件成形制造相关技术领域，公开了一种无芯模旋压成形旋轮加载路径智能优化方法，采用有限元软件，建立无芯模旋压有限元模型、无芯模旋压瞬时成形工况及状态实时提取模型，并获取不同初始工况下瞬时成形工况与瞬时成形状态对应的量化数据；基于量化数据采用深度神经网络建立无芯模旋压不同瞬时成形工况下的旋压成形状态预测模型；采用粒子群优化算法构造粒子群优化算法适应度函数，对瞬时旋轮加载路径优化；最后建立无芯模旋压成形旋轮加载路径优化平台，运行得满足优化目标的旋轮加载路径。本发明用于优化无芯模旋压成形旋轮加载路径，能有效降低旋压成形过程中的凸缘波动程度，避免起皱缺陷的形成，获得目标壁厚减薄率。 The invention belongs to the related technical field of part forming and manufacturing, and discloses a coreless spinning forming spinning roller loading path intelligent optimization method, which adopts finite element software to establish a coreless spinning finite element model and a coreless spinning instantaneous forming working condition and state real-time extraction model, and obtains quantized data corresponding to the instantaneous forming working condition and the instantaneous forming state under different initial working conditions; based on the quantized data, a deep neural network is adopted to establish a spinning forming state prediction model under different instantaneous forming working conditions of