基于人工神经网络技术的板料拉深成形工艺优化的数值建模  

Numerical modeling of parameters optimization of sheet metal forming in drawing process based on artificial neural network

作　　者：潘江峰[1] 钟约先[1] 袁朝龙[1] 罗捷[2] 

机构地区：[1]清华大学机械工程系 [2]西北机电工程研究所,咸阳712099

出　　处：《塑性工程学报》2007年第5期1-4,共4页Journal of Plasticity Engineering

摘　　要：文章利用人工神经网络技术,建立了板料拉深成形工艺参数和性能评价指标之间的映射关系,为各参数的研究和优化提供了重要参考;详细分析了其中的几项关键技术:拉延筋的描述、性能评价指标的建立和正交实验法确定训练样本。最后,对某翼子板进行拉深成形建模,通过对训练后的网络进行测试,网络误差小于5%,验证了所建网络模型的正确性和实用性,为工艺优化奠定了基础。Based on the technique of artificial neural network, a mapping between sheet forming parameters and performance eval- uation indexes was built, which provides important preferences for researching and optimizing these parameters. Several key technologies were analyzed such as description of draw bead, establishing of performance evaluation, and orthogonal experiment. At last a model of a wing was built. According to the test results, the error of the network were less than 5%. That means the network is available, and also it establishes foundation of the process parameters optimization.

关 键 词：人工神经网络 板料拉深 数值建模 数值模拟 

分 类 号：TG386.3[金属学及工艺—金属压力加工]