曲面翻边是板料冲压成形的重要工艺。采用数值模拟与人工神经网络相结合的方法,建立了基于BP神经网络的曲面翻边件成形性能预测的数学模型。然后对神经网络进行了训练,并对训练后的网络进行了测试。测试结果与数值模拟的结果比较,验证了该模型的正确性及有效性,能为预测和优化曲面翻边件成形质量提供有效的手段。 Surface flanging is an important process of sheet metal stamping. A mathematical model for predicting the formability of the curved flanges based on BP neural network was established by combining numerical simulation and artificial neural network. Then the neural network was trained, and the network after training was tested. The test results are compared with the numerical simulation results to verify the correctness and validity of the model, which can provide an effective means to predict and optimize the forming quality of the curved flange.