一种用人工神经网络重建自由曲面的方法

Neural Network Approach to the Reconstruction of Freeform Surfaces

提出一种神经网络方法，用于逆工程中自由曲面的重建。讨论了网络结构、修改的ＢＰ学习算法，并给出了网络重建一个ＮＵＲＢＳ曲面的精度。结果表明该方法可以用来重建已有曲面的数学模型，进而用于加工这些曲面。

The paper presents a neural network approach to the reconstruction of freeform surfaces for reverse engineering. To evaluate the effectiveness of the approach, a mathematically known surface, a nonuniform B-spline surface, was used for generating a number of samples for training the networks. The trained networks then generated a number of new points which were compared with the calculated points using the known surface equations. The networks structure and modified BP algorithm were also discussed. The results show that the approach can be used to reconstruct computer representations of the existing surfaces and to manufacture them. An example is included to illustrate the approach.