在多层布线的线段－相交图模型基础上，利用Ｈｏｐｆｉｅｌｄ人工神经网络理论，通过把通孔数目这个优化目标与Ｈｏｐｆｉｅｌｄ网络能量函数相联系的方法来解决多层布线通孔最小化问题。算法考虑了许多来自实际的约束。结果证明，这是一个有效的算法，且具有较快的收敛速度 Based on the multi-layer line-intersection graph model, Hopfield artificial neural network theory is used to solve the problem of multi-layer wiring via hole minimization by connecting the optimization goal of the hole number with the Hopfield network energy function. The algorithm considers many of the constraints from the actual. The result proves that this is an efficient algorithm and has a faster convergence rate