采用神经网络方法来建立集装箱角铸件化学成分与力学性能之间的依赖关系 ,继而用这一模型进行检验和预测 ,取得了良好的效果。该方法还可广泛应用于其它金属材料的力学性能与化学成分关系模型的建立 ,为冗长的力学性能表格提供了一种数据压缩技术 The neural network method was used to establish the dependency between chemical composition and mechanical properties of container angle castings, and then the model was used to test and forecast the results. Good results were achieved. The method can also be widely applied to the establishment of the relationship model between the mechanical properties and chemical composition of other metal materials, and provides a data compression technology for the long form of mechanical properties