以神经网络为基本工具，利用其强大的非线性映射能力，并结合有限元法动力分析成果，为预测在复合射孔条件下岩层裂缝扩展深度提供了一条新的途径。

By using ANN and its powerful nonlinear mapping ability and combining production of FEM dynamic analysis, a new way to predicting terrane crack depth of complex fire hole is offered.

youdao

综合比较了核机器方法与人工神经网络法的预测效果，同时展示了常规核与复合核的性能对比。

Experiment results show that, kernel machine method is better than artificial neural network, and compound kernel functions is better than common single kernel functions.

youdao

综合比较了核机器方法与人工神经网络法的预测效果，同时展示了常规核与复合核的性能对比。

Experiment results show that, kernel machine method is better than artificial neural network, and compound kernel functions is better than common single kernel functions.

youdao