当使用微分方程时，要对其进行线性化并受限于一定的约束条件才能建立有用的输入-输出关系。
When differential equations are encountered, they are linearized and subjected to whatever constraints are necessary to establish useful input-output relationships.
神经网络的出现为一类输入输出关系呈高度非线性的系统提供了建模的有效工具。
The emergence of neural network provide effective tools for a system with highly nonlinear input-output relations.
母线保护的物理对象是一个输入输出关系确定的函数对象，可用一个ANN模型去替代，或用一个ANN数学模型去逼近母线保护物理对象的输入输出之间的函数关系。
Physical object of bus protection is a function with certain relation between inputs and outputs, which can be replaced by an ANN model, i. e. can be approximated by an ANN mathematical model.
应用推荐