论文部分内容阅读
研究了神经网络的一典型模型—反向传播(B-P)模型在稀土复氧化物电阻率特性分类中的应用,验证了该方法的可靠性,并与主成分法进行了比较。实验结果与理论分析表明,神经网络方法优于传统的模式识别方法。
The application of a typical model of back propagation neural network (B-P) model in resistivity characterization of rare earth complex oxide is studied. The reliability of the method is verified and compared with the principal component method. Experimental results and theoretical analysis show that the neural network method is superior to the traditional pattern recognition method.