改进的椭球单元网络及其在故障诊断中的应用

针对椭球单元网络在应用中存在的一些问题，提出了改进措施。这些措施主要围绕改进网络的分类能力和表达能力、合理确定网络结构、避免错误泛化等。通过进行聚类初始化处理和引入有界椭球，改进了BP算法；通过在网络训练过程中引入“节点分裂”和“节点修剪”机制，使得训练后的网络结构更为合理，能适应实际问题的需要；工建议在聚类样本送入网络训练前，先进行PCA处理，以确定更为合理的椭球轴向和降低椭球维数，进一步达到缩短训练时间、增强泛化能力的目的。在CSTR故障诊断中的应用表明：改进的椭球单元网络（BPE）具有任意的非线性分界能力、描述紧邻非线性界面的能力和避免对未知故障类空间进行任意划分的能力。

Improved Ellipsoidal unit Neural Networks and Its Applications in CSTR

To overcome the limitations of the standard ellipsoidal unit neural networks, some new approaches used in ellipsoidal unit neural networks have been proposed. These new approaches address three main issues: firstly, to understand better and represent the nature of fault classification boundaries; secondly, to determine the network structure without the usual trial and error schemes; lastly, to avoid erroneous generalizations. The application in CSTR shows that the ellipsoidal unit networks can possess arbitrary nonlinear classifying ability, nonlinear interfacial describing ability, and obtain accurate and efficient diagnosis results.