摘要
提出了一种用于多工况对象系统故障检测与分离的模糊方向神经网络．神经网络用模糊集表示故障模式．模糊集是由模糊超体聚集形成的集合体，模糊超体是由单位方向、夹角和两个半径确定．模糊方向神经网络能在一次循环学习中形成非线性方向边界．并不断融合新样本信息和精炼已存在的故障模式．发动机故障检测与分离的仿真研究验证了模糊方向神经网络分类器的优越性能。
A supervised learning fuzzy direction neural network used for fault detection and isolation (FDI) of the multi-condition process of a typical plant is proposed in this paper. Direction neural network utilizes fuzzy sets as fault classes of the plant. Each fuzzy set is an aggregate of fuzzy direction bodies. A fuzzy direction body is described by a direction vector, an included angle and two radii. The fuzzy direction neural network can learn nonlinear direction failure boundaries in a single pass through the training data and provides the ability to incorporate new and refine exisiting failure classes without retraining. The FDI simulation of the engine system demonstrates the strong qualities of the fuzzy direction neural network.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
1997年第3期370-375,共6页
Control Theory & Applications
关键词
故障检测
模糊集
神经网络
方向超体
failure detection and isolation
neural network
fuzzy set
direction body
