论文信息 - Use of Neutral Networks for on-Line Vibration Monitoring

Use of Neutral Networks for on-Line Vibration Monitoring

Some of the problems involved with monitoring the variable vibration behaviour observed on large turbine generators are described. The uses of neural networks are discussed and an alternative to the more commonly used network is proposed which has a significantly shorter training time. Examples are given of the use of these techniques for studying an oil whirl problem, an intertum fault, and reactive load dependent behaviour.

I W Mayes

[1] Bernard Widrow,et al. 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[2] Q Zhuge,et al. Signature Analysis for Reciprocating Machinery with Adaptive Signal Processing , 1991 .

[3] Sheng Chen,et al. Practical identification of NARMAX models using radial basis functions , 1990 .

[4] Kurt Hornik,et al. Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[5] Sheng Chen,et al. Recursive hybrid algorithm for non-linear system identification using radial basis function networks , 1992 .

[6] Yubao Chen,et al. Machinery condition monitoring by inverse filtering and statistical analysis , 1992 .

[7] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[8] S. Billings,et al. Rational model identification using an extended least-squares algorithm , 1991 .

[9] C. Micchelli. Interpolation of scattered data: Distance matrices and conditionally positive definite functions , 1986 .

[10] Sheng Chen,et al. Parallel recursive prediction error algorithm for training layered neural networks , 1990 .

[11] D. Broomhead,et al. Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .