Abstract
A novel dynamical neuro-fuzzy network (DFNN) is provided based on the forward neuro-fuzzy network ANFIS, which combines the advantages of fuzzy system, neural network and PID algorithm. DFNN is constructed by adding a recurrent layer between the normalized layer and output layer of ANFIS, and backpropogation learning algorithm (BP) is given to DFNN. Compared with ANFIS and PID controller, DFNN has better control results. The parameters of DFNN have the implicite meaning and their initial values can be chosen by the experience of expert which increase the converging speed of network. Because of the dynamical ability of DFNN, it has the stronger ability of handling the dynamical system.
| Original language | English |
|---|---|
| Pages (from-to) | 589-592 |
| Number of pages | 4 |
| Journal | Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology |
| Volume | 20 |
| Issue number | 5 |
| Publication status | Published - 2000 |
Keywords
- Learning algorithm
- Neuro-fuzzy network
- Recurrent system
Fingerprint
Dive into the research topics of 'A novel dynamical neuro-fuzzy network controller'. Together they form a unique fingerprint.Cite this
Liu, C. J., Liao, X. Z., & Zhang, Y. H. (2000). A novel dynamical neuro-fuzzy network controller. Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 20(5), 589-592.