Skoči na glavni sadržaj

Izvorni znanstveni članak

Tension control system design of a filament winding structure based on fuzzy neural network

Zheng Li ; Hebei University of Science and Technology


Puni tekst: engleski PDF 482 Kb

str. 9-17

preuzimanja: 1.094

citiraj


Sažetak

Filament winding products are widely used due to their quality, high strength and a series of advantages in the industrial areas. The process involves winding filaments under varying amounts of tension over a male mould or mandrel. The tension control product has become the most important object in the process. This study describes the tension force control of filament winding with fuzzy neural network controller design and its application to fiber reinforced plastics. The controller produces the error of the closed loop control system response and the actual system output for the desired tension system, instead of ordinary PID adjustment mechanism. Dynamic performance analysis of a traditional PID controller and fuzzy neural network controller is performed in detail using simulation and experiments. The results show that the system can not only exhibit desired dynamic performance but can also adapt to the wide range of speed and tension force changes by a proper servo motor and winding operation. This study provides the primary theoretical guide for the configuration design, optimization and control research of the FNN applications to industrial winding process.

Ključne riječi

FNN, neural network, control system, tension force, filament winding

Hrčak ID:

133244

URI

https://hrcak.srce.hr/133244

Posjeta: 1.468 *