This paper describes a control system for a tubular synchronous linear motor based on a combination of a linear PID controller and a nonlinear neural network. The nonlinear part of the controller is introduced to progressively augment the tracking performance of the system and is trained online by a compact GA. We implement a variant of a known compact GA that well lends itself to practical implementations in low capacity microcontrollers, thanks to its reduced memory requirements and better distributed computational loads. The potential of the proposed approach is assessed by means of a simulation study on a detailed model of a linear motor. The control system obtained through genetic search outperforms alternative schemes obtained with linear design techniques.

Compact GAs for neural network online training in tubular linear motor control / Cupertino, Francesco; Mininno, E.; Naso, David; Turchiano, Biagio; Salvatore, L.. - In: IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION. - ISSN 1089-778X. - (2007), pp. 1542-1547. (Intervento presentato al convegno IEEE Congress on Evolutionary Computation, CEC 2007 tenutosi a Singapore nel September 25-28, 2007) [10.1109/CEC.2007.4424656].

Compact GAs for neural network online training in tubular linear motor control

CUPERTINO, Francesco;NASO, David;TURCHIANO, Biagio;
2007-01-01

Abstract

This paper describes a control system for a tubular synchronous linear motor based on a combination of a linear PID controller and a nonlinear neural network. The nonlinear part of the controller is introduced to progressively augment the tracking performance of the system and is trained online by a compact GA. We implement a variant of a known compact GA that well lends itself to practical implementations in low capacity microcontrollers, thanks to its reduced memory requirements and better distributed computational loads. The potential of the proposed approach is assessed by means of a simulation study on a detailed model of a linear motor. The control system obtained through genetic search outperforms alternative schemes obtained with linear design techniques.
2007
IEEE Congress on Evolutionary Computation, CEC 2007
978-1-4244-1339-3
Compact GAs for neural network online training in tubular linear motor control / Cupertino, Francesco; Mininno, E.; Naso, David; Turchiano, Biagio; Salvatore, L.. - In: IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION. - ISSN 1089-778X. - (2007), pp. 1542-1547. (Intervento presentato al convegno IEEE Congress on Evolutionary Computation, CEC 2007 tenutosi a Singapore nel September 25-28, 2007) [10.1109/CEC.2007.4424656].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/15199
Citazioni
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact