DSP-based probabilistic fuzzy neural network control for li-ion battery charger

Faa Jeng Lin, Ming Shi Huang, Po Yi Yeh, Han Chang Tsai, Chi Hsuan Kuan

Research output: Contribution to journalArticlepeer-review

72 Scopus citations

Abstract

A DSP-based probabilistic fuzzy neural network (PFNN) controller to control a two-stage ac-dc charger is proposed in this study. The charger is composed of an ac-dc boost converter with power factor correction and a phase-shift full-bridge dc-dc converter. Moreover, the designed charger adopts a constant-current and constant-voltage (CC-CV) charging strategy to charge lithium-ion battery packs. To improve the transient of voltage regulation during load variation, a PFNN controller is proposed to replace the traditional proportional-integral controller. Furthermore, the discontinuous charging voltage and current during the transition between the CC and CV charging modes can also be reduced significantly using the proposed PFNN controller. The network structure and the online learning algorithms of the PFNN controller are introduced in detail. In addition, the control performances of the proposed PFNN control system for CC-CV charging are evaluated by experimental results.

Original languageEnglish
Article number6148286
Pages (from-to)3782-3794
Number of pages13
JournalIEEE Transactions on Power Electronics
Volume27
Issue number8
DOIs
StatePublished - 2012

Keywords

  • Constant-current (CC) charging
  • constant-voltage (CV) charging DSP
  • phase-shift full-bridge (PSFB)
  • power factor correction (PFC)
  • probabilistic fuzzy neural network (PFNN)

Fingerprint

Dive into the research topics of 'DSP-based probabilistic fuzzy neural network control for li-ion battery charger'. Together they form a unique fingerprint.

Cite this