• MALSORI
• /
• no.50
• /
• pp.51-69
• /
• 2004

In this paper, we present a one-pass semi-dynamic network decoding framework that inherits both advantages of fast decoding speed from static network decoders and memory efficiency from dynamic network decoders. Our method is based on the novel language model network representation that is essentially of finite state machine (FSM). The static network derived from the language model network [1][2] is partitioned into smaller subnetworks which are static by nature or self-structured. The whole network is dynamically managed so that those subnetworks required for decoding are cached in memory. The network is near-minimized by applying the tail-sharing algorithm. Our decoder is evaluated on the 25k-word Korean broadcast news transcription task. In case of the search network itself, the network is reduced by 73.4% from the tail-sharing algorithm. Compared with the equivalent static network decoder, the semi-dynamic network decoder has increased at most 6% in decoding time while it can be flexibly adapted to the various memory configurations, giving the minimal usage of 37.6% of the complete network size.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.118-127
• /
• 2015

This paper presents an advanced torque ripple minimization method of a switched reluctance motor (SRM) using torque sharing function (TSF). Generally, TSF is applied into the torque control. However, the conventional TSF cannot follow the expected torque well because of the nonlinear characteristics of the SRM. Moreover, the tail current that is generated at a high speed motor drive makes unexpected torque ripples. The proposed method combined TSF with fuzzy logic control (FLC). The advantage of this method is that the torque can be controlled unity at any conditions. In addition, the controller can track the torque under the condition of the wrong TSF. The effectiveness of the proposed algorithm is verified by the simulations and experiments.