DR-FNN을 이용한 LMTT Positioning System의 예측 제어

Predictive Control for LMTT Positioning System using DR-FNN

LMTT(Linear Motor-based Transfer Technology)는 항만 컨테이너 이송장치의 자동화 시스템으로 기술적 포화상태에 이른 AGV(Automated Guided Vehicle)의 대체 수단으로 제안되었다. 본 논문에서는 PMLSM(Permanent Magnetic Linear Synchronous Motor)을 기본 구조로 한 LMTT에서 발생할 수 있는 문제인 cogging force와 force ripple 등의 외란에 강인하고, 컨테이너 이적재를 통한 자체 하중의 급격한 변화에 적응성을 갖는 제어기를 설계하고자 한다. 제안된 제어 시스템은 두 개의 DR-FNN (Dynamically-constructed Recurrent Fuzzy Neural Network)를 이용하여 다단예측이 가능하도록 하여 위치 제어시 정밀도와 에너지 효율을 높이고자 한다.

In the maritime container terminal, LMTT(Linear Motor-based Transfer Technology) is horizontal transfer system for the yard automation, which has been proposed to take the place of AGV (Automated Guided Vehicle). The system is based on PMLSM(Permanent Magnetic Linear Synchronous Motor) that is consists of stator modules on the rail and shuttle car(mover). Because of large variant of mover's weight by loading and unloading containers, the difference of each characteristic of stator modules, and a stator module's trouble etc., LMCPS (Linear Motor Conveyance Positioning System) is considered as that the system is changed its model suddenly and variously. In this paper, we will introduce the softcomputing method of a multi-step prediction control for LMCPS using DR-FNN(Dynamically-constructed Recurrent Fuzzy Neural Network). The proposed control system is used two networks for multi-step prediction Consequently, the system has an ability to adapt for external disturbance, cogging force, force ripple, and sudden changes of itself.