http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
GMDP 신경망 알고리즘과 PID 제어기를 이용한 효율적인 PLANT 제어에 관한 연구
장진청,설재훈,장종승,추연규,임영도 동아대학교 공과대학 부설 한국자원개발연구소 1995 硏究報告 Vol.19 No.2
Adapative control theory or parameter tuning of PID controller is mainly limited in linear systems. But in this paper, using a nonlinear mapping capability of NNS, we derive a realtime tuning method of PID controller based on a Back-Propagation method of single GMDP NN. A variety of neural models, especially higher-order networks, are known to computationlly powerful for complex application. While they have advantages over traditional multilayered perceptrons, the uniformity in their network structures, learning algorithms and loop time creates practical problems. Thus this paper evaluates the capability between MLP and GMDP for performing velocity control. Backpropagation is applied to the GMDP as learning rule.