• Journal of Advanced Marine Engineering and Technology
• /
• 제20권4호
• /
• pp.11-19
• /
• 1996

Recently, fuzzy and neural network techniques have been successfully applied to control of complex and ill-defined system in a wide variety of areas, such as robot, water purification, automatic train operation system and automatic container crane operation system, etc. In this paper, we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feedforward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand, feedforward neural networks provide salient features, such as learning and parallelism. In the proposed neuro-fuzzy controller, the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error backpropagation algorithm as a learning rule, while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally, the effectiveness of the proposed controller is verified through computer simulation of an inverted pendulum system.

• Journal of Power Electronics
• /
• 제5권1호
• /
• pp.1-10
• /
• 2005

This paper presents the application of a simple neuro-based speed control scheme of a permanent magnet (PM) dc motor. To validate its efficiency, the performance characteristics of the proposed simple neuro-based scheme are compared with those of a Neural Network controller and those of a Fuzzy Logic controller under different operating conditions. The comparative results show that the simple neuro-based speed control scheme is robust, accurate and insensitive to load disturbances.

• 한국해양생명과학회지
• /
• 제9권1호
• /
• pp.9-21
• /
• 2024

마비성 패류 독소(Paralytic shellfish poisoning, PSP)는 유해 조류에 의해 생성되며, 독소에 노출된 수산물을 섭취하였을 때 중독이 발생한다. 수산물 중 PSP를 검출하는 표준 시험법인 Mouse bioassay (MBA)는 낮은 검출한계와 동물 윤리 문제로 대체 시험법의 개발 필요성이 대두되고 있다. 이러한 대체 시험법 중, PSP가 신경 세포막의 Na⁺ 채널을 차단하는 기전을 이용한 마우스 뇌신경 모세포종 세포 기반 시험법(Neuro-2a assay)의 표준화를 위한 노력이 대두되고 있다. Neuro-2a assay의 원리는 Neuro-2a 세포주에 Na⁺/K⁺ ATPase 억제제인 Ouabain(O)과 Na⁺ 채널 활성화제인 Veratridine (V)을 처리하여 과도한 Na⁺ 유입으로 인한 세포사멸을 유도한 상태에서, Na⁺ 채널 억제제인 PSP를 처리하게 되면 Na⁺ 유입이 차단되어 세포가 생존하는 것을 측정하는 것이다. 본 연구에서는 PSP 검출을 위한 Neuro-2a assay를 국내 연구 환경에 맞게 다양한 매개변수를 개선하여 최적 시험법을 확립하고자 하였다. 고려한 매개변수들은 세포밀도, 배양 조건 및 PSP 처리 조건 등으로, 그 결과는 아래와 같다. 초기 세포밀도는 40,000 cells/well로, 세포 배양시간 및 처리시간은 각각 24시간으로 설정하였다. 또한 최적 O/V 농도는 500/50 μM로 설정하였다. 본 연구에서 PSP 중 Saxitoxin (STX)에 대해서 O/V 처리가 된 상태에서 S자형 용량-반응 그래프가 도출되는 8가지 농도(368~47,056 fg/μl)를 확인하였고, Neuro-2a assay의 실험실 간 변동성 비교를 통해, 실험의 적정성 확인을 위한 5가지 Quality Control Criteria와 실험 데이터의 신뢰가능 범위(Data Criteria) 6가지를 설정하였다. 확 립된 조건으로 Neuro-2a assay를 진행한 결과 반수영향농도(EC₅₀) 값은 약 1,800~3,500 fg/μl로 나타났다. 실험실 간 변동성 비교 결과, Quality Control Criteria 값 및 Data criteria 값의 변동계수(coefficients of variation (CVs))가 1.98~29.15% 범위로 산출되어 실험의 적정성 및 재현성이 확인되었다. 본 연구를 통해 우리나라에서 활용할 수 있는 PSP 검출용 Neuro-2a assay 시험법의 최적 조건 및 5가지 Quality control 기준을 제시하였고, PSP 중 대표적인 독소인 STX을 대상으로 Neuro-2a assay를 실시한 결과 유의한 EC₅₀ 값을 산출할 수 있었으며, 향후 국내 수산물을 대상으로 MBA를 대체할 수 있는 PSP 검출법으로 활용될 것으로 기대된다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1999년도 추계학술대회 논문집 - 한국공작기계학회
• /
• pp.162-169
• /
• 1999

In this paper, it is presented a new scheme of adaptive-neuro control system to implement real-time control of robot manipulator using digital Signal Processors. Digital signal processors DSPs. are micro-processors that are particularly developed for variables. Digital version of most advanced control algorithms can be defined as sums and products of measured variables, thus it can be programmed and executed through DSPs. In addition, DSPs are as fast in computation as most 32-bit micro-processors and yet at a fraction of their prices. These features make DSPs a biable computatinal tool in digital implementation of sophisticated controllers. Unlike the well-established theory for the adaptive control of linear systems, there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of robot control. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method. The proposed adaptive-neuro control scheme is illustrated to be a efficient control scheme for implementation of real-time control of robot system by the simulation and experiment.

• Journal of Advanced Marine Engineering and Technology
• /
• 제24권2호
• /
• pp.72-81
• /
• 2000

In this paper, we design an adaptive neuro-fuzzy inference system(ANFIS) precompensator for load frequency control of 2-area power systems. While proportional integral derivative (PID) controllers are used in power systems, they may have some problems because of high nonlinearities of the power systems. So, a neuro-fuzzy-based precompensation scheme is incorporated with a convectional PID controller to obtain robustness to the nonlinearities. The proposed precompensation technique can be easily implemented by adding a precompensator to an existing PID controller. The applied neruo-fuzzy inference system precompensator uses a hybrid learning algorithm. This algorithm is to use both a gradient descent method to optimize the premise parameters and a least squares method to solve for the consequent parameters. Simulation results show that the proposed control technique is superior to a conventional Ziegler-Nichols PID controller in dynamic responses about load disturbances.

• 한국생산제조학회지
• /
• 제22권2호
• /
• pp.256-262
• /
• 2013

This paper presents a linear path control algorithm for NeuroMate robot in a skull drilling system. For the path control inverse kinematics of the robot is analyzed and a linear interpolation algorithm is presented. A geometric approach is used for solving inverse kinematic equations for the robot. Four feasible solutions are found through the approach. The approach gives geometric insights for selecting the best solution from the feasible solutions. The presented linear interpolation algorithm computes a next position considering current velocity and remaining distance to the target position. Presented algorithm is implemented and tested in a skull drilling system.

• Journal of Advanced Marine Engineering and Technology
• /
• 제28권2호
• /
• pp.228-236
• /
• 2004

In this paper. we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feed forward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand. feed forward neural networks provide salient features. such as learning and parallelism. In the proposed neuro-fuzzy controller. the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error back propagation algorithm as a learning rule. while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally. the effectiveness of the proposed controller is verified through computer simulation for an inverted pole system.

• 한국정보통신학회논문지
• /
• 제25권11호
• /
• pp.1495-1504
• /
• 2021

초소형 바이너리 발전 플랜트는 열원과 냉각원 사이의 저온도차 열에너지를 이용하여 열에너지를 전력으로 변환한다. 실제 발전환경에서 플랜트의 특성치는 환경 조건이나 관련 장비의 부식과 같은 부정적인 영향으로 인해 변동하고, 플랜트 특성치의 변동은 PID 파라미터가 고정된 종래의 PID 제어시스템에서 불안정한 터빈 출력으로 이어진다. 본 논문에서는 플랜트의 특성치 변동에 따라 PID 파라미터를 적응적으로 조정하는 신경망 기반의 Neuro PID 제어시스템을 제안한다. 초소형 바이너리 발전 플랜트의 동작점 근방에서 동특성을 나타내는 이산시간 전달함수 모델을 도출하고, 제안된 제어시스템의 설계 전략을 기술한다. 제안된 Neuro PID 제어시스템을 종래의 PID 제어시스템과 비교하고, 시뮬레이션 결과를 통해 그 유효성을 보인다.

• 조명전기설비학회논문지
• /
• 제16권5호
• /
• pp.104-111
• /
• 2002

본 논문에서는 EM(Expectation-Maximization) 알고리즘을 이용한 자동적인 퍼지 규칙생성과 적응 뉴로-퍼지 제어기(Adaptive Neuro-Fuzzy Controller)의 설계를 제안한다. EM 알고리즘은 가우시안 혼합모델(Gaussian Mixture Model)의 최대우도추정(Maximum Likelihood Estimate)을 위해 사용되어지며 본 논문에서는 규칙생성을 위해 클러스터 중심을 추정한다. 추정된 클러스터는 ANFIS(Adaptive Neuro-Fuzzy Inference System)의 퍼지 규칙과 소속함수를 구축하는데 사용되어진다. 시뮬레이션으로 제안된 적응 뉴로-퍼지 제어기의 성능을 입증하기 위해 목욕물 온도 제어 시스템에 대해 다루고 기존 퍼지 제어기에 비해 적은 규칙의 수와 작은 값의 SAE(Sum of Absolute Error)으로 성능개선을 확인하였다.

• Smart Structures and Systems
• /
• 제15권4호
• /
• pp.931-947
• /
• 2015

This paper focuses on the design of an intelligent control system. The used techniques are based on Neuro Fuzzy approaches applied to a magnetorheological damper in order to reduce the vibrations over footbridges; it has been applied to the Science Museum Footbridge of Valladolid, particularly. A model of the footbridge and of the damper has been built using different simulation tools, and a successful comparison with the real footbridge and the real damper has been carried out. This simulated model has allowed the reproduction of the behaviour of the footbridge and damper when a pedestrian walks across the footbridge. Once it is determined that the simulation results are similar to real data, the control system is introduced into the model. In this sense, different strategies based on Neuro Fuzzy systems have been studied. In fact, an ANFIS (Artificial Neuro Fuzzy Inference System) method has also been used, in addition to an alternative Neuro Fuzzy approach. Several trials have been carried out, using both techniques, obtaining satisfactory results after using these techniques.