• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2005년도 추계학술대회 논문집
• /
• pp.17-22
• /
• 2005

This paper presents a new adaptive autopilot for ships based on the Adaptive Neural Networks. The proposed adaptive autopilot is designed with some modifications and improvements from the previous studies on Adaptive Neural Networks by Adaptive Interaction (ANNAI) theory to perform course-keeping, turning and track-keeping control. A strategy for automatic selection c! the neural network controller parameters is introduced to improve the adaptation ability and the robustness of new ANNAI autopilot. In Part II of the paper, to show the effectiveness and feasibility of the proposed ANNAI autopilot, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances are presented.

• 한국항해항만학회지
• /
• 제29권9호
• /
• pp.771-776
• /
• 2005

This paper presents a new adaptive autopilot for ships based on the Adaptive Neural Networks. The proposed adaptive autopilot is designed with some modifications and improvements from the previous studies on Adaptive Neural Networks by Adaptive Interaction (ANNAI) theory to perform course-keeping, turning and track-keeping control. A strategy for automatic selection of the neural network controller parameters is introduced to improve the adaptation ability and the robustness of new ANNAI autopilot. In Part II of the paper, to show the effectiveness and feasibility of the proposed ANNAI autopilot, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances will be presented.

• 한국음향학회지
• /
• 제28권8호
• /
• pp.832-842
• /
• 2009

Automatic speech recognition (ASR) has been successfully applied to many real human computer interaction (HCI) applications; however, its performance tends to be significantly decreased under noisy environments. The invention of audio visual speech recognition (AVSR) using an acoustic signal and lip motion has recently attracted more attention due to its noise-robustness characteristic. In this paper, we describe our novel integration scheme for AVSR based on a late integration approach. Firstly, we introduce the robust reliability measurement for audio and visual modalities using model based information and signal based information. The model based sources measure the confusability of vocabulary while the signal is used to estimate the noise level. Secondly, the output probabilities of audio and visual speech recognizers are normalized respectively before applying the final integration step using normalized output space and estimated weights. We evaluate the performance of our proposed method via Korean isolated word recognition system. The experimental results demonstrate the effectiveness and feasibility of our proposed system compared to the conventional systems.

• Journal of Electrical Engineering and Technology
• /
• 제10권5호
• /
• pp.1969-1982
• /
• 2015

The virtual inertia control (VIC) of wind turbine with directly-driven permanent-magnet synchronous generator (D-PMSG) can act similarly to the conventional synchronous generator in inertia response and frequency control, thereby supporting the system frequency stability. However, because the wind speed is inconstant and changeable to a certain extent and the D-PMSG is a complex nonlinear system, there are great difficulties in the virtual inertia optimal control of the D-PMSG. Based on the design principle of the active disturbance rejection control (ADRC), this paper presents a new VIC strategy for the D-PMSG from the perspective of power disturbance suppression in the system. The strategy helps fulfill the power grid disturbance estimation and compensation by means of the extended state observer (ESO) so as to improve the disturbance-resisting performance of the system. Compared with conventional proportional-derivative virtual inertia control (PDVIC), this method, which is of better adaptability and robustness, can not only improve the property of the D-PMSG responding to the system frequency but also reduce the influence of wind speed disturbance. The simulation and experiment results have verified the effectiveness and feasibility of the VIC based on the ADRC.

• Smart Structures and Systems
• /
• 제25권5호
• /
• pp.559-567
• /
• 2020

Vibration at the tip of various flexible manipulators may affect their operation accuracy and work efficiency. To suppress such vibrations, the feasibility of using MFC actuators and sensors is investigated in this paper. Considering the convergence of the famous filtered-x least mean square (FXLMS) algorithm could not be guaranteed while it is employed for vibration suppression of plants with varying secondary path, this paper proposes a new multiple model switching adaptive control algorithm to implement the real time active vibration suppression tests with a new multiple switching strategy. The new switching strategy is based on a cost function with reconstructed error signal and disturbance signal instead of the error signal from the error sensor. And from a robustness perspective, a new variable step-size sign algorithm (VSSA) based FXLMS algorithm is proposed to improve the convergence rate. A cantilever beam with varying tip mass is employed as flexible manipulator model. MFC layers are attached on both sides of it as sensors and actuators. A co-simulation platform was built using ADAMS and MATLAB to test the feasibility of the proposed algorithms. And an experimental platform was constructed to verify the effectiveness of MFC actuators and sensors and the real-time vibration control performance. Simulation and experiment results show that the proposed FXLMS algorithm based multiple model adaptive control approach has good convergence performance under varying load conditions for the flexible cantilever beam, and the proposed FX-VSSA-LMS algorithm based multiple model adaptive control algorithm has the best vibration suppression performance.

• 한국전산구조공학회논문집
• /
• 제21권6호
• /
• pp.597-605
• /
• 2008

본 논문에서는 지진으로부터 구조물을 효과적으로 보호하기 위하여 MR 엘라스토머(MRE)를 이용한 새로운 형태의 스마트 기초격리 시스템을 제안하고, 이에 대한 내진성능을 파악하였다. MRE는 자성물질을 포함한 실리콘 혹은 고무로써 자기장에 의해 강성이 변하는 스마트 재료이다. 기초격리 시스템은 토목 및 건축분야에서 구조물의 내진성능 향상을 위해 가장 널리 쓰이는 장치로 지반과 구조물을 격리시켜 구조물에 가해지는 입력 하중을 감소시켜주는 장치이다. 기존 수동형태의 기초격리 장치는 다양한 입력하중에 대한 적응성이 부족하고 기초격리 장치에서의 과도한 변위 등의 단점이 있는 반면, 새로 제안한 시스템은 제어 가능한 강성범위가 넓어 이를 개선할 수 있다. MRE를 이용한 기초격리 장치의 성능을 확인하기 위하여 기초격리 장치를 도입한 단층 및 5층의 건물에 대해 다양한 역사지진 하중을 이용하여 수치해석을 수행하였다. 수치해석 결과, 제안된 시스템은 기존 수동형태의 시스템에 비해 구조물의 응답 및 기초격리장치의 변위를 감소시키는 데 탁월한 효과가 있음을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4268-4289
• /
• 2020

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It's based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.

• Structural Engineering and Mechanics
• /
• 제24권4호
• /
• pp.463-478
• /
• 2006

The design of structural frameworks for buildings is constantly evolving and is dependent on regional issues such as loading and constructability. One of the most promising recent developments for low to medium rise construction in terms of efficiency of construction, robustness and aesthetic appearance utilises concrete-filled steel tubular sections as the columns in a moment-resisting frame. These are coupled to rigid or semi-rigid connections to composite steel-concrete beams. This paper includes the results of a pilot experimental programme leading towards the development of economical, reliable connections that are easily constructed for this type of frame. The connections must provide the requisite strength, stiffness and ductility to suit gravity loading conditions as well as gravity combined with the governing lateral wind or earthquake loading. The aim is to develop connections that are stiffer, less expensive and easier to construct than those in current use. A proposed fabricated T-stub connection is to be used to connect the beam flanges and the column. These T-stubs are connected to the column using "blind bolts" with extensions, allowing installation from the outside of the tube. In general, the use of the extensions results in a dramatic increase in the strength and stiffness of the T-stub to column connection in tension, since the load is shared between membrane action in the tube wall and the anchorage of the bolts through the extensions into the concrete.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2010년도 추계학술대회 초록집
• /
• pp.90.2-90.2
• /
• 2010

The coated metallic bipolar plates are getting attractive due to their good feasibility of mass production, low contact resistance, high electrical/thermal conductivity, low gas permeability and good mechanical strength comparing with graphite materials. Yet, metallic bipolar plates for polymer electrolyte membrane(PEM) fuel cells typically require coatings for corrosion protection. Other requirements for the corrosion protective coatings include low electrical contact resistance between metallic bipolar plate and gas diffusion layer, good mechanical robustness, low mechanical and fabrication cost. The authors have evaluated a number of protective coatings deposited on stainless steel substrate by electroplating. The coated metallic bipolar plates are investigated with an electrochemical polarization tests, salt dipping tests, adhesion tests for corrosion resistance and then the contact resistance was measured. The results showed that the selective samples electroplated with optimized method, satisfied the DOE target for corrosion resistance and contact resistance, and also were very stabilized in the typical fuel cell environments in the long-term.

• Journal of Communications and Networks
• /
• 제16권1호
• /
• pp.45-55
• /
• 2014

The paper investigates the problem of designing the multiple-antenna relay in a two-way relay network by taking into account the imperfect channel state information (CSI). The objective is to design the multiple-antenna relay based upon the CSI estimates, where the estimation errors are included to attain the robust design under the worst-case philosophy. In particular, the worst-case transmit power at the multiple-antenna relay is minimized while guaranteeing the worst-case quality of service requirements that the received signal-to-noise ratio (SNR) at both sources are above a prescribed threshold value. Since the worst-case received SNR expression is too complex for subsequent derivation and processing, its lower bound is explored instead by minimizing the numerator and maximizing the denominator of the worst-case SNR. The aforementioned problem is mathematically formulated and shown to be nonconvex. This motivates the pursuit of semidefinite relaxation coupled with a randomization technique to obtain computationally efficient high-quality approximate solutions. This paper has shown that the original optimization problem can be reformulated and then relaxed to a convex problem that can be solved by utilizing suitable randomization loop. Numerical results compare the proposed multiple-antenna relay with the existing nonrobust method, and therefore validate its robustness against the channel uncertainty. Finally, the feasibility of the proposed design and the associated influencing factors are discussed by means of extensive Monte Carlo simulations.