This paper investigates the problem of ship course control in the presence of model uncertainties, external disturbances, and actuator saturation. A high-performance autopilot is developed based on a direct neural network adaptive dynamic surface control (DSC) framework integrated with deep reinforcement learning. To compensate for lumped uncertainties arising from unmodeled dynamics and disturbances, a radial basis function (RBF) neural network is employed to provide online approximation within the control design. Moreover, the actuator saturation constraint is explicitly incorporated into the controller, avoiding performance degradation commonly encountered in conventional DSC schemes.To alleviate the reliance on manual parameter tuning, the controller parameter adaptation is formulated as a continuous-action optimization problem and solved using a deep deterministic policy gradient (DDPG) algorithm. The DDPG agent learns an optimal tuning policy by maximizing a reward function that penalizes course tracking errors, excessive control variations, and energy consumption. Simulation results demonstrate that the proposed method achieves improved tracking accuracy, smoother control inputs, and enhanced robustness under complex operating conditions, thereby validating the effectiveness of the DDPG-based adaptive tuning strategy for autonomous ship navigation.

This paper investigates the problem of ship course control in the presence of model uncertainties, external disturbances, and actuator saturation. A high-performance autopilot is developed based on a direct neural network adaptive dynamic surface control (DSC) framework integrated with deep reinforcement learning. To compensate for lumped uncertainties arising from unmodeled dynamics and disturbances, a radial basis function (RBF) neural network is employed to provide online approximation within the control design. Moreover, the actuator saturation constraint is explicitly incorporated into the controller, avoiding performance degradation commonly encountered in conventional DSC schemes.To alleviate the reliance on manual parameter tuning, the controller parameter adaptation is formulated as a continuous-action optimization problem and solved using a deep deterministic policy gradient (DDPG) algorithm. The DDPG agent learns an optimal tuning policy by maximizing a reward function that penalizes course tracking errors, excessive control variations, and energy consumption. Simulation results demonstrate that the proposed method achieves improved tracking accuracy, smoother control inputs, and enhanced robustness under complex operating conditions, thereby validating the effectiveness of the DDPG-based adaptive tuning strategy for autonomous ship navigation.

Aiming at the control problem of nonlinear uncertain systems with asymmetric saturated actuators and u nknown external disturbances, a composite control method integrating dynamic surface control (DSC), ad aptive neural network estimation, and a nonlinear saturation compensation mechanism is proposed. In the scenarios of ship course and trajectory tracking, the system faces multiple challenges such as symmetric and asymmetric actuator saturation, as well as unknown external disturbances. Radial basis function (R BF) neural networks are utilized for online approximation of unknown nonlinear functions and external d isturbances. Combined with dynamic surface technology, the problem of "explosion of complexity" in tra ditional backstepping control is eliminated. A nonlinear function with inverse correlation to error gain is designed to dynamically adjust the control gain, balancing the requirements of tracking accuracy and sat uration suppression. Furthermore, a Gaussian error function is introduced to construct a continuously diff erentiable asymmetric saturation model. An auxiliary dynamic system is integrated to compensate for the saturation nonlinear effect, achieving smooth amplitude limitation of rudder angle commands. Comparati ve MATLAB simulation results demonstrate that the course tracking error is reduced by 1°, the fluctuati on amplitude of the rudder angle is decreased by approximately 50%, the number of rudder angle satura tion events is reduced by about 60%, and the error convergence time is shortened by roughly 30%. The proposed composite control method effectively addresses the issues of asymmetric saturation and externa l disturbances, significantly enhancing the accuracy and robustness of the ship course control system.

To address the issue of low heading tracking efficiency caused by nonlinear dynamic characteristics in ship heading motion, this paper proposes a neural network-based adaptive hyperbolic tangent control method for ship heading. By designing a second-order system robust controller, a saturated auxiliary design system is introduced into the regulator for direct internal compensation, enhancing the system's anti-interference capability under complex operating conditions. Meanwhile, hyperbolic tangent nonlinear modification is incorporated into the control strategy to optimize the output characteristics of control signals. The controller adopts a backstepping approach to design virtual control laws for trajectory tracking and utilizes the Radial Basis Function (RBF) of neural networks to approximate the uncertain parts of the ship model. The control algorithm is simulated and tested in the MATLAB environment, and its tracking effect is analyzed. Simulation results show that the control algorithm can ensure the stability of the closed-loop system under conditions of dynamic changes in system parameters, external disturbances, and uncertainties, and effectively solve the nonlinear problems in ship traffic control during trajectory tracking. The controller is designed concisely, meets the requirements of engineering practice, improves ship maneuverability, and has reference value for ship control.

Conventional fixed-time traffic signal operations at urban intersections are typically based on prescheduled plans that presume stable and recurring traffic patterns, particularly during peak commuting hours. However, recent societal changes—including flexible work schedules, telecommuting, and evolving workweek structures—have introduced greater variability in traffic demand, thereby diminishing the effectiveness of traditional peak-hour-focused control strategies. This study investigated the performance of an AI-based adaptive traffic signal control system that operated independently of predefined time plans. A field demonstration was conducted in Jeju City, South Korea, where the system was deployed in both the cyclic and acyclic operation modes. By leveraging real-time traffic data obtained from AI-enabled video detectors, the system adjusted the signal timings on a per-second basis in response to dynamic traffic conditions. The performance was evaluated against the conventional time-of-day (TOD) control method under diverse traffic scenarios, including typical weekdays, weekends, and local event days. The AI-based system achieved substantial reductions in intersection delays—24.3% on weekdays, 22.2% on weekends, and 17.1% on event days—compared with the TOD baseline. Moreover, it preserved a comparable level of traffic progression (measured by the proportion of non-stop vehicle flows) even during acyclic operations. The greatest efficiency gains were observed during the nighttime and low-traffic periods, underscoring the capacity of the system to minimize unnecessary delays under variable conditions. These results highlighted the potential of AI-based adaptive signal control as a viable alternative to conventional fixed-time operations, offering enhanced responsiveness and operational flexibility in increasingly complex urban traffic environments. Future research will focus on scaling the system to larger networks and developing integrated optimization strategies across multiple intersections.

In this study, we propose an adaptive traffic control method that utilizes predictions of near-future traffic arrivals at a signalized intersection based on real-time data collected at an upstream intersection to design acyclic traffic signal timing accordingly. The proposed adaptive control method utilizes a deep learning model developed in this study to predict future traffic arrivals at downstream intersections 24 s ahead based on upstream intersection data at 4 s decision intervals. Using the predicted arrival traffic volume, signal timings were designed to minimize delays. A rolling-horizon approach was employed to correct the prediction errors during this process. The performance of the proposed traffic signal control method was validated by comparing it with the traditional time-of-day (TOD) traffic signal operation method over a 24 h period. The results of comparative validation tests conducted through simulations in a virtual environment indicate that the proposed adaptive traffic control system operates efficiently to minimize average control delays. During the morning peak period, a reduction time of 43.19 s per vehicle (57.02%) was observed, whereas the afternoon peak period exhibited a reduction of 37.91 s per vehicle (48.35%). Additionally, data analysis revealed that the optimal phase length suggested by the pre-timed method, which assumes uniform vehicle arrivals, is statistically identical at a 95% confidence level to the average phase length of the adaptive traffic control system, which assumes random vehicle arrivals. This study confirms the necessity of adopting proactive real-time signal control systems that utilize a new traffic information collection method to respond to dynamic traffic conditions and move away from conventional TOD signal operation, which primarily focuses on peak commuting hours. Additionally, it confirms the need for a fundamental shift in the underlying philosophy traditionally used in traffic signal design

기존 신호제어기법은 과거 주기에 파악된 교통상황을 바탕으로 다음 주기의 교통신호시간을 설계하는 방식으로 신호시간을 설계하기 위해 관측할 때의 교통상황과 신호시간을 제공받는 교통상황 간의 간극이 존재하였다. 또한, 설정된 주기길이 동안 차량이 교차로에 일정하게 도착하는 균일분포를 가정하지만, 실제 교차로에 도착하는 교통량의 행태는 비 균일분포로 실제 교통수요에 대응하기 어렵 다는 한계가 존재한다. 본 연구는 이러한 한계를 극복하기 위해 교차로로 진입하는 상류 교차로의 교통정보를 활용하여 단기 미래 도 착 교통량 예측모델 개발을 통해 관측 시점과 제공 시점 간의 간극을 최소화한다. 또한, 기존 주기길이 동안의 교통량 도착분포를 비 균일분포로 가정하여 주기길이가 고정되지 않는 방식(Acyclic)의 적응식 신호제어 기법(ATC) 개발한다. 제안된 단기 미래 도착 교통 량 예측모델은 실제 스마트교차로 자료를 가공하여 시뮬레이션을 통하여 학습데이터를 구축하여 장단기 메모리(LSTM) 모형과 시간 분산(TimeDistributed) 모형을 적용하여 딥러닝 모델을 개발하였다. 적응식 교통신호제어 기법은 실시간 예측 교통량을 활용하여 교통 류별 예측 지체 산출을 통하여 지체가 최소화되는 현시 종료 지점에서 현시를 종료하고 다음 시간 단계에서 예측된 교통량을 통해 최 적 현시를 재산출하는 롤링 호라이즌(Rolling Horizon)을 수행한다. 제안 신호제어 기법의 평가를 위해 미시적 교통 시뮬레이션을 활 용하여 기존 신호제어 기법인 TOD 신호제어 기법과 제안기법 간의 평가를 수행하였다.

This study explores the course tracking control problem of unmanned surface vessels (USVs) under the influence of actuator faults and internal and external uncertainties. In the control strategy desig n, we first model the unknown dynamics and use adaptive technology to construct an online appro ximator to compensate for the unknown dynamics of the system. Under the framework of adaptive backstepping, a robust adaptive course tracking control scheme is constructed. This control strategy does not require any prior knowledge of the model in advance. The stability analysis of the theoret ical mathematical derivation of the control strategy was conducted based on Lyapunov stability theo ry. Finally, the effectiveness of the control strategy proposed in this paper was verified through sim ulation.

본 연구에서는 운전 시뮬레이션을 이용하여 적응형 정속 주행(adaptive cruise control: ACC) 시스템에 대한 운전자의 신뢰 및 도로 혼잡도가 운전자의 작업부하와 상황인식에 미치는 효과를 알아보았다. ACC 시스템에 대한 운전자의 신뢰는 ACC 시스템이 정상 작동하는 조건과 시스템이 오작동하는 조건을 통해 신뢰상승 집단과 신뢰감소 집단으로 구분하였다. 도로 혼잡도는 운전자 차량 주변의 차량 수로 수준을 조작하였다. ACC 시스템에 대한 신뢰와 도로 혼잡도를 달리한 네 가지의 실험 조건 각각에 대해 운전자들의 작업부하와 상황인식을 측정하였다. 본 연구의 결과를 요약하면 다음과 같다. 먼저 ACC 시스템에 대한 신뢰감소 집단은 신뢰상승 집단에 비해 이 시스템의 사용으로 인한 운전부담 경감이나 안전운전 확보 등을 포함한 측정 항목 모두에서 시스템에 대한 신뢰 점수가 유의하게 더 낮았다. 둘째, ACC 시스템에 대한 신뢰감소 집단은 신뢰상승 집단에 비해 이차과제에서 더 느린 반응시간을 보였고, 시스템 사용에서의 주관적인 작업부하 수준도 더 높게 평정하였다. 셋째, 이와는 대조적으로 운전자들의 운전상황에 대한 상황인식은 ACC 시스템 신뢰감소 집단이 신뢰상승 집단보다 유의하게 더 우수하였다. 본 연구의 결과들은 ACC 시스템에 대한 신뢰가 운전 중에 수행하는 다양한 정보처리에 영향을 미칠 수 있음을 보였는데, 이것은 자동화된 운전보조 시스템의 설계에서 사용자의 시스템에 대한 신뢰가 중요한 변인으로 고려되어야 한다는 것을 시사한다.

This paper investigates to design a controller for maritime autonomous surface ship (MASS) by means of adaptive super-twisting algorithm (ASTA). A input-out feedback linearization method is considered for multi-input multi-output (MIMO) system. Sliding Mode Controller (SMC) is suitable for MASS subject to ocean environments due to its robustness against parameter uncertainties and disturbances. However, conventional SMC has inherent disadvantages so-called, chattering phenomenon, which resulted from the high frequency of switching terms. Chattering may cause harmful failure of actuators such as propeller and rudder of ships. The main contribution of this work is to address an appropriate controller for MASS, simultaneously controls surge and yaw motion in severe step inputs. Proposed control mechanism well provides convergence bewildered by external disturbances in the middle of steady-state responses as well as chattering attenuation. Also, the adaptive algorithm is contributed to reducing non-overestimated value of control gains. Control inputs of surge and yaw motion are displayed by smoother curves without excessive control activities of actuators. Finally, no overshoot can be seen in transient responses.

이 논문에서는 다중 재난을 고려한 복합 구조제어 시스템의 최적 설계방법을 제시한다. 한 가지 유형의 위험에 대해 하나의 시스템이 설계되는 전형적인 구조제어 시스템과는 달리, 구조물의 지진 및 바람에 의한 진동응답을 저감하기 위해 능동 및 수동제어 시스템에 대한 동시 최적 설계방법을 제안하였다. 수치 예로서, 30층 빌딩 구조물에 설치된 30개의 점성 댐퍼와 복합형 질량 감쇠기에 대한 최적 설계문제를 보였다. 최적화 문제를 풀기 위해 자체적응 화음탐색(harmony search, HS)알 고리즘을 채택하였다. 화음탐색 알고리즘은 사람이 연주하는 악기의 튜닝 과정을 모방한 전역 최적화를 위한 메타 휴리스틱 진화 연산방법의 하나이다. 또한 전역 탐색 및 빠른 수렴을 위해 자가적응적이고 동적인 매개변수 조정 알고리즘을 도입하였다. 최적화 설계 결과, 능동 및 수동 시스템이 독립적으로 최적화된 표준적인 복합제어 시스템에 비해 제안한 동시 최적제어 시스템의 성능과 효율성이 우수함을 보였다.

A connected control method for the adjacent buildings has been studied to reduce dynamic responses. In these studies, seismic loads were generally used as an excitation. Recently, multi-hazards loads including earthquake and strong wind loads are employed to investigate control performance of various control systems. Accordingly, strong wind load as well as earthquake load was adopted to evaluate control performance of adaptive smart coupling control system against multi-hazard. To this end, an artificial seismic load in the region of strong seismicity and an artificial wind load in the region of strong winds were generated for control performance evaluation of the coupling control system. Artificial seismic and wind excitations were made by SIMQKE and Kaimal spectrum based on ASCE 7-10. As example buildings, two 20-story and 12-story adjacent buildings were used. An MR (magnetorheological) damper was used as an adaptive smart control device to connect adjacent two buildings. In oder to present nonlinear dynamic behavior of MR damper, Bouc-Wen model was employed in this study. After parametric studies on MR damper capacity, optimal command voltages for MR damper on each seismic and wind loads were investigated. Based on numerical analyses, it was shown that the adaptive smart coupling control system proposed in this study can provide very good control performance for Multi-hazards.

A robust adaptive control approach is proposed for underactuated surface ship linear path-tracking control system based on the backstepping control method and Lyapunov stability theory. By employing T-S fuzzy system to approximate nonlinear uncertainties of the control system, the proposed scheme is developed by combining “dynamic surface control” (DSC) and “minimal learning parameter” (MLP) techniques. The substantial problems of “explosion of complexity” and “dimension curse” existed in the traditional backstepping technique are circumvented, and it is convenient to implement in applications. In addition, an auxiliary system is developed to deal with the effect of input saturation constraints. The control algorithm avoids the singularity problem of controller and guarantees the stability of the closed-loop system. The tracking error converges to an arbitrarily small neighborhood. Finally, MATLAB simulation results are given from an application case of Dalian Maritime University training ship to demonstrate the effectiveness of the proposed scheme.

A shared tuned mass damper (STMD) was proposed in previous research for reduction of dynamic responses of the adjacent buildings subjected to earthquake loads. A single STMD can provide similar control performance in comparison with two traditional TMDs. In previous research, a passive damper was used to connect the STMD with adjacent buildings. In this study, a smart magnetorheological (MR) damper was used instead of a passive damper to compose an adaptive smart STMD (ASTMD). Control performance of the ASTMD was investigated by numerical analyses. For this purpose, two 8-story buildings were used as example structures. Multi-input multi-output (MIMO) fuzzy logic controller (FLC) was used to control the command voltages sent to two MR dampers. The MIMO FLC was optimized by a multi-objective genetic algorithm. Numerical analyses showed that the ASTMD can effectively control dynamic responses of adjacent buildings subjected to earthquake excitations in comparison with a passive STMD.

본 연구에서는 유비쿼터스 식물공장의 재배환경에 필요한 요소들의 센서 네트워크를 구성하고 자동으로 감지하여 적응형 뉴로-퍼지 추론시스템을 통하여 환경변화를 추론하여 식물공장의 재배환경을 적절하게 제어할 수 있는 새로운 자동제어시스템의 프레임워크를 제안하고, 이를 설계하였다. 유비쿼터스 식물공장 환경을 제어하기 위하여 식물공장의 재배환경에 영향을 미치는 환경요소인 실내온도, 근권온도, 습도, 광도, CO2 농도를 측정할 수 있는 센서 네트워크를 구성하고 측정된 환경요소의 변화에 따라 램프, 환기, 습도, CO2 농도, 온도를 제어할 수 있는 장치를 자동으로 제어할 수 있는 식물공장 자동제어시스템을 설계하였다. 이를 위하여 본 연구에서는 센서를 통하여 받아들이는 입력값을 퍼지소속함수로 변화하고 적응형 뉴로-퍼지시스템에 따라 추론하고 평가하여 보다 정밀하게 식물공장을 자동으로 제어할 수 알고리즘을 개발하였고 이를 구현하였다. 개발된 자동제어시스템을 상추 식물공장에 적용한 결과 만족스러운 시험결과를 얻을 수 있었다. 향후 연구로는 식물공장에서 재배하고 있는 작물별 생장모델의 적합도 검정 및 개선을 위하여, 작물별 재배규칙을 보다 상세히 도출하는 것이 필요하고, 작물의 재배에 필요한 지식을 보다 정량적으로 표현하고 지식상에 내포하고 있는 불확실성을 해결하는 것이 필요하다. 더 나아가 식물공장에서 환경인자간의 상호관련성을 보다 정밀하게 수식화하고 이를 추론할 수 있는 정밀하고 과학적인 자동제어시스템의 개발이 필요하다.

Overlay parameter control of the semiconductor photolithography process is researched in this paper. Overlay parameters denote the error in superposing the current pattern to the pattern previously created. The reduction of the overlay deviation is one of the key factors in improving the quality of the semiconductor products. The semiconductor process is affected by numerous environment and equipment factors. Through process condition prediction and control, the overlay inaccuracy can be reduced. Generally, three types of process condition change exist; uncontrollable white noise, slowly changing drift, and abrupt condition shift. To effectively control the aforementioned process changes, control scheme using adaptive deadband is proposed. The suggested approach and existing control method are cross evaluated through simulation.

구조물이 과동한 기진력을 받을 때에 구조물의 진동 제어를 위하여 적응형 뱅뱅 제어 알고리듬이 저자들에 의해서 제안된 바 있으며, 이 제어 알고리듬을 1자유도계의 시험 구조물에 적용하여 제어 성능을 실험적으로 확인하였다. 본 논문은 이의 연장으로서 제안된 적응형 뱅뱅 제어 알고리듬을 최상층에 유압식 농동질량 감쇠기가 설치된 다자유도계의 시험 구조물에 적용하여 이의 유용성을 확인하였다. 이를 통하여 제안된 적응형 뱅뱅 제어 알고리듬은 제어 및 전체 구조계의 안전성이 보장되는 가운데 과도항 외부의 기진력을 받는 다자유도계의 구조물의 진동을 제어함에 효과적임을 확인할 수 있었다.