• Proceedings of the KIEE Conference
• /
• 2005.11b
• /
• pp.145-147
• /
• 2005

This paper presents a methodology for satisfying the thermal comfort of Indoor environment and reducing the summer peak demand power by minimizing the power consumption for an Air-conditioner within a space. KEPCO(Korea Electric Power Corporation) use the fixed duty cycle control method regardless of the indoor thermal environment. This method has disadvantages that energy saying depends on the set-point value of the Air-Conditioner and DLC has no net effects on Air-conditioners if the appliance has a lower operating cycle than the fixed duty cycle. A variable duty cycle estimates the PMV(Predict Mean Vote) at the next step with a predicted temperature and humidity coming from the back propagation neural network model. It is possible to reduce the energy consumption by maintaining the Air-conditioner's OFF state when the PMV lies in the thermal comfort range. The proposed methodology uses the historical real data of Sep. 7th, 2001 from a classroom in seoul to verify the effectiveness of the variable duty cycle method comparing with fixed duty cycle. The result shows that the variable duty cycle reduces the peak demand to 2.6times more than fixed duty cycle and increases the load control ratio by 8% more. Based on the variable duty cycle control algorithm, the effectiveness of DLC is much more improved as compared with the fixed duty cycle.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.4
• /
• pp.1-8
• /
• 2020

Motion synthesis using physics-based controllers can generate a character animation that interacts naturally with the given environment and other characters. Recently, various methods using deep neural networks have improved the quality of motions generated by physics-based controllers. In this paper, we present a control policy learned by deep reinforcement learning (DRL) that enables Luxo, the mascot character of Pixar animation studio, to run towards a random goal location while imitating a reference motion and maintaining its balance. Instead of directly training our DRL network to make Luxo reach a goal location, we use a reference motion that is generated to keep Luxo animation's jumping style. The reference motion is generated by linearly interpolating predetermined poses, which are defined with Luxo character's each joint angle. By applying our method, we could confirm a better Luxo policy compared to the one without any reference motions.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.11
• /
• pp.76-88
• /
• 1998

While most of the research on reinforcement learning assumed a discrete control space, many of the real world control problems need to have continuous output. This can be achieved by using continuous mapping functions for the value and action functions of the reinforcement learning architecture. Two questions arise here however. One is what sort of function representation to use and the other is how to determine the amount of noise for search in action space. The ubiquitous neural network is used here to learn the value and policy functions. Next, the reinforcement predictor that is intended to predict the next reinforcement is introduced that also determines the amount of noise to add to the controller output. The proposed reinforcement learning architecture is found to have a sound on-line learning control performance especially at high-speed road following of high curvature road. Both computer simulation and actual experiments on a test vehicle have been performed and their efficiency and effectiveness has been verified.

• Smart Structures and Systems
• /
• v.19 no.4
• /
• pp.341-350
• /
• 2017

Based on the super elastic properties of the shape memory alloy (SMA) and the inverse piezoelectric effect of piezoelectric (PZT) ceramics, a kind of hybrid semi-active control device was designed and made, its mechanical properties test was done under different frequency and different voltage. The local search ability of genetic algorithm is poor, which would fall into the defect of prematurity easily. A kind of adaptive immune memory cloning algorithm(AIMCA) was proposed based on the simulation of clone selection and immune memory process. It can adjust the mutation probability and clone scale adaptively through the way of introducing memory cell and antibody incentive degrees. And performance indicator based on the modal controllable degree was taken as antigen-antibody affinity function, the optimization analysis of damper layout in a space truss structure was done. The structural seismic response was analyzed by applying the neural network prediction model and T-S fuzzy logic. Results show that SMA and PZT friction composite damper has a good energy dissipation capacity and stable performance, the bigger voltage, the better energy dissipation ability. Compared with genetic algorithm, the adaptive immune memory clone algorithm overcomes the problem of prematurity effectively. Besides, it has stronger global searching ability, better population diversity and faster convergence speed, makes the damper has a better arrangement position in structural dampers optimization leading to the better damping effect.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.17-23
• /
• 2019

In this paper, quality control (QC) is applied to each meteorological element of weather data collected from seven IoT sensors such as temperature. In addition, we propose a method for estimating the data regarded as error by means of machine learning. The collected meteorological data was linearly interpolated based on the basic QC results, and then machine learning-based QC was performed. Support vector regression, decision table, and multilayer perceptron were used as machine learning techniques. We confirmed that the mean absolute error (MAE) of the machine learning models through the basic QC is 21% lower than that of models without basic QC. In addition, when the support vector regression model was compared with other machine learning methods, it was found that the MAE is 24% lower than that of the multilayer neural network and 58% lower than that of the decision table on average.

• Journal of Korean Society for Quality Management
• /
• v.46 no.3
• /
• pp.739-752
• /
• 2018

Purpose: The purpose of this study was to investigate the relationship between kiln processing parameters and NOx emissions that occur in the sintering and calcination steps of the cement manufacturing process and to derive the main factors responsible for producing emissions outside emission limit criteria, as determined by category models and classification rules, using data mining techniques. The results from this study are expected to be useful as guidelines for NOx emission control standards. Methods: Data were collected from Precalciner Kiln No.3 used in one of the domestic cement plants in Korea. Thirty-four independent variables affecting NOx generation and dependent variables that exceeded or were below the NOx emiision limit (>1 and <0, respectively) were examined during kiln processing. These data were used to construct a detection model of NOx emission, in which emissions exceeded or were below the set limits. The model was validated using SPSS MODELER 18.0, artificial neural network, decision treee (C5.0), and logistic regression analysis data mining techniques. Results: The decision tree (C5.0) algorithm best represented NOx emission behavior and was used to identify 10 processing variables that resulted in NOx emissions outside limit criteria. Conclusion: The results of this study indicate that the decision tree (C5.0) can be applied for real-time monitoring and management of NOx emissions during the cement firing process to satisfy NOx emission control standards and to provide for a more eco-friendly cement product.

• Information and Communications Magazine
• /
• v.9 no.11
• /
• pp.70-79
• /
• 1992

제6세대 컴퓨터로 불리는 신경컴퓨터는 학습과 병렬처리에 의해 인간의 두뇌 기능을 모방한다. 인간의 두뇌는 시각인식, 음성인식, 촉각감지 등 패턴인식뿐 아니라 인간의 복잡한 신체구조를 시각, 촉각 같은 감각기관의 도움을 얻어 움직이는 중요한 역할도 한다. 바로 이 모터제어(motor control) 역시 신경회로가 담당하기 때문에 이를 기계적 신체에 해당하는 로보트 또는 광범위하게 기계, 비행기, 산업공정에 응용하는 것은 매우 자연스럽게 보인다. 이처럼 신경회로가 제어에 응용되는 것을 신경제어 (neurocontrol)라 하고 이를 이용한 기계를 지능기계(intelligent machinery)라 한다. 지능기계는 기본적으로 인간처럼 경험축적 학습 불확실한 환경에서의 적응 자기진단 등의 장점을 가지고 있다. 신경회로의 지극히 광범위한 응용분야중 신경제어는 가장 먼저 실현될 가능성이 높다. 실제로 로보트나 공정제어(process control)처럼 복잡한 비선형 시스템의 제어는 다량의 센서 정보에 기초한 실시간 제어를 필수로 하며 이는 신경회로를 사용함으로써 가장 효율적, 경제적으로 구현할 수 있다. 실제로 신경제어는 전세계적으로 이미 시스템 제어에 응용되어 좋은 결과를 내고 있다. 신경회로의 로보트나 자동화 응용은 학술적인 측면에서는 복잡한 비선형 시스템의 지능제어 (intelligent control)문제에 대한 신선한 해결책을 마련해줄 뿐 아니라 산업자동화라는 막대한 시장을 뒤로 하고 있어 이론에서 실제에 걸쳐 가장 광범위한 파급효과를 가지는 최첨단 기술로 보여진다. 고부가가치 상품을 통한 국제 경쟁력 제고의 차원에서도 정부, 기업 등의 과감한 연구 개발투자가 선행되어야 한다. 특히 이 분야의 연구는 선진국도 최근에 시작한 점으로 보아 정부, 기업이 이에 대한 연구 개발투자를 현명하게 할 경우에 세계적 기술 경쟁력도 확보할 수 있을 것이다. 본 해설에서는 로보트 및 시스템 제어에 관한 기초 이론을 설명하고 신경회로 적용기술을 소개하고 기존 방법과 비교 했을 때의 우월성, 전세계적인 응용연구, 국내외 연구개발 현황, 상업화 가능성, 산업계 응용례, 기술상의 문제점, 향후 전망 등을 다루기로 한다.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.05a
• /
• pp.408-411
• /
• 2009

In this paper, conventional PI, fuzzy neural network(FNN) and adaptive teaming mechanism(ALM)-FNN for rotor field oriented controlled(RFOC) induction motor are studied comparatively. The widely used control theory based design of PI family controllers fails to perform satisfactorily under parameter variation nonlinear or load disturbance. In high performance applications, it is useful to automatically extract the complex relation that represent the drive behaviour. The use of learning through example algorithms can be a powerful tool for automatic modelling variable speed drives. They can automatically extract a functional relationship representative of the drive behavior. These methods present some advantages over the classical ones since they do not rely on the precise knowledge of mathematical models and parameters. Comparative study of PI, FNN and ALM-FNN are carried out from various aspects which is dynamic performance, steady-state accuracy, parameter robustness and complementation etc. To have a clear view of the three techniques, a RFOC system based on a three level neutral point clamped inverter-fed induction motor drive is established in this paper. Each of the three control technique: PI, FNN and ALM-FNN, are used in the outer loops for rotor speed. The merit and drawbacks of each method are summarized in the conclusion part, which may a guideline for industry application.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.11
• /
• pp.1423-1433
• /
• 2018

Recently, a permanent magnet synchronous motor of middle and small-capacity has high torque, high precision control and acceleration / deceleration characteristics. But existing control has several problems that include unpredictable disturbances and parameter changes in the high accuracy and rigidity control industry or nonlinear dynamic characteristics not considered in the driving part. In addition, in the drive method for the control of low-vibration and high-precision, the process of connecting the permanent magnet synchronous motor and the load may cause the response characteristic of the system to become very unstable, to cause vibration, and to overload the system. In order to solve these problems, various studies such as adaptive control, optimal control, robust control and artificial neural network have been actively conducted. In this paper, an incremental encoder of the permanent magnet synchronous motor is used to detect the position of the rotor. And the position of the detected rotor is used for low vibration and high precision position control. As the controller, we propose augmented state feedback control with a speed observer and first order deadbeat disturbance observer. The augmented state feedback controller performs control that the position of the rotor reaches the reference position quickly and precisely. The addition of the speed observer to this augmented state feedback controller compensates for the drop in speed response characteristics by using the previously calculated speed value for the control. The first order deadbeat disturbance observer performs control to reduce the vibration of the motor by compensating for the vibrating component or disturbance that the mechanism has. Since the deadbeat disturbance observer has a characteristic of being vulnerable to noise, it is supplemented by moving average filter method to reduce the influence of the noise. Thus, the new controller with the first order deadbeat disturbance observer can perform more robustness and precise the position control for the influence of large inertial load and natural frequency. The simulation stability and efficiency has been obtained through C language and Matlab Simulink. In addition, the experiment of actual 2.5[kW] permanent magnet synchronous motor was verified.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.75-80
• /
• 2010

Noise handing is very important in voice recognition of vehicle environment. that has been studying about to hardware and software approach. hardware method that is noise filter circuit design, basically using Low-pass filter. it was shown a good result. and the side of software that has been developing about to algorithm for Noise canceler, NN(neural network), etc. in this paper we have analysis about to classified parameter pattern matting level for voice recognition on car noise environment that use of DTW(Dynamic Time Warping) which is applicable time series pattern recognition algorithm.