• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.3
• /
• pp.170-175
• /
• 2001

Q-learning is a kind of reinforcement learning where the agent solves the given task based on rewards received from the environment. Most research done in the field of Q-learning has focused on discrete domains, although the environment with which the agent must interact is generally continuous. Thus we need to devise some methods that enable Q-learning to be applicable to the continuous problem domain. In this paper, an extended fuzzy rule is proposed so that it can incorporate Q-learning. The interpolation technique, which is widely used in memory-based learning, is adopted to represent the appropriate Q value for current state and action pair in each extended fuzzy rule. The resulting structure based on the fuzzy inference system has the capability of solving the continuous state about the environment. The effectiveness of the proposed structure is shown through simulation on the cart-pole system.

• Journal of Biosystems Engineering
• /
• v.15 no.2
• /
• pp.134-142
• /
• 1990

This study was carried out for the development of greenhouse temperature control system by modifying an APPLE-II microcomputer attached with several interface systems. The interface systems are composed of 12 bit A/D converter, output port, multiplexer, time clock, etc. Under the operation of developed system, the greenhouse temperature was to be manipulated within the setting temperatures assumed to be appropriate for certain plant growth. The temperature control equimpents installed in the greenhouse are one-speed propeller type fan and two-phase electric heater, which are selectively started or stopped according to the control logic programmed in the control system. The results are summarized as follows : 1. The difference between two temperatures measured by the developed system and the self-recording thermometer calibrated with standard thermometer was less than $1^{\circ}C$. 2. When the temperature were measurd by 12 bit A/D converter and both electric heater and ventilation fan were controlled by developed ON/OFF logic, greenhouse temperature showed narrow fluctuation bands of less than $1^{\circ}C$ near the setting temperatures. 3. The temperature acquisition and control system developed in this study is expected to be applicable to environment control system such as greenhouse only by modifying the logic based on long term experimental data. 4. In order to reduce the measurement error and to increase the system control efficiency, it is recommended that continuous study should be carried out in the aspect of eliminating various systematic noises and improving the environmental control logic.

• Korean Journal of Logic
• /
• v.8 no.1
• /
• pp.47-67
• /
• 2005

Bayesian networks have been used in studying and simulating causal inferences by using the probability function distributed over the variables consisting of inquiry space. The focus of the debates concerning Bayesian networks is the causal Markov condition that constrains the probabilistic independence between all the variables which are not in the causal relations. Cartwright, a strong critic about the Bayesian network theory, argues that the causal Markov condition cannot hold in indeterministic systems, so it cannot be a valid principle for causal inferences. The purpose of the paper is to explore whether her argument on the causal Markov condition is valid. Mainly, I shall argue that it is possible for upholders of the causal Markov condition to respond properly the criticism of Cartwright through the continuous causal model that permits the infinite sequence of causal events.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.2
• /
• pp.146-152
• /
• 2002

Mold level control has been a major control task for continuous casting plants. The system involves nonlinearities such as stick-slip friction in the sliding gate, time-delay, friction force variations between molten steel and the inner wall of mold, and nozzle logging/unclogging. These complex problems should be solved to control mold level for steel cast. In this paper, we propose a neural fuzzy mold level control technique for solving these complex problems and give experiment studies to show the mold level control in continuous casting process.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.220-226
• /
• 2002

In this paper, we develop the intelligent digitally redesigned fuzzy controller for nonlinear systems. Takagi-Sugeno (TS) fuzzy model is used to model the nonlinear systems and a continuous-time fuzzy-model-based controller is designed based on the extended parallel-distributed-compensation(EPDC) method . The digital controllers are determined from existing analogue controllers. The proposed method provides an accurate and effective method for digital control of continuous-time nonlinear systems and enables us to efficiently implement a digital controller via the pre-determined continuous-time 75 fuzzy-model-based controller. We have applied the proposed method to the duffing forced oscillation system to show the effectiveness and feasibility of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.67-67
• /
• 2000

In this paper, a hybrid type fuzzy controller is proposed to maintain molten steel level stable and reliable manner in high speed continuous casting regardless of various disturbances such as casting speed change, tundish weight variation, 치ogging/undoning of SEN(Submerged Entry Nozzle), periodic bulgings, etc. To accomplish this purpose, hardware filter and software filer are carefully designed to eliminate high frequency noise and to smooth input signals from harsh environments. In order to minimize the molten steel level variations from various disturbances the controller uses hybrid type control term: fuzzy logic term, proportional term, differential term and nonlinear feedback compensation tenn. The proposed controller is applied tn commercial mini-mill plant and shows considerable improvement in minimizing the molten steel variation.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.668-678
• /
• 1996

A control system using fuzzy logic for a large capacity continuous dryer has been developed in order to minimize the damage of rice quality. The system has been verified in the case of 17% of object moisture content. With the initial input moisture contents of 20.46%(wb), 20.96%(wb) and 18.98%(wb), the final moisture contents of 17.99%(wb), 17.6%(wb) and 17.23%(wb) are obtained, respectively. The results show that the system controls the moisture content with the maximum error of 0.99% of the object moisture content.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.4
• /
• pp.984-995
• /
• 1996

Data errors according to the various noises caused in the satellite communication links are corrected by the Viterbi decoding algorithm which has extreme error correcting capability. In this paper, we designed and implemented a convolutional encoder and Viterbi decoder ASIC which is used to encode the input data at the transmit side and correct the errors of the received data at the receive side for use in the VSAT communication system. And this chip may be used in any BPSK, QPSK, or OQPSK transmission system. The ambiguity resolver corrects PSK modem ambiguities by delaying, interting, and/or exchanging code symbol to restore their original sequence and polarity. In case of previous decoding system, ambiguity state(AS) of data is resolved by external control logic and extra redundancy data are needed to resolve AS. But, by adopting decoder proposed in this paper, As of data is resolved automatically by internal logic of decoder in case of continuous mode, and by external As line withoug extra redudancy data in burst mode case. So, decoding parts are simple in continuous mode and transmission efficiency is increased in bust mode. The features of this chip are full duplex operation with independent transmit and receive control and clocks, start/stop inputs for use in burst mode systems, loopback function to verify encoder and decoder, and internal or external control to resolve ambinguity state. For verification of the function and performance of a fabricated ASIC chip, we equiped this chip in the Central and Remote Earth Station of VSAT system, and did the performance test using the commerical INTELSAT VII under the real satellite link environmens. The results of test were demonstrated the superiority of performance.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.3
• /
• pp.1271-1279
• /
• 2017

A highly accurate model-free controller is proposed for trajectory tracking control of robot manipulators. The proposed controller incorporates time-delay estimation (TDE) to estimate and cancel continuous nonlinearities of robot dynamics, and exploits fuzzy logic systems to suppress the effect of the TDE error, which is due to discontinuous nonlinearities such as friction. To this end, integral sliding mode is defined using desired error dynamics, and a Mamdani-type fuzzy inference system is constructed. As a result, the proposed controller achieves the desired error dynamics well. Implementation of the proposed controller is easy because the design of the controller is intuitive and straightforward, and calculations of the complex robot dynamics are not required. The tracking performance of the proposed controller is verified experimentally using a 3-degree of freedom PUMA-type robot manipulator.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.257-262
• /
• 2019

Recently, with a great deal of attention and utilization to the UAV like a drone, many application cases using UAV in various fields have been proliferated rapidly. These UAV, however, has many risks like balance deviation and drone crash due to the external environmental factors. The attitude control algorithm for UAV is the most important portion in order to maintain the safe management of UAV, and the best solution is PID control algorithm which is generously used and almost perfect attitude control technology nowadays. In this paper, we propose the smart attitude control algorithm using fuzzy logic in order to provide safe and continuous attitude control against external environmental factors, and compare the performance through simulation study between PID and our algorithm.