• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.301-308
• /
• 1997

The learning speed of the neural networks, the most important factor in applying to real problems, greatly depends on the learning rate of the networks, Three approaches-empirical, deterministic, and stochastic ones-have been proposed to date. We proposed a new learning-rate selection algorithm using an evolutionary programming search scheme. Even though the performance of our method showed better than those of the other methods, it was found that taking much time for selecting evolutionary learning rates made the performance of our method degrade. This was caused by using static intervals (called static windows) in order to update learning rates. Out algorithm with static windows updated the learning rates showed good performance or didn't update the learning rates even though previously updated learning rates shoved bad performance. This paper introduce a window control scheme to avoid such problems. With the window control scheme, our algorithm try to update the learning ra es only when the learning performance is continuously bad during a specified interval. If previously selected learning rates show good performance, new algorithm will not update the learning rates. This diminish the updating time of learning rates greatly. As a result, our algorithm with the window control scheme show better performance than that with static windows. In this paper, we will describe the previous and new algorithm and experimental results.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.4
• /
• pp.33-41
• /
• 2004

This study examines the relationship between multiple sales force management practices and performance within each of Miles & Snow (1978)'s strategy types and Walker & Ruekert (1987)'s strategy types. The findings are as follows : First, Prospectors seem to be associated with increased performance when they are utilizing a relationship selling strategy, internal sales force, moderate levels of supervision, outcome-based control system and incentive-oriented compensation system. Second, Analyzers seem to be associated with increased performance when they are utilizing a relationship selling strategy, internal sales force, outcome-based control system to deal with the instability in their strategic focus. Third, Low Cost Defender seem to be associated with increased performance when they are utilizing a relationship selling strategy, external sales force, low levels of supervision, outcome-based control system and salary-oriented compensation system. Fourth, Differentiated Defenders seem to be associated with increased performance when they are utilizing a relationship selling strategy, high levels of supervision, balanced (outcome+behavior) control system and salary-oriented compensation system.

• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.4
• /
• pp.256-265
• /
• 2023

This paper describes the results of the development of the submarine Free Running Model (FRM). First, the goal of development was set based on the test conditions and the test environment, and the system was obtained accordingly. The target submarine, Joubert BB2 submarine, was selected with a scale of 18.35 in accordance with the development goal. In order to conduct a submarine FRM test underwater, where communication is impossible, the FRM must operate at least semi-autonomously. For this purpose, an Extended Kalman Filter (EKF) based underwater integrated navigation system and control system using a sailplane and an X-shaped sternplane were designed respectively. In addition, a ballast system was designed to enable the model to float to the water surface in case of an emergency. To verify its propulsion, navigation, and control performance, the FRM tests were conducted in both indoor and outdoor basins. As a result, the relationship between propeller RPM and vehicle speed was derived, and it was confirmed that the navigation and control performance met the target value.

• Journal of Drive and Control
• /
• v.17 no.2
• /
• pp.45-54
• /
• 2020

The IMV is a combination of four two-way valve systems which replace a conventional four-way spool valve to improve efficiency mostly in excavator hydraulics. As the environmental regulations for construction equipment have tightened, some overseas advanced companies have released commercial excavators in which the MCV is implemented with the IMVs. Development of the IMV type MCV relies on the control algorithm as well as the robust performance of proportional flow control valves. In this study, the IMV controller was designed and verified with experiments for the excavator working unit, which determines the IMV mode of operation and the extent of the valve opening in consideration of the load conditions on hydraulic actuators. First, the open-loop controller was designed with a joystick command vs. a PSV reference current map comprising several control parameters in to compensate for the different flow characteristics and non-linearities of two-way flow control valves. Second, the closed-loop controller was designed with the PI control fed by the actuator displacement and outputs actuator percent effort equivalent to the operator's joystick command. Finally, the performance of the IMV type MCV was verified with the trajectory control of position references derived from the energy consumption test standard. Experimental results showed the control performance of the IMV developed in this study, and suggest that future studies to be conducted to advance technical progress.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.737-742
• /
• 2007

The method of the reducing duct noise can be classified by passive and active control techniques. However, passive control has a limited effect of noise reduction at low frequencies (below 500Hz) and is limited by the space. On the other hand, active control can overcome these passive control limitations. The active control technique mostly uses the Least-Mean-Square (LMS) algorithm, because the LMS algorithm can easily obtain the complex transfer function in real-time particularly when the Filtered-X LMS (FXLMS) algorithm is applied to an active noise control (ANC) system. However, the convergence performance of the LMS algorithm decreases slightly so it may delay the convergence time when the FXLMS algorithm is applied to the active control of duct noise. Thus the Co-FXLMS algorithm was developed to improve the control performance in order to solve this problem. The Co-FXLMS algorithm is realized by using an estimate of the cross correlation between the adaptation error and the filtered input signal to control the step size. In this paper, the performance of the Co-FXLMS algorithm is presented in comparison with the FXLMS algorithm. Simulation results show that active noise control using Co-FXLMS is effective in reducing duct noise.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1450-1454
• /
• 1996

Even though digital control type high speed solenoid valve is a little inferior to analog control type servo valve and proportional control valve in performance, it is cheap and has secure performance against pollutant and simple control circuit. But high speed solenoid valve is hardly used for heavy machinery instead of servo valve or proportional control valve that is used in severe condition because the valve itself is small capacity and it shows wide dead zone during on-off control and chattering of hydraulic cylinder by chattering of pressure. It is desirable to use low-priced and strong pollutant resistant high speed solenoid valve for obtaining reliability of operation from severe working condition because it isn't necessary to acquire response characteristic of high frequency when we consider the characteristic of heavy machinery operation. In this study, PWM control algorithm for pilot pressure control of large capacity pilot operating valve will be used for precision position control of heavy machinery hydraulic cylinder. Not only cost reduction of main control valve but also high reliability of heavy machinery in severe condition can be obtained by using this pilot operating spool valve with high speed solenoid valve.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.6 s.144
• /
• pp.566-574
• /
• 2005

Reduction of a ship's rolling is the most important performance requirement for improving the safety of the crew on board and preventing damage to cargos as well as improving the comfort of the ride. A mass driving anti-rolling system (MO-ARS) might be one candidate of several systems against the ship's rolling. As the movable range of the mass on the ship is finite, the control system must include restriction on the mass position to protect the device and the ship. This restriction usually causes windup phenomenon and control performance is deteriorated seriously. Two control algorithms, anti-windup control and saturated sliding mode control, are studied in this paper. Control performance and robustness problem are checked out by numerical simulations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.131-138
• /
• 2022

The demand for chiller equipment that keeps each machine at a constant temperature to maintain the best possible condition is growing rapidly. PID (Proportional Integral Derivation) control is a popular temperature control method. The error, which is the difference between the desired target value and the current system output value, is calculated and used as an input to the system using a proportional, integrator, and differentiator. Through such a closed-loop configuration, a desired final output value of the system can be reached using only the target value and the feedback signal. Furthermore, various temperature control methods have been devised as the control performance of various high-performance equipment becomes important. Therefore, it is necessary to design for accurate data-driven temperature control for chiller equipment. In this research, support vector regression is applied to the classic PID control for accurate temperature control. Simulated annealing is applied to find optimal PID parameters. The results of the proposed control method show fast and effective control performance for chiller equipment.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.2
• /
• pp.303-311
• /
• 2012

In this study, we introduce a dynamic process model as well as the design methodology of optimized fuzzy controller for its efficient application to vacuum production system to produce a semiconductor, solar module and display and so on. In a vacuum control field, PID control method is widely used from the viewpoint of simple structure and preferred performance. But, PID control method is very sensitive to the change of environment of control system as well as the change of control parameters. Therefore, it's difficult to get a preferred performance results from target system which has a complicated structure and lots of nonlinear factors. To solve such problem, we propose the design methodology of an optimized fuzzy PID controller through a following series of steps. First a dynamic characteristic of the target system is analyzed through a series of experiments. Second the process model is built up and its characteristic is compared with real process. Third, the optimized fuzzy PID controller is designed using genetic algorithms. Finally, the fuzzy controller is applied to target system and then its performance is compared with that of other conventional controllers(PID, PI, and Fuzzy PI controller). The performance of the proposed fuzzy controller is evaluated in terms of auto-tuned control parameters and output responses considered by ITAE index, overshoot, rise time and steady state time.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.6
• /
• pp.183-189
• /
• 2003

The study of the automotive noise reduction has been concentrated on the reduction of the automotive engine noise because the engine noise is the major cause of automotive noise. However, many studies of automotive engine noise led to the interest of the noise reduction of the exhaust and intake system. Recently, the active control method is used to reduce the noise of an automotive exhaust and intake system. It is mostly used the LMS(Least-Mean-Square) algorithm as an algorithm of active control because the LMS algorithm can easily obtain the complex transfer function in real-time. Especially, Filtered-X LMS (FXLMS) algorithm is applied to an Active Noise Control system. However, the convergence performance of LMS algorithm went bad when the FXLMS algorithm was applied to an active control of the induction noise under rapidly accelerated driving conditions. So, in order to solve this problem, the modified FXLMS algorithm is proposed. In this study, the improvement of the control performance using the modified FXLMS algorithm under rapidly and suddenly accelerated driving conditions was identified. Also, the performance of an active control using the LMS algorithm under rapidly accelerated driving conditions was evaluated through the theoretical derivation using a chirp signal to have similar characteristics with the induction noise signal.