• Geomechanics and Engineering
• /
• v.37 no.3
• /
• pp.197-211
• /
• 2024

This research studies the effect of geotechnical factors on EPB-TBM performance parameters. The modeling was performed using simple and multivariate linear regression methods, artificial neural networks (ANNs), and Sugeno fuzzy logic (SFL) algorithm. In ANN, 80% of the data were randomly allocated to training and 20% to network testing. Meanwhile, in the SFL algorithm, 75% of the data were used for training and 25% for testing. The coefficient of determination (R²) obtained between the observed and estimated values in this model for the thrust force and cutterhead torque was 0.19 and 0.52, respectively. The results showed that the SFL outperformed the other models in predicting the target parameters. In this method, the R² obtained between observed and predicted values for thrust force and cutterhead torque is 0.73 and 0.63, respectively. The sensitivity analysis results show that the internal friction angle (φ) and standard penetration number (SPT) have the greatest impact on thrust force. Also, earth pressure and overburden thickness have the highest effect on cutterhead torque.

• Journal of the Korea Computer Graphics Society
• /
• v.2 no.1
• /
• pp.7-14
• /
• 1996

A particle system is defined as a collection of primitive particles that together represent irregular and ever-changing objects such as smoke, clouds, waterfalls, and explosions. A particle system can be a powerful tool for modeling a deformable object's motion and change of form since it has dynamic properties with time. As an object becomes more complicated and shows more chaotic behavior, however, we need much more parameters for describing its characteristics completely. Consequently, the conventional particle system leads to difficulty in managing all of the parameters properly since one parameter can affect the others. Moreover, motion equations for representing particles' behavior are usually approximated to gain speed-ups. The inevitable errors in calculating the equations can cause an unexpected outcome. In this paper, we present a new approach of applying fuzzy contol to mage particles' motion and attributes changes over time. We also give an implementation result of a fuzzy particle system to show the feasibility of the proposed method. Applications of the system to explosions, nebulae, volcanos, and grass are presented.

• Journal of Digital Contents Society
• /
• v.9 no.2
• /
• pp.245-250
• /
• 2008

Psychology of color is a research field of psychology for studying human's behavior connected with color. Color carries symbolism and image while sharing psychological consensus with human. Each color has a respective image such as hope, passion, love, life, death, and so on. Peculiar stimuli by colors on these images have great influence on human's emotion and psychology. We therefore proposed a method for understanding human's state of emotion based on colors in this paper. In order to understand human's state of emotion, we analyzed color information used to model a room by a user and then described frequencies of each color as percent using fuzzy inference rules by membership values of fuzzy membership functions for colors used for modeling the room. When we applied the proposed color-based emotion analysis method to emotional state based on colors of Alschuler and Hattwick, we could see the proposed method is efficient.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.37-47
• /
• 1998

This paper proposes a controller design method using the evolutionary computation algorithm and the fuzzy logic to control the wafer temperature in rapid thermal processing. First, we design the feedforward static controller to provide the control powers of the lamps for the given steady state temperature. Second, the feedforward dynamic controller is designed for the additional control powers to achieve a given transient response. These feedforward controllers are implemented by using the fuzzy logic to act as a global nonlinear controller over a wide range of operating points. The parameters of these controllers are optimized by using the evolutionary computation algorithm so that it can be used when the mathematical model is not available. In addition, the feedback error controller is introduced to compensate the feedforward controllers when there exist disturbances and modeling errors. The gain of feedback error controller is also obtained by the evolutionary computation algorithm. Through simulations, we verify the proposed control system can give a satisfactory performance.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.4
• /
• pp.82-91
• /
• 1997

In this paper, a design method of the boiler-turbine control system in the coal fired power plant is proposed. We need to control electric output and drum pressure and water level in drum to guarantee stable operation and save energy for generating electricity and decrease air pollution in the boiler-turbine system. This boiler-turbine control system is composed of reference model part and model following part. The multivariable boiler-turbine system is separated into 3 SISO(Single Input Single Output) systems applying the concept of relative gain matrix. Each 3 reference models for separated boiler-turbine system are composed of 1st order nominal plant and hysteresis integral control system and they make good dy¬namic response with no overshoot and fast rising time. Each fuzzy controller to follow as close as possible to the response of each reference model is designed. The robustness and the good tracking property can be achieved using 5150 fuzzy controllers when there are modeling errors, disturbances and parameter pertur¬bations. The effectiveness of the proposed design method is verified through simulations.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.11
• /
• pp.1477-1485
• /
• 2018

There are two major issues for activated sludge process in sewage treatment plant. One is how to make sewage be more clean and the other is the energy saving in sewage treatment process. The major monitoring sewage qualities are chemical oxygen demand, phosphorus, nitrogen, suspended solid in effluent. These are transmitted to the national TMS(Telemetry Monitoring System) at every hour. If these exceed the environmental standard, the environmental charges imposed. So, these water qualities are to be controlled below the environmental standard in operation of sewage treatment plant. And recently, the energy saving is also important in process operation. Over 50% energy is consumed in blowers and motors for injection oxygen into aeration tank. So, with the water qualities to be controlled below the environmental standard, the energy saving also is to be accomplished for efficient plant management. Almost researches are aimed to control water quality without considering energy saving. AI techniques have been used for control water quality. AI modeling simulator provided the optimal control inputs(blower speed, waste sludge, return sludge) for control water quality. Blower speed is the main control input for activated sludge process. To make sewage be more clean, the excessive blower speed is supplied, but water quality is not better than the previous. In results, non necessary energy is consumed. In this paper we propose a new method that the energy saving also is to be accomplished with the water qualities to be controlled below the environmental standard for efficient plant management. Water qualities in only aeration tank are used the inputs of fuzzy models. Outputs of these models are chemical oxygen demand, phosphorus, nitrogen, suspended solid in effluent and have the environmental standards. In test, we found this method could save 10% energy than the previous methods.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.165-172
• /
• 1998

The electromechanical energy conversion conditioning and processing implementation in USM direct motion control system is generally divided into two power stages: the two-phase high-frequency ac power inversion stage for driving piezoelectric ceramic PZT transducer array off the USM stator and the mechanical thrust power conversion stage based on the frictional force between the piezo electric stator array and the rotary slider of the USM. However, the dynamic and steady-state mathematical modeling of the USM is extremely default from a theoretical point of view because it contains many complicated an nonlinear characteristics dependant on operation temperature. In +2$0^{\circ}C$~3$0^{\circ}C$, the operating characteristics of the USM has represented normal condition. But the other temperature, it has abnormal condition so that driving frequency, current and motor speed will be down. The recent USM has controller without temperature compensation. This study represents the fuzzy controller for speed compensation according to operating temperature by driving frequency.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.3
• /
• pp.237-242
• /
• 2014

Surge phenomenon can be occurred in a compressor when the performance of turbofan engine for an aircraft is changed considerably such as take-off phase. This study is aimed to avoid surge phenomenon. This paper propose the PID and Fuzzy control System for the turbofan engine with control inputs, the VIGV(Variable Inlet Guide Vane) in closed loop, and the fuel mass flow in open loop. We design the Dynamic modeling, NPSS S-function, which is connection block of simulink between NPSS(Engine analysis program) and Simulink. Finally, we certify the performance to prevent a serge phenomenon in the VIGV control system using the both methods, PID and fuzzy.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.128-135
• /
• 2015

In this study, we develop the very short-term precipitation forecasting model as well as classifier based on polynomial radial basis function neural networks by using AWS(Automatic Weather Station) and KLAPS(Korea Local Analysis and Prediction System) meteorological data. The polynomial-based radial basis function neural networks is designed to realize precipitation forecasting model as well as classifier. The structure of the proposed RBFNNs consists of three modules such as condition, conclusion, and inference phase. The input space of the condition phase is divided by using Fuzzy C-means(FCM) and the local area of the conclusion phase is represented as four types of polynomial functions. The coefficients of connection weights are estimated by weighted least square estimation(WLSE) for modeling as well as least square estimation(LSE) method for classifier. The final output of the inference phase is obtained through fuzzy inference method. The essential parameters of the proposed model and classifier such ad input variable, polynomial order type, the number of rules, and fuzzification coefficient are optimized by means of Particle Swarm Optimization(PSO) and Differential Evolution(DE). The performance of the proposed precipitation forecasting system is evaluated by using KLAPS meteorological data.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.4
• /
• pp.180-189
• /
• 2009

Currently, most automobile companies are interested in research on intelligent autonomous vehicle. They are mainly focused on driver's intelligent assistant and driver replacement. In order to develop an autonomous vehicle, lateral and longitudinal control is necessary. This paper presents a lateral and longitudinal control system for autonomous vehicle that has only mono-vision camera. For lane detection, we present a new lane detection algorithm using clothoid parabolic road model. The proposed algorithm in compared with three other methods such as virtual line method, gradient method and hough transform method, in terms of lane detection ratio. For adaptive control, we apply a vanishing point estimation to fuzzy control. In order to improve handling and stability of the vehicle, the modeling errors between steering angle and predicted vanishing point are controlled to be minimized. So, we established a fuzzy rule of membership functions of inputs (vanishing point and differential vanishing point) and output (steering angle). For simulation, we developed 1/8 size robot (equipped with mono-vision system) of the actual vehicle and tested it in the athletics track of 400 meter. Through the test, we prove that our proposed method outperforms 98 % in terms of detection rate in normal condition. Compared with virtual line method, gradient method and hough transform method, our method also has good performance in the case of clear, fog and rain weather.