• Journal of the Korea Society of Computer and Information
• /
• v.29 no.11
• /
• pp.57-66
• /
• 2024

In this paper, an approach based on deep learning and parameter dependent control is proposed for electronic throttle body(ETB) control which has variable parameters and nonlinear torques. Firstly we present parameter estimation method for ETB system using deep neural network. To estimate parameters of ETB, we design deep neural networks and train by use time response characteristic such as rise time, overshoot and settling time. Parameters of ETB are estimated through trained neural networks by using time response data. Secondly we design parameter dependent PID controller which is adjusted automatically with the estimated system parameter of ETB. To design optimal parameter dependent gain of PID controller, we use ITAE(Integral of time multiplied by absolute error) criteria. In addition, we design feed-forward controller to reject nonlinear torque. Finally we present simulation results of ETB syatem with parameter variation and nonlinear torque to verify controller design method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1202-1209
• /
• 2018

This paper is concerned with the problem of setting controller's parameters when applying the intelligent PID (i-PID), which has recently been proposed and had many successful results, to the two-degree-of-freedom (2DoF) PID controller structure. Generally, the parameter settings of conventional PID controllers are known to be quite difficult and be dependent on the characteristics of the plants. In addition, it is less known how the two 2DoF parameters are set up for the improvement of transient characteristics. Here, we are going to present one of the criteria for parameter setting in the case of using a 2DoF i-PID, by evaluating the error signals to the set-point and disturbance. That is, we first, obtain parameters of i-PID by optimizing the disturbance responses, and then determine two parameters of 2DoF component through optimizing set-point response. The standard values of all parameters are calculated for the 7 types of test batches and rounded up as a table.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1327-1334
• /
• 1999

The stabilization control of ball-beam system is difficult because of its nonlinearity and structural unstability. Futhermore, a series of classical methods such as the PID and the full state feedback controller(FSFC) based on the local linearizations have narrow stabilizable regions. At the same time, the fine tunings of their gain parameters are also troublesome. Therefore, in this paper, three improved design techniques of stabilization controller for a ball-beam system were proposed. These parameter tuning methods in the double PID controller(DPIDC), the FSFC and the a sliding mode controller(SMC) were dependent upon the Real Value Elitist Genetic Algorithm (RVEGA). Finally, by applying the DPIDC, the FSFC and the Real Variable Elitist Genetic Algorithm based Sliding Mode Control(RVEGA SMC) to the stabilizations of a ball-beam system, the performances of the RVEGA SMC technique were showed to be superior to those of two other type controllers.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.8 no.6
• /
• pp.35-42
• /
• 1999

This paper concentrates on the position control of a pneumatic cylinder under parameter variation. A closed-loop control is proposed to design the different controllers(P, PI, PID, PD controller) in order to choose the best con-troller based on the fast and accurate control of the system. It is shown that the control algorithm, is robust and effective in attaining the fast and accurate position control of system under time-dependent parameter variation. Experimental results showed that PD controller law is effective to obtain the fast response and to increase that sta-blity of the system The method is a useful control algorithm which always automatically adjusts the position con-trol in accordance with the error using carrier wave of triangle type regardless of changes on the operating condi-tion and physical differences between components.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.165-170
• /
• 2001

This paper presents performance analysis of two-linked robot system using ER (electro rheological) valve actuators. An ER fluid consisting of soluble chemical starches (particles) and silicone oil is made and its field-dependent yield stress is experimentally distilled using electro-viscometer. From this result, the design parameters of ER valve are determined. Based on parameter study, an ER valve system is designed and manufactured. Furthermore, the measured pressure drop is compared with predicted one obtained from the Bingham model. Following the evaluation of field-dependent pressure drop of ER valve, a two-linked robot system with two ER valve actuators is then constructed and its governing equation of motion is derived. From this equation, PID controller is established. Consequently, control performances of the proposed two-linked robot system featuring ER valve are evaluated.