• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2006.06a
• /
• pp.87-88
• /
• 2006

In this paper, tuning rules of the PID controller for load disturbance rejection are proposed incorporating with real-coded genetic algorithms(RCGAs). The optimal parameters sets of the PID controller are obtained based on a first-order plus time delay model and a RCGA. As for assessing the performance of the controller, criteria(ISE, IAE and ITAE) are adopted. Then tuning formulae are derived using the tuned parameters sets, potential tuning rule models and another RCGA. A simulation work is carried out to verify the effectiveness of the proposed rules.

• Journal of Advanced Marine Engineering and Technology
• /
• v.33 no.7
• /
• pp.1003-1011
• /
• 2009

This study aims at precise control of oil outlet temperature in the oil cooler system of machine tools for enhancement of working speed and processing accuracy. PID control logic is adopted to obtain desired oil outlet temperature of the oil cooler system with hot-gas bypass method. We showed that the gains of PID controller could be easily determined by using gain tuning methods to get the gain of PID controller without any mathematical model. We also investigated various gain tuning methods to design the gains of PID and compared each control performance for selecting the optimal tuning method on the hot gas bypass method through experiments. Moreover, we confirmed excellent control performance with proposed PI controller gain even though disturbances were abruptly added to the experimental system.

• Journal of KSNVE
• /
• v.8 no.3
• /
• pp.441-449
• /
• 1998

A self-tuning control scheme, incorporated with the simplified 1st-order ARMAX(Auto-Regressive Moving Average eXogenous) model, for single rod hydraulic cylinder which has varying dynamic characteristics is presented here. An adaptive controller is developed for the system that uses feedforward and optimal feedback control for simultaneous parameter identification and tracking control. Through experimental results, the performance comparison of the self-tuning controller with a fixed gain proportional controller clearly shows its superior ability in handling load changes in quiescent states.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.218-220
• /
• 2004

A new wide-band VCO topology using Miller capacitance is proposed. Contrary to conventional VCO using the Miller capacitance where the variable amplifier gain is negative, the proposed VCO uses both the negative and positive variable amplifier gain to enhance the frequency tuning range significantly. The proposed VCO is simulated using HSPICE. The simulations show that 410MHz and 220MHz frequency tuning range are obtained using the negative .and positive variable amplifier gain, respectively. The tuning range of the proposed VCO is $23\%$ of the center frequency(2.8GHz). The phase noise is -104dBc/Hz at 1MHz offset by simple model. The operating current is only 3.84mA at 2.5V power supply.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.964-967
• /
• 1993

This paper presents an auto tuning method of fuzzy inference using Genetic Algorithm. The determination of membership functions by human experts is a difficult problem. Therefore, some auto-tuning methods have been proposed to reduce the time-consuming operations. However, the convergence of the tuning by the previous methods depends on the initial conditions of the fuzzy model. So, we proposes an auto tuning method for the fuzzy neural network by Genetic Algorithm (ATF system). This paper shows effectiveness of the ATF system by simulations.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.127-135
• /
• 2023

This research paper explores the application of FinBERT, a variational BERT-based model pre-trained on financial domain, for sentiment analysis in the financial domain while focusing on the process of identifying suitable training data and hyperparameters. Our goal is to offer a comprehensive guide on effectively utilizing the FinBERT model for accurate sentiment analysis by employing various datasets and fine-tuning hyperparameters. We outline the architecture and workflow of the proposed approach for fine-tuning the FinBERT model in this study, emphasizing the performance of various datasets and hyperparameters for sentiment analysis tasks. Additionally, we verify the reliability of GPT-3 as a suitable annotator by using it for sentiment labeling tasks. Our results show that the fine-tuned FinBERT model excels across a range of datasets and that the optimal combination is a learning rate of 5e-5 and a batch size of 64, which perform consistently well across all datasets. Furthermore, based on the significant performance improvement of the FinBERT model with our Twitter data in general domain compared to our news data in general domain, we also express uncertainty about the model being further pre-trained only on financial news data. We simplify the complex process of determining the optimal approach to the FinBERT model and provide guidelines for selecting additional training datasets and hyperparameters within the fine-tuning process of financial sentiment analysis models.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.1
• /
• pp.8-17
• /
• 2002

This paper suggests that the immune algorithm can effectively be used in tuning of a PID controller. The artificial immune network always has a new parallel decentralized processing mechanism for various situations, since antibodies communicate to each other among different species of antibodies/B-cells through the stimulation and suppression chains among antibodies that form a large-scaled network. In addition to that, the structure of the network is not fixed, but varies continuously. That is, the artificial immune network flexibly self-organizes according to dynamic changes of external environment (meta-dynamics function). However, up to the present time, models based on the conventional crisp approach have been used to describe dynamic model relationship between antibody and antigen. Therefore, there are some problems with a less flexible result to the external behavior. On the other hand, a number of tuning technologies have been considered for the tuning of a PID controller. As a less common method, the fuzzy and neural network or its combined techniques are applied. However, in the case of the latter, yet, it is not applied in the practical field, in the former, a higher experience and technology is required during tuning procedure. In addition to that, tuning performance cannot be guaranteed with regards to a plant with non-linear characteristics or many kinds of disturbances. Along with these, this paper used immune algorithm in order that a PID controller can be more adaptable controlled against the external condition, including moise or disturbance of plant. Parameters P, I, D encoded in antibody randomly are allocated during selection processes to obtain an optimal gain required for plant. The result of study shows the artificial immune can effectively be used to tune, since it can more fit modes or parameters of the PID controller than that of the conventional tuning methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.79-87
• /
• 2024

Recently, the importance of pre-trained language models (PLM) has been emphasized for natural language processing (NLP) such as text classification, sentiment analysis, and question answering. Korean PLM shows high performance in NLP in general-purpose domains, but is weak in domains such as finance, medicine, and law. The main goal of this study is to propose a language model learning process and method to build a financial-specific language model that shows good performance not only in the financial domain but also in general-purpose domains. The five steps of the financial-specific language model are (1) financial data collection and preprocessing, (2) selection of model architecture such as PLM or foundation model, (3) domain data learning and instruction tuning, (4) model verification and evaluation, and (5) model deployment and utilization. Through this, a method for constructing pre-learning data that takes advantage of the characteristics of the financial domain and an efficient LLM training method, adaptive learning and instruction tuning techniques, were presented.

• Journal of Welding and Joining
• /
• v.20 no.4
• /
• pp.544-550
• /
• 2002

Arc-spot welding is generally used in joining of precise parts such as case and core in electronic compressor. It is important to control joining deformation in electronic compressor because clearance control in micrometer order is needed for excellent airtightness and anti-nose. The countermeasures far this deformation in field have mainly been dependent on the rule of try and error by operator's experience because of productivities. For control this deformation problem without influence on productivities, development of exact simulation model should be needed. In this study, to solve this deformation problem in arc-spot welded structure with case and core, we intend to make a simulation model that is able to predict deformation in precise order by tuning and feedback between sensing data and simulation results. This paper include development of heat input model for arc-spot welding, temperature monitoring and make a heat transfer model using sensing data in product.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.61-64
• /
• 1996

This paper presents a new approach to the design of self-tuning adaptive control system that is robust to the changing dynamic configuration as well as to the load variation factors using Digital signal processors for robot manipulators. TMS32OC50 is used in implementing real-time adaptive control algorithms to provide advanced performance for robot manipulator. In this paper, an adaptive control scheme is proposed in order to design the pole-placement self-tuning controller which can reject the offset due to any load disturbance without a detailed description of robot dynamics. Parameters of discrete-time difference model are estimated by the recursive least-square identification algorithm, and controller parameters are determined by the pole-placement method. Performance of self-tuning adaptive controller is illustrated by the simulation and experiment for a SCARA robot.