• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.45-48
• /
• 1999

Model predictive control algorithm requires a relevant model of the system to be controlled. Unfortunately, the first principle model describing a polymerization reaction system has a large number of parameters to be estimated. Thus there is a need for the identification and control of a polymerization reactor system by using available input-output data. In this work, the polynomial auto-regressive moving average (ARMA) models are employed as the input-output model and combined into the nonlinear model predictive control algorithm based on the successive linearization method. Simulations are conducted to identify the continuous styrene polymerization reactor system. The input variables are the jacket inlet temperature and the feed flow rate whereas the output variables are the monomer conversion and the weight-average molecular weight. The polynomial ARMA models obtained by the system identification are used to control the monomer conversion and the weight-average molecular weight in a continuous styrene polymerization reactor It is demonstrated that the nonlinear model predictive controller based on the polynomial ARMA model tracks the step changes in the setpoint satisfactorily. In conclusion, the polynomial ARMA model is proven effective in controlling the continuous styrene polymerization reactor.

• Nuclear Engineering and Technology
• /
• v.35 no.5
• /
• pp.399-411
• /
• 2003

A model predictive control method is applied to design an automatic controller for thermal power control in a reactor core. The basic concept of the model predictive control is to solve an optimization problem for a finite future at current time and to implement as the current control input only the first optimal control input among the solutions of the finite time steps. At the next time step, the second optimal control input is not implemented and the procedure to solve the optimization problem is then repeated. The objectives of the proposed model predictive controller are to minimize the difference between the output and the desired output and the variation of the control rod position. The nonlinear PWR plant model (a nonlinear point kinetics equation with six delayed neutron groups and the lumped thermal-hydraulic balance equations) is used to verify the proposed controller of reactor power. And a controller design model used for designing the model predictive controller is obtained by applying a parameter estimation algorithm at an initial stage. From results of numerical simulation to check the controllability of the proposed controller at the $5\%/min$ ramp increase or decrease of a desired load and its $10\%$ step increase or decrease which are design requirements, the performances of this controller are proved to be excellent.

• Journal of Korea Technology Innovation Society
• /
• v.14 no.3
• /
• pp.552-577
• /
• 2011

We have analyzed technology transfer and commercialization process and factors affecting the outcomes of technology commercialization of public research institutes in Korea. A technology commercialization process model was presented as an input, intermediate outcomes/capabilities, output (outcome) structure using the structural equation model. Input variables include R&D input, technology commercialization strategy/support, collaboration, social capital. The model also includes R&D capabilities and technology commercialization performance as intermediate variable and output variable respectively. The technology commercialization performance was measured as the number of technology transfer and spin-off. We conducted survey and 88 institutes responded. Empirical results show that R&D input influence R&D capabilities and R&D capabilities influence the output of technology transfer and commercialization. Collaboration activities and social capital also appear to have a positive effect on the output. However, the effect of strategy and support on the output appear to be not statistically significant.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.72-78
• /
• 2006

The paper proposes reference model error feedback control scheme for motion control system with hard non-linear components as like saturation and dead-zone in plant input part. Additionally, the plant has the system uncertainty effected by plant model parameter deviation and disturbance. The control algorithm uses the reference model to apply additional feedback loop with the error between reference model output and actual output effected by disturbance and non-linear components. And the stability evaluation based on Popov stability and controller design method are formulated to be performed. The effectiveness of the proposed scheme is examined by simulations. The results are proven by reasonable performances following reference model responses with good disturbance rejection performance without over-tuning of controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.485-485
• /
• 2000

A design method of model following control system using neural networks is proposed. An unknown nonlinear single-input single-output plant is identified using a multilayer neural networks. A linear controller is designed fer the linear approximation model obtained by linearinzing the identification model. The identification model is also used as a plant emulator to obtain the prediction error. Deficient servo performance due to controlling nonlinear plant with only linear controller is mended by adjusting the linear controller output using the prediction output and the parameters of the identification model. An optimal preview controller is adopted as the linear controller by reason of having good servo performance lowering the peak of control input. Validity of proposed method is illustrated through a numerical simulation.

• IE interfaces
• /
• v.19 no.4
• /
• pp.291-299
• /
• 2006

In order to enhance sustainable war fighting capabilities, it is important to maintain a good ammunition support system. In this paper, we evaluate the performance of ammunition companies using Imprecise Data Envelopment Analysis (IDEA)-BCC and IDEA-Additive model, which can deal with imprecise data in DEA. The input variables of IDEA models were selected by stepwise multiple regression analysis. With the regression model, we could choose the number of soldiers, officers, and ammunition warehouses as input variables that have significant effects on the output performance. Then, we applied the IDEA-BCC model with the concept of potential efficiency. The results of the model indicate that 8 out of 16 ammunition companies are efficient, 7 are inefficient, and 1 is potentially efficient. We could also identify the possible input excesses and output shortfalls to reach the efficient frontier using the IDEA-Additive model.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.11
• /
• pp.990-998
• /
• 2007

Adaptive output feedback control technique using Neural Networks(NN) is proposed for uncertain nonlinear Multi-Input Multi-Output(MIMO) systems. Modified Dynamic Inversion Model(MDIM) is introduced to decouple uncertain nonlinearities from inversion-based control input. MDIM consists of approximated dynamic inversion model and inversion model error. One NN is applied to compensate the MDIM of the system. The output of the NN augments the tracking controller which is based upon a filtered error approximation with online weight adaptation laws which are derived from Lyapunov's direct method to guarantee tracking performance and ultimate boundedness. Several numerical results are illustrated in the simulation of Van der Pol system and unmanned helicopter with model uncertainties.

• Journal of Korea Water Resources Association
• /
• v.49 no.9
• /
• pp.789-798
• /
• 2016

Frequent algal blooms at major river systems in Korea have been serious social and environmental problems. Especially, the appearance of cyanobacteria with toxic materials is a threat to secure a safe drinking water. In order to model the behaviour of cyanobacteria cell number, an exclusive causality analysis using prewhitening technique was introduced to delineate effective parameters to predict the cell numbers of cyanobacteria in Seungchon Weir and Juksan Weir along Youngsan river system. Both input and output transfer function models were obtained to explain temporal variation of cyanobacteria cell number. A threshold behaviour of water temperature was implemented into the model development to consider winter characteristic of cyanobacteria. The implementation of water temperature threshold into the model structure improves the predictability in simulation. Even though the input output transfer model cannot completely explained all blooms of cyanobacteria, the simple structure of model provide a feasibility in application which can be important in practical aspect.

• ETRI Journal
• /
• v.29 no.1
• /
• pp.89-94
• /
• 2007

A mathematical model for the input-output characteristic of an amplifier exhibiting gain expansion and weak and strong nonlinearities is presented. The model, basically a Fourier-series function, can yield closed-form series expressions for the amplitudes of the output components resulting from multisinusoidal input signals to the amplifier. The special case of an equal-amplitude two-tone input signal is considered in detail. The results show that unless the input signal can drive the amplifier into its nonlinear region, no gain expansion or minimum intermodulation performance can be achieved. For sufficiently large input amplitudes that can drive the amplifier into its nonlinear region, gain expansion and minimum intermodulation performance can be achieved. The input amplitudes at which these phenomena are observed are strongly dependent on the amplifier characteristics.