• Design & Manufacturing
• /
• v.17 no.1
• /
• pp.27-32
• /
• 2023

In this paper, we intend to predict the mass of the spiral using CAE and machine learning. First, We generated 125 data for the experiment through a complete factor design of 3 factors and 5 levels. Next, the data were derived by performing a molding analysis through CAE, and the machine learning process was performed using a machine learning tool. To select the optimal model among the models learned using the learning data, accuracy was evaluated using RMSE. The evaluation results confirmed that the Support Vector Machine had a good predictive performance. To evaluate the predictive performance of the predictive model, We randomly generated 10 non-overlapping data within the existing injection molding condition level. We compared the CAE and support vector machine results by applying random data. As a result, good performance was confirmed with a MAPE value of 0.48%.

• Journal of Power Electronics
• /
• v.18 no.5
• /
• pp.1398-1408
• /
• 2018

In order to further improve the steady-state control performance of model predictive torque control (MPTC), a double-vector-based model predictive torque control without a weighting factor is proposed in this paper. The extended voltage vectors synthesized by two basic voltage vectors are used to increase the number of feasible voltage vectors. Therefore, the control precision of the torque and the stator flux along with the steady-state performance can be improved. To avoid testing all of the feasible voltage vectors, the solution of deadbeat torque control is calculated to predict the reference voltage vector. Thus, the candidate voltage vectors, which need to be evaluated by a cost function, can be reduced based on the sector position of the predicted reference voltage vector. Furthermore, a cost function, which only includes a reference voltage tracking error, is designed to eliminate the weighting factor. Moreover, two voltage vectors are applied during one control period, and their durations are calculated based on the principle of reference voltage tracking error minimization. Finally, the proposed method is tested by simulations and experiments.

• Journal of Power Electronics
• /
• v.15 no.1
• /
• pp.202-215
• /
• 2015

This paper investigates the stability and performance of model predictive controlled active-front-end (AFE) rectifiers for energy storage systems, which has been increasingly applied in power distribution sectors and in renewable energy sources to ensure an uninterruptable power supply. The model predictive control (MPC) algorithm utilizes the discrete behavior of power converters to determine appropriate switching states by defining a cost function. The stability of the MPC algorithm is analyzed with the discrete z-domain response and the nonlinear simulation model. The results confirms that the control method of the active-front-end (AFE) rectifier is stable, and that is operates with an infinite gain margin and a very fast dynamic response. Moreover, the performance of the MPC controlled AFE rectifier is verified with a 3.0 kW experimental system. This shows that the MPC controlled AFE rectifier operates with a unity power factor, an acceptable THD (4.0 %) level for the input current and a very low DC voltage ripple. Finally, an efficiency comparison is performed between the MPC and the VOC-based PWM controllers for AFE rectifiers. This comparison demonstrates the effectiveness of the MPC controller.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.57-58
• /
• 2022

Concrete mix design is used as essential data for the quality of concrete, analysis of structures, and stable use of sustainable structures. However, since most of the formulation design is established based on the experience of experts, there is a lack of data to base it on. are suffering Accordingly, in this study, the purpose of this study is to build a predictive model to use the concrete mixing factor as basic data for calculation using the DNN technique. As for the data set for DNN model learning, OPC and ternary concrete data were collected according to the presence or absence of admixture, respectively, and the model was separated for OPC and ternary concrete, and training was carried out. In addition, by varying the number of hidden layers of the DNN model, the prediction performance was evaluated according to the model structure. The higher the number of hidden layers in the model, the higher the predictive performance for the prediction of the mixing elements except for the compressive strength factor set as the output value, and the ternary concrete model showed higher performance than the OPC. This is expected because the data set used when training the model also affected the training.

• Journal of the Korean Society of Safety
• /
• v.21 no.4 s.76
• /
• pp.25-32
• /
• 2006

LonWorks over IP(LonWorks-IP) virtual device network(VDN) is an integrated form of LonWorks device network and IP data network. In especially real-time distributed servo applications on the factory floor, timely response is essential for predictive and preventive maintenance. The time delay in servo control on LonWorks-IP based VDN has highly stochastic nature. LonWorks-IP based VDN induced transmission delay deteriorates the performance and stability of the real-time distributed control system and can't give an effective preventive and predictive maintenance. In order to guarantee the stability and performance of the system, and give an effective preventive and predictive maintenance, LonWorks-IP based VDN induced time-varying uncertain time delay needs to be predicted and compensated. In this paper new Pill control scheme based on Smith predictor, disturbance observer and band pass filter is proposed and tested through computer simulation about position control of DC servo motor. It is shown that how can the proposed control scheme be designed to minimize the effects of uncertain varying time delay and model uncertainties. The validity of the proposed control scheme is compared and demonstrated with the comparison of internal model controllers(IMC) based on Smith predictor with and without disturbance observer.

• KIEAE Journal
• /
• v.17 no.4
• /
• pp.83-88
• /
• 2017

Purpose: The objective of this study is to develop a predictive model for calculating the amount of cooling load for the different setback temperatures during the setback period. An artificial neural network (ANN) is applied as a predictive model. The predictive model is designed to be employed in the control algorithm, in which the amount of cooling load for the different setback temperature is compared and works as a determinant for finding the most energy-efficient optimal setback temperature. Method: Three major steps were conducted for proposing the ANN-based predictive model - i) initial model development, ii) model optimization, and iii) performance evaluation. Result:The proposed model proved its prediction accuracy with the lower coefficient of variation of the root mean square errors (CVRMSEs) of the simulated results (Mi) and the predicted results (Si) under generally accepted levels. In conclusion, the ANN model presented its applicability to the thermal control algorithm for setting up the most energy-efficient setback temperature.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.19-28
• /
• 2022

Recently, cryptocurrency has attracted much attention, and price prediction studies of cryptocurrency have been actively conducted. Especially, efforts to improve the prediction performance by applying the deep learning model are continuing. LSTM (Long Short-Term Memory) model, which shows high performance in time series data among deep learning models, is applied in various views. However, it shows low performance in cryptocurrency price data with high volatility. Although, to solve this problem, new input features were found and study was conducted using them, there is a lack of study on input features that drop predictive performance. Thus, in this paper, we collect the recent trends of six cryptocurrencies including Bitcoin and Ethereum and analyze effects of input features on the cryptocurrency price predictive performance through statistics and deep learning. The results of the experiment showed that cryptocurrency price predictive performance the best when open price, high price, low price, volume and price were combined except for rate of closing price fluctuation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.9
• /
• pp.5455-5459
• /
• 2013

Background: The risk of malignancy index (RMI) for the evaluation of adnexal masses is a sensitive tool in certain populations. The best cut off value for RMI 1, 2 and 3 is 200. The cut off value of RMI-4 to differentiate benign from malignant lesions is 450. Our aim was to evaluate the efficiency of four different malignancy indexes (RMI1-4) in a homogeneous population. Materials and Methods: We evaluated a total of 153 non-pregnant women with adnexal masses who did not have a history of malignancy and who were above 18 years of age. Results: A cut-off value of 250 for RMI-1 provided 95.9% inter-observer agreement, yielding 95.9% specificity, 93.5% negative predictive value, 75.0% sensitivity and 82.8% positive predictive value. A cut-off value of 250 for RMI-1 showed high performance in preoperative diagnosis of invasive malignant lesions than cut-off value of 200 in our population. A cut-off value of 350 for RMI-2 provided 94.5% inter-observed agreement, yielding 94.2% specificity, 93.4% negative predictive value, 75.0% sensitivity and 77.4% positive predictive value. RMI-2 showed the higher performance when the cut-off value was set at 350 in our population. A cut-off value of 250 provided 95.2% inter-observer agreement, yielding 95.0% specificity, 93.2% negative predictive value, 75.0% sensitivity, and 88.0% positive predictive value. RMI-3 showed the highest performance to diagnose malignant adnexal masses when the cut-off value was set at 250. In our study, RMI-4 showed similar statistical performance when the cut-off value was set at 400 [(Kappa: 0.684/p=0.000), yielding 93.8% inter-observer agreement, 93.4% specificity, 93.4% negative predictive value, 75.0% sensitivity, and 75.0% negative predictive value]. Conclusions: We showed successful utilization of RMIs in preoperative differentiation of benign from malignant masses. Many studies conducted in Asian and Pacific countries have reported different cut-off values as was the case in our study. We think that it is difficult to determine universally accepted cut-off values for RMIs for common use around the globe.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.445-454
• /
• 2017

The performance of spatial downscaling models depends on the quality of input coarse scale products. Thus, the impact of intrinsic errors contained in coarse scale satellite products on predictive performance should be properly assessed in parallel with the development of advanced downscaling models. Such an assessment is the main objective of this paper. Based on a synthetic satellite precipitation product at a coarse scale generated from rain gauge data, two synthetic precipitation products with different amounts of error were generated and used as inputs for spatial downscaling. Geographically weighted regression, which typically has very high explanatory power, was selected as the trend component estimation model, and area-to-point kriging was applied for residual correction in the spatial downscaling experiment. When errors in the coarse scale product were greater, the trend component estimates were much more susceptible to errors. But residual correction could reduce the impact of the erroneous trend component estimates, which improved the predictive performance. However, residual correction could not improve predictive performance significantly when substantial errors were contained in the input coarse scale data. Therefore, the development of advanced spatial downscaling models should be focused on correction of intrinsic errors in the coarse scale satellite product if a priori error information could be available, rather than on the application of advanced regression models with high explanatory power.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.7
• /
• pp.85-93
• /
• 2020

In peer-to-peer (P2P) loan markets, as most lenders are unskilled and inexperienced ordinary individuals, it is important to know the characteristics of borrowers that significantly impact their repayment performance. This study investigates the effects and importance of borrowers' past repayment performance track record within the platform to identify its predictive power. To this end, I analyze the detailed loan repayment data from two leading P2P lending platforms in Korea using a Cox proportional hazard, multiple linear regression, and logit models. Furthermore, the predictive power of the factors proxied by borrowers' track records are evaluated through the receiver operating characteristic (ROC) curves. As a result, it is found that the borrowers' past track record within the platform have the most important impact on the repayment performance of their current loans. In addition, this study also reveals that the borrowers' track record is much more predictive of their repayment performance than any other factor. The findings of this study emphasize that individual lenders must take into account the quality of borrowers' past transaction history when making a funding decision, and that platform operators should actively share the borrowers' past records within the markets with lenders.