• 전력전자학회:학술대회논문집
• /
• 전력전자학회 1999년도 전력전자학술대회 논문집
• /
• pp.526-530
• /
• 1999

This paper presents a newly developed speed sensorless drive using Neural Network algorithm. Neural Network algorithm can be divided into three categories. In the first one, a Back Propagation-based NN algorithm is well-known to gradient descent method. In the second scheme, a Extended Kalman Filter-based NN algorithm has just the time varying learning rate. In the last scheme, a Recursive Least Square-based NN algorithm is faster and more stable than the classical back-propagation algorithm for training multilayer perceptrons. The number of iterations required to converge and the mean-squared error between the desired and actual outputs is compared with respect to each method. The theoretical analysis and experimental results are discussed.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 춘계학술대회 학술발표 논문집 제15권 제1호
• /
• pp.217-220
• /
• 2005

The RPO algorithm is a recently developed tool in the area of reinforcement Loaming, And it has been shown In be very successful in several application problems. In this paper, we consider a robot-control problem utilizing a modified RPO algorithm in which its critic network is adapted via RLS(Recursive Least Square) algorithm. We also developed a MATLAB-based animation program, by which the effectiveness of the training algorithms were observed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.215-220
• /
• 1998

In order to optimize fuzzy model, we use the optimal algorithm with a hybrid type in the identification of premise parameters and standard least square method in the identification of consequence parameters of a fuzzy model. The hybrid optimal identification algorithm is carried out using a genetic algorithm and improved complex method. Also, the performance index with weighting factor is proposed to achieve a balance between the insults of performance for the training and testing data. Several numerical examples are used to evaluate the performance of the proposed model.

• 자원리싸이클링
• /
• 제27권1호
• /
• pp.84-91
• /
• 2018

본 연구에서는 레이저유도 플라즈마 분광법(Laser induced breakdown spectroscopy, LIBS) 기반의 금속 종류별 스펙트럼 데이터를 이용하여 연성정보(soft information)를 추정하고 최빈 클래스로 분류하는(most probable classification) 금속 분류 방법을 제안한다. 폐금속 자원과 같이 사전 정보가 없는 금속을 분류하는 경우 몇 가지 핵심 구성성분에 대한 정량 분석을 통해서 클래스를 추정하는 방법이 효율적이다. 이에 따라 부분 집합 기반의 부분최소제곱회귀법(Partial Least Square Regression, PLSR)을 이용하여 LIBS 검출 스펙트럼으로부터 각 성분의 농도를 독립적으로 신뢰성 있게 추정하고, 인증 표준물질(CRM) 등 알려진 모집합의 농도정보에 기반하여 최고 확률을 갖도록 분류하는 기술을 제안한다. 샘플 스펙트럼들의 다변량 분석을 통해서 여러 성분의 추정 농도를 다변량 정규 분포를 갖는 것으로 가정하고 통합(Joint) 추정 연성정보를 구할 수 있으며, 이를 활용한 최빈 확률 검출이나 추가적인 사전 정보의 결합 등을 통해서 분류 성능을 향상시킬 수 있다. 제안된 기술의 평가를 위해서 9가지 종류의 CRM 금속시료의 LIBS 스펙트럼 데이터를 사용하며, 부분 집합 기반의 PLSR 농도 추정 기술을 기반으로 단변량 혹은 다변량 정규 분포 연성 정보추정을 통해 미지 금속의 검출과 연성 정보의 검출 등을 테스트 하였다. 또한 방사형 차트(Radar chart)를 이용하여 추정된 농도와 획득한 연성정보를 효과적으로 시각화함으로써 기존 라이브러리에 포함된 부분 집합의 금속과 비교하여 해당 금속과의 유사성을 그래프를 통해 추정할 수 있다.

• Natural Product Sciences
• /
• 제24권3호
• /
• pp.164-170
• /
• 2018

Rapid geographical classification of Bupleuri Radix is important in quality control. In this study, near infrared spectroscopy (NIRS) combined with supervised pattern recognition was attempted to classify Bupleuri Radix according to geographical origins. Three supervised pattern recognitions methods, partial least square discriminant analysis (PLS-DA), quadratic discriminant analysis (QDA) and radial basis function support vector machine (RBF-SVM), were performed to establish the classification models. The QDA and RBF-SVM models were performed based on principal component analysis (PCA). The number of principal components (PCs) was optimized by cross-validation in the model. The results showed that the performance of the QDA model is the optimum among the three models. The optimized QDA model was obtained when 7 PCs were used; the classification rates of the QDA model in the training and test sets are 97.8% and 95.2% respectively. The overall results showed that NIRS combined with supervised pattern recognition could be applied to classify Bupleuri Radix according to geographical origin.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제53권3호
• /
• pp.188-195
• /
• 2004

This paper presents neural load torque observer that is used to deadbeat load torque observer and gain compensation by parameter estimator As a result, the response of the PMSM(permanent magnet synchronous motor) follows that nominal plant. The load torque compensation method is composed of a neural deadbeat observer To reduce the noise effect, the post-filter implemented by MA(moving average) process, is adopted. The parameter compensator with RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller The parameter estimator is combined with a high performance neural load torque observer to resolve the problems. The neural network is trained in on-line phases and it is composed by a feed forward recall and error back-propagation training. During the normal operation, the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against the load torque and the Parameter variation. A stability and usefulness are verified by computer simulation and experiment.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권3호
• /
• pp.323-331
• /
• 2020

The study aims to assess the impact of foreign direct investment (FDI) and international trade (export and import) on Vietnam's economic growth for the 2000-2018 period. Secondary data is taken from the General Statistics Office of Vietnam. Ordinary least-square method is used in analyzing the impact of FDI, export and import on economic growth of Vietnam. Empirical test results show that FDI and international trade are related to Vietnam's economic growth. However, each economic variable has a different impact. FDI has a positive and statistically significant influence on economic growth of Vietnam. Export also has positive and statistically significant impact to the economic growth, while import has a negative but not statistically significant effect. The result is useful for the policy makers of Vietnam on foreign economic relations. In order to improve the effect of FDI and international trade on growth of the economy, the government of Vietnam should: (1) continue applying preferential policies to attract FDI; (2) select foreign investors aiming to quality, efficiency, high technology and environmental protection; (3) continue pursuing export-oriented policy; (4) enhance the added value of exported goods and control the type of imported goods; (5) further liberalize trade through signing and implementation of international trade commitments.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권6호
• /
• pp.789-799
• /
• 1999

In this paper, the optimization of fuzzy inference systems is proposed for fuzzy model of nonlinear systems. A fuzzy model needs to be identified and optimized by means of the definite and systematic methods, because a fuzzy model is primarily acquired by expert's experience. The proposed rule-based fuzzy model implements system structure and parameter identification using the HCM(Hard C-mean) clustering method, genetic algorithms and fuzzy inference method. Two types of inference methods of a fuzzy model are the simplified inference and linear inference. in this paper, nonlinear systems are expressed using the identification of structure such as input variables and the division of fuzzy input subspaces, and the identification of parameters of a fuzzy model. To identify premise parameters of fuzzy model, the genetic algorithms is used and the standard least square method with the gaussian elimination method is utilized for the identification of optimum consequence parameters of fuzzy model. Also, the performance index with weighting factor is proposed to achieve a balance between the performance results of fuzzy model produced for the training and testing data set, and it leads to enhance approximation and predictive performance of fuzzy system. Time series data for gas furnace and sewage treatment process are used to evaluate the performance of the proposed model.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권9호
• /
• pp.707-717
• /
• 2020

Global warming affects climate change and has an overall impact on all aspects of life. On the other hand, community behavior and disaster aspects also have an important role in people's lives. This will also have an impact on regional development. This study aims to find the effect of climate, disaster, and social community on rural development. This study uses data on the potential of rural development from PODES 2014, and 2018 data collection on climate conditions and regional status is sourced from relevant ministries. This research uses Ordinary Least Square (OLS) Regression Analysis method, then continued with CHAID analysis to find the segmentation of the role of climate, disaster, and social factors on rural development. The results of this study found that all research regressor variables significantly influence the Rural Development Index (IPD2018), with an R-squared value of 32.9 percent. Efforts need to be taken in order to implement policies that are targeted, effective, and efficient. The results of this study can be a reference for the government in determining policies by focusing on rural development that have high duration of sunshine, cultivating natural disaster warnings, especially in areas prone to natural disasters, and need to focus on underdeveloped areas.

• Journal of Power Electronics
• /
• 제8권4호
• /
• pp.354-362
• /
• 2008

This paper presents neural load torque compensation method which is composed of a deadbeat load torque observer and gains compensation by a parameter estimator. As a result, the response of the PMSM (permanent magnet synchronous motor) obtains better precision position control. To reduce the noise effect, the post-filter is implemented by a MA (moving average) process. The parameter compensator with an RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller. The parameter estimator is combined with a high performance neural load torque observer to resolve problems. The neural network is trained in online phases and it is composed by a feed forward recall and error back-propagation training. During normal operation, the input-output response is sampled and the weighting value is trained multi-times by the error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against load torque and parameter variation. Stability and usefulness are verified by computer simulation and experiment.