• 전자공학회논문지B
• /
• 제29B권8호
• /
• pp.15-23
• /
• 1992

Neural network control has many innovative potentials for fast, accurate and intelligent adaptive control. In this paper, two kinds of neurocontrol architectures for the dynamic control of robot manipulators are developed. One is based on a System Identification and Control scheme and the other is based on the Feedback-Error leaming scheme. Both of the proposed architectures use an inverse dynamic neurocontroller in parallel with a linear neurocontroller. The difference is that the first architecture uses the system identifier to get the signals used for training neurocontrollers, while the second architecture uses a properly defined energy function. Compared with the previous types of neurocontrollers which are using an inverse dynamic neurocontroller and a fixed PD gain controller, the proposed architectures not only eliminate the painful process of the fixed gain tuning but also exhibit superior peformances because the linear neurocontroller can adapt its gains according to the applied task. This superior performance is tested and verified through computer simulation of the dynamic control of the PUMA 560 arm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2372-2377
• /
• 2003

Nonlinear dynamic system exist widely in many types of systems such as chemical processes, biomedical processes, and the main steam temperature control system of the thermal power plant. Up to the present time, PID Controllers have been used to operate these systems. However, it is very difficult to achieve an optimal PID gain with no experience, because of the interaction between loops and gain of the PID controller has to be manually tuned by trial and error. This paper suggests control approaches by immune fuzzy for the nonlinear control system inverted pendulum, through computer simulation. This paper defines relationship state variables $x,{\dot{x}},{\theta},\dot{\theta}$ using immune fuzzy and applied its results to stability.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.280-285
• /
• 1991

Neural network control has many innovative potentials for fast, accurate and intelligent adaptive control. In this paper, a learning control architecture for the dynamic control of a robot manipulator is developed using inverse dynamic neurocontroller and linear neurocontroher. The inverse dynamic neurocontrouer consists of a MLP (multi-layer perceptron) and the linear neurocontroller consists of SLPs (single layer perceptron). Compared with the previous type of neurocontroller which is using an inverse dynamic neurocontroller and a fixed PD gain controller, proposed architecture shows the superior performance over the previous type of neurocontroller because linear neurocontroller can adapt its gain according to the applied task. This superior performance is tested and verified through the control of PUMA 560. Without any knowledge on the dynamic model, its parameters of a robot , (The robot is treated as a complete black box), the neurocontroller, through practice, gradually and implicitly learns the robot's dynamic properties which is essential for fast and accurate control.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권2호
• /
• pp.146-156
• /
• 2003

Nonlinear dynamic system exist widely in many types of systems such as chemical processes, biomedical processes, and the main steam temperature control system of the thermal power plant. Up to the present time, PID Controllers have been used to operate these systems. However, it is very difficult to achieve an optimal PID gain with no experience, because of the interaction between loops and gain of the PID controller has to be manually tuned by trial and error. This paper suggests control approaches by immune fuzzy for the nonlinear control system inverted pendulum, through computer simulation. This paper defines relationship state variables $x,\dot{x},{\theta},\dot{\theta}$ using immune fuzzy and applied its results to stability.

• Journal of Radiation Protection and Research
• /
• 제46권4호
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• 융합신호처리학회논문지
• /
• 제3권1호
• /
• pp.74-79
• /
• 2002

많은 제어기법들이 이산시간영역제어계에서 제어성능을 개선하기 위해서 제안되고 있다. 이 제어기법들을 이용한 제어계에서 계의 응답특성은 제어기의 이득에 관계한다. 특히 외란이나 부하변동에 의해서 계의 응답이 변할 때 제어기의 이득을 재조정할 필요가 있다. 본 논문에서는 다층 신경망으로 I-PD제어기와 전치보상기를 설계하였다. I-PD제어기와 전치보상기의 이득이 자동적으로 역전파 알고리즘에 의해서 조정되도록 하였다. 제어계의 응답이 어떤 조건에 의해서 변할 때 I-PD제어기와 전치보상기의 이득들이 역전파 알고리즘에 의해서 자동적으로 조정되게 하였다. 이 I-PD제어기법을 직류 서보 전동기를 구동원으로 하는 위치제어계에 적용하여 제어기의 제어성능을 실험 결과로 타당성을 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 춘계학술대회 논문집 에너지변화시스템부문
• /
• pp.225-227
• /
• 2009

The conventional fixed gain PI controller is very sensitive to step change of command speed, parameter variation and load disturbances. The precise speed control of interior permanent magnet synchronous motor(IPMSM) drive becomes a complex issue due to nonlinear coupling among its winding currents and the rotor speed as well as the nonlinear electromagnetic developed torque. Therefore, there exists a need to tune the PI controller parameters on-line to ensure optimum drive performance over a wide range of operating conditions. This paper is proposed artificial intelligent-PI(AIPI) controller of IPMSM drive using adaptive learning mechanism(ALM) and fuzzy neural network(FNN). The proposed controller is developed to ensure accurate speed control of IPMSM drive under system disturbances and estimation of speed using artificial neural network(ANN) controller. The PI controller parameters are optimized by ALM-FNN at all possible operating condition in a closed loop vector control scheme. The validity of the proposed controller is verified by results at different dynamic operating conditions.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2009년도 춘계학술대회 논문집
• /
• pp.420-423
• /
• 2009

The conventional fixed gain PI controller is very sensitive to step change of command speed, parameter variation and load disturbances. The precise speed control of interior permanent magnet synchronous motor(IPMSM) drive becomes a complex issue due to nonlinear coupling among its winding currents and the rotor speed as well as the nonlinear electromagnetic developed torque. Therefore, there exists a need to tune the PI controller parameters on-line to ensure optimum drive performance over a wide range of operating conditions. This paper is proposed hybrid intelligent-PI(HIPI) controller of IPMSM drive using adaptive learning mechanism(ALM) and fuzzy neural network(FNN). The proposed controller is developed to ensure accurate speed control of IPMSM drive under system disturbances and estimation of speed using artificial neural network(ANN) controller. The PI controller parameters are optimized by ALM-FNN at all possible operating condition in a closed loop vector control scheme. The validity of the proposed controller is verified by results at different dynamic operating conditions.

• 말소리와 음성과학
• /
• 제13권1호
• /
• pp.45-51
• /
• 2021

End-to-end (E2E) automatic speech recognition (ASR) has achieved promising performance gains with the introduced self-attention network, Transformer. However, due to training time and the number of hyperparameters, finding the optimal hyperparameter set is computationally expensive. This paper investigates the impact of hyperparameters in the Transformer network to answer two questions: which hyperparameter plays a critical role in the task performance and training speed. The Transformer network for training has two encoder and decoder networks combined with Connectionist Temporal Classification (CTC). We have trained the model with Wall Street Journal (WSJ) SI-284 and tested on devl93 and eval92. Seventeen hyperparameters were selected from the ESPnet training configuration, and varying ranges of values were used for experiments. The result shows that "num blocks" and "linear units" hyperparameters in the encoder and decoder networks reduce Word Error Rate (WER) significantly. However, performance gain is more prominent when they are altered in the encoder network. Training duration also linearly increased as "num blocks" and "linear units" hyperparameters' values grow. Based on the experimental results, we collected the optimal values from each hyperparameter and reduced the WER up to 2.9/1.9 from dev93 and eval93 respectively.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.158-168
• /
• 2024

There is hardly any person in modern times who has not taken soft drinks instead of drinking water. The rate of people taking soft drinks being surprisingly high, researchers around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases and so on. Therefore, in this work an image-based tool is developed to monitor the nutritional information of soft drinks by using deep convolutional neural network with transfer learning. At first, visual saliency, mean shift segmentation, thresholding and noise reduction technique, collectively known as 'pre-processing' are adopted to extract the location of drinks region. After removing backgrounds and segment out only the desired area from image, we impose Discrete Wavelength Transform (DWT) based resolution enhancement technique is applied to improve the quality of image. After that, transfer learning model is employed for the classification of drinks. Finally, nutrition value of each drink is estimated using Bag-of-Feature (BoF) based classification and Euclidean distance-based ratio calculation technique. To achieve this, a dataset is built with ten most consumed soft drinks in Bangladesh. These images were collected from imageNet dataset as well as internet and proposed method confirms that it has the ability to detect and recognize different types of drinks with an accuracy of 98.51%.