• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.505-507
• /
• 2004

This paper attempts to compensate the nonlinearity between the input voltage and the output displacement of the piezoelectric stack in dynamic actuation by the following two ways. Firstly, the charge steering by circuit configuration reduces the hysteresis of piezoelectric actuator remarkably. However, it makes the ripple in positioning due to the phase lag and noise induced from the elements of the long closed loop. Secondly, the feedforward control by neural network compensates the hysteresis of the piezoelectric actuators effectively with the appropriate selection of the input variables for the training. The improvement of the dynamic performance of the piezoelectric actuators by the developed linearization technique is verified by experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.246-249
• /
• 2007

In numerical analysis for phase change material, numerical values of thermodynamic properties such as temperature, pressure, specific volume, enthalpy and entropy are required. But the steam table or diagram itself cannot be used without modelling. In this study applicability of neural networks in modelling superheated vapor region of water was examined by comparing with the quadratic spline. neural network consists of an input layer with 2 nodes, two hidden layers and an output layer with 3 nodes. Quadratic spline interpoation method was also applied for comparison. Neural network model revealed smaller percentage error to quadratic spline interpolation. From these results, it is confirmed that the neural networks could be powerful method in modelling the superheated range of the steam table.

• Journal of Integrative Natural Science
• /
• 제4권3호
• /
• pp.238-242
• /
• 2011

For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. The system that uses the artificial neural network(ANN) falls in a local minima when it learns many nonlinear data, and its classification accuracy ratio becomes low. To make up for this risk, the SVM/ANN hybrid algorithm is proposed in this paper. The proposed algorithm is the method that ANN learns selectively after clustering the SNR data by SVM, then more improved performance estimation can be obtained than using ANN only and The proposed algorithm can make the higher classification accuracy by decreasing the nonlinearity of the massive data during the training procedure. Experimental results indicate that the proposed SVM/ANN hybrid algorithm generally outperforms ANN algorithm.

• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.48-54
• /
• 2023

Nowadays, a blind man finds it very difficult to cross the roads. They should be very vigilant with every step they take. To resolve this problem, Convolutional Neural Networks(CNN) is a best method to analyse the data and automate the model without intervention of human being. In this work, a traffic signal recognition system is designed using CNN for the visually impaired. To provide a safe walking environment, a voice message is given according to light state and timer state at that instance. The developed model consists of two phases, in the first phase the CNN model is trained to classify different images captured from traffic signals. Common Objects in Context (COCO) labelled dataset is used, which includes images of different classes like traffic lights, bicycles, cars etc. The traffic light object will be detected using this labelled dataset with help of object detection model. The CNN model detects the color of the traffic light and timer displayed on the traffic image. In the second phase, from the detected color of the light and timer value a text message is generated and sent to the text-to-speech conversion model to make voice guidance for the blind person. The developed traffic light recognition model recognizes traffic light color and countdown timer displayed on the signal for safe signal crossing. The countdown timer displayed on the signal was not considered in existing models which is very useful. The proposed model has given accurate results in different scenarios when compared to other models.

• Journal of the Korean Society for Precision Engineering
• /
• 제14권5호
• /
• pp.118-127
• /
• 1997

In this study, We use microstep control to reduce vibration of step motor. Microstep control of step motor is usually thought of as an extension of conventional step motor control technology. The essence of micro stepping is that we divide the full step of a step motor into a number of substep called microstep and cause the stepmotor to move through a substep per input pulse. In ideal case, by controlling the individual phase currents of a two-phase step motor sinusoidally we can get uniform torque and step angle. But due to the nonlinear characteristics of the step motor, we need to compensate current waveform to improve the over-all smoothness of the conventional micro stepping system. We implement digital Pulse Width Modul- ation (PWM) driver to drive step motor and microphone was used for detecting vibration. Driver enables speed change automatically by increasing or decreasing micro stepping ratio which we call Automatic Switching on the Fly. To compensate the torque harmonics, neural network is applied to the system and we found compensated optimal input current waveform. Finally we can get smooth motion of step motor in a wide range of motor speed.

• Journal of Electrical Engineering and Technology
• /
• 제2권4호
• /
• pp.485-493
• /
• 2007

This paper deals with the problem of detection of induction motor incipient faults. Artificial Neural Network (ANN) approach is applied to detect two types of incipient faults (1). Interturn insulation and (2) Bearing wear faults in single-phase induction motor. The experimental data for five measurable parameters (motor intake current, rotor speed, winding temperature, bearing temperature and the noise) is generated in the laboratory on specially designed single-phase induction motor. Initially, the performance is tested with two inputs i.e. motor intake current and rotor speed, later the remaining three input parameters (winding temperature, bearing temperature and the noise) were added sequentially. Depending upon input parameters, the four ANN based fault detectors are developed. The training and testing results of these detectors are illustrated. It is found that the fault detection accuracy is improved with the addition of input parameters.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• 제51권4호
• /
• pp.211-218
• /
• 2002

We propose a intelligent controller for FACTS device to stabilize a power system. In order to identify the nonlinear characteristics of the power system and to estimate a control signal, an artificial neural network is utilized. Parameter and location of Unified Power Flow Controller(UPFC) on power system operating conditions are discussed. A UPFC is composed of an excitation transformer, a boosting, two three-phase GTO based voltage source converters, and a dc link capacitor. The proposed controller is applied to UPFC to verified the effectiveness of the proposed control system. The results show that the proposed nonlinear FACTS controller is able to enhance the transient stability of a three machine and nine bus system.

• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.119-126
• /
• 2024

Disease caused by the coronavirus (COVID-19) is sweeping the globe. There are numerous methods for identifying this disease using a chest imaging. Computerized Tomography (CT) chest scans are used in this study to detect COVID-19 disease using a pretrain Convolutional Neural Network (CNN) ResNet50. This model is based on image dataset taken from two hospitals and used to identify Covid-19 illnesses. The pre-train CNN (ResNet50) architecture was used for feature extraction, and then fully connected layers were used for classification, yielding 97%, 96%, 96%, 96% for accuracy, precision, recall, and F1-score, respectively. When combining the feature extraction techniques with the Back Propagation Neural Network (BPNN), it produced accuracy, precision, recall, and F1-scores of 92.5%, 83%, 92%, and 87.3%. In our suggested approach, we use a preprocessing phase to improve accuracy. The image was enhanced using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, which was followed by cropping the image before feature extraction with ResNet50. Finally, a fully connected layer was added for classification, with results of 99.1%, 98.7%, 99%, 98.8% in terms of accuracy, precision, recall, and F1-score.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 한국복합재료학회 2003년도 춘계학술발표대회 논문집
• /
• pp.14-17
• /
• 2003

Vibration control of a composite plate with a surface-bonded fiber Bragg grating (FBG) sensor and piezoceramic actuators has been performed using a neural network based adaptive predictive control algorithm. For the detection of Bragg wavelength changes, two cavity lengths in Fabry-Perot read-out interferometers are used in order to produce two quadrature phase shifted signals. The FBG sensor system and real-time neuro-adaptive control algorithm could be applicable to diverse dynamic systems.

• International Journal of Quality Innovation
• /
• 제6권1호
• /
• pp.109-118
• /
• 2005

The parameter design is the most emphasized measure by researchers for a new products development. It is critical for makers to achieve simultaneously in both the time-to-market production and the quality enhancement. However, there are difficulties in practical application, such as (1) complexity and nonlinear relationships co-existed among the system's inputs, outputs and control parameters, (2) interactions occurred among parameters, (3) where the adjustment factors of Taguchi's two-phase optimization procedure cannot be sure to exist in practice, and (4) for some reasons, the data became lost or were never available. For these incomplete data, the Taguchi methods cannot treat them well. Neural networks have a learning capability of fault tolerance and model free characteristics. These characteristics support the neural networks as a competitive tool in processing multivariable input-output implementation. The successful fields include diagnostics, robotics, scheduling, decision-making, prediction, etc. This research is a case study of spherical annealing model. In the beginning, an original model is used to pre-fix a model of parameter design. Then neural networks are introduced to achieve another model. Study results showed both of them could perform the highest spherical level of quality.