• Smart Structures and Systems
• /
• v.25 no.4
• /
• pp.459-469
• /
• 2020

The presence of cracks in mechanical components is a very important problem that, if it is not detected on time, can lead to high economic costs and serious personal injuries. This work presents a methodology focused on identifying cracks in unbalanced rotors, which are some of the most frequent mechanical elements in industry. The proposed method is based on Artificial Neural Networks that give a solution to the presented inverse problem. They allow to estimate unknown crack parameters, specifically, the crack depth and the eccentricity angle, depending on the dynamic behavior of the rotor. The necessary data to train the developed Artificial Neural Network have been obtained from the frequency spectrum of the displacements of the well- known cracked Jeffcott rotor model, which takes into account the crack breathing mechanism during a shaft rotation. The proposed method is applicable to any rotating machine and it could contribute to establish adequate maintenance plans.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.8
• /
• pp.816-824
• /
• 1991

It is well known that dynamic control is needed for fast and accurate control. Neural networks are ideal for representing the strongly nonlinear relationship in the dynamic equations including complex unmodeled effects. It thus creates many advantages over conventional methods such as simple, fast and accurate control through neural network's inherent learning and massive parallelism. In this paper, dynamic control of the full six degrees of freedom of an industrial robot arm will be presented using neural networks. Moreover, through application to a real robot the usefulness of neurocontrol is demonstrated. The back propagation and feedback-error learning is used to train the neurocontroller. Simulated control of a PUMA 560 arm demonstrates that it moves at high speed with good accuracy and generalizes over untrained trajectories as well as adapt to unforseen load changes and sensor noise.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.564-568
• /
• 1992

A neural optimization network is designed to solve the collsion-free inverse kinematics problem for redundant robot manipulators under the constraints of joint limits, maximum velocities and maximum accelerations. And the fuzzy rules are proposed to determine the weightings of neural optimization networks to avoid the collision between robot manipulator and obstacles. The inputs of fuzzy rules are the resultant distance, change of the distance and sum of the changes. And the output of fuzzy rules is defined as the capability of collision avoidance of joint differential motion. The weightings of neural optimization networks are adjusted according to the capability of collision avoidance of each joint. To show the validities of the proposed method computer simulation results are illustrated for the redundant robot with three degrees of freedom,

• Structural Engineering and Mechanics
• /
• v.30 no.6
• /
• pp.679-698
• /
• 2008

On marine vessels, delicate instruments such as navigation radars are normally mounted on ship masts. However the vibrations at the top of mast where the radar is mounted often cause serious deterioration in radar-tracking resolution. The most serious problem is caused by the rotational vibrations at the top of mast that may be due to wind loading, inertial loading from ship rolling and base excitations induced by the running propeller. This paper presents a method of semi-active vibration control using magneto-rheological (MR) dampers to reduce the rotational vibration of the mast. In the study, the classical optimal control algorithm, the independent modal space control algorithm and the double input - single output fuzzy control algorithm are employed for the vibration control. As the phenomenological model of an MR damper is highly nonlinear, which is difficult to analyse, a back- propagation neural network is trained to emulate the inverse dynamic characteristics of the MR damper in the analysis. The trained neural network gives the required voltage for each MR damper based on the displacement, velocity and control force of the MR damper quickly. Numerical simulations show that the proposed control methods can effectively suppress the rotational vibrations at the top of mast.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.8
• /
• pp.186-192
• /
• 1999

This paper introduces a study of a method for the forward kinematic analysis, which finds the 6 DOF motions and velocities from the given six cylinder lengths in the Stewart platform. From the viewpoints of kinematics, the solution for the inverse kinematic is easily found by using the vectors of the links which are composed of the joint coordinates in base and plate frames, to act contrary to the serial manipulator, but forward kinematic is difficult because of the nonlinearity and complexity of the Stewart platform dynamic equation with the multi-solutions. Hence we, first in this study, introduce the linear estimator using the Luenberger's observer, and the estimator using the nonlinear measured model for the forward kinematic solutions. But it is difficult to find the parameter of the design for the estimation gain or to select the estimation gain and the constant steady state error exists. So this study suggests the estimator with the estimation gain to be learned by the neural network with the structure of multi-perceptron and the learning method using back propagation and shows the estimation performance using the simulation.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2019

Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.6
• /
• pp.1574-1580
• /
• 2008

In this paper, to bring under robust and accurate control of auto-equipment systems which disturbance, parameter alteration of system, uncertainty and so forth exist, neural network controller called dynamic neural processor(DNP) is designed In order to perform a elaborate task like as assembly, manufacturing and so forth of components, tracking control on the trajectory of power coming in contact with a target as well as tracking control on the movement course trajectory of end-effector is indispensable. Also, the learning architecture to compute inverse kinematic coordinates transformations in the Plants of auto-equipment systems is developed and the example that DNP can be used is explained. The architecture and learning algorithm of the proposed dynamic neural network, the DNP, are described and computer simulations are provided to demonstrate the effectiveness of the proposed learning method using the DNP.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.2
• /
• pp.171-177
• /
• 2002

In this paper, we propose a new data fusion method to improve the performance of individual prediction models for time series data. Individual models used are ARIMA and neural network and their results are combined based on the weight reflecting the inverse of EWMA of squared prediction error of each individual model. Monte Carlo simulation is used to identify the situation where the proposed approach can take a vintage point over typical fusion methods which utilize MSE for weight. Study results indicate the following: EWMA performs better than MSE fusion when the data size is large with a relatively big amplitude, which is often observed in intra-cranial pressure data. Additionally, EWMA turns out to be a best choice among MSE fusion and the two individual prediction models when the data size is large with relatively small random noises, often appearing in tax revenue data.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.1042-1046
• /
• 1993

This paper describes a control scheme for a robot manipulator system which uses visual information to position and orientate the end-effector. In this scheme, the position and orientation of the target workpiece with respect to the base frame of the robot are assumed to be unknown, but the desired relative position and orientation of the end-effector to the target workpiece are given in advance. The control scheme directly integrates visual data into the servoing process without subdividing the process into determination of the position and orientation of the workpiece and inverse kinematics calculation. A neural network system is used for determining the change in joint angles required in order to achieve the desired position and orientation. The proposed system can be control the robot so that it approach the desired position and orientation from arbitrary initial ones. Simulation for the robot manipulator with six degrees of freedom will be done. The validity and the effectiveness of the proposed control scheme will be verified by computer simulations.