• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1652-1662
• /
• 1995

In this paper, a hybrid neural network is proposed to improve the learning ability of a neural network. The union of the characteristics of a Self-Organizing Neural Network model and of multi-layer perceptron model using the backpropagation learning method gives us the advantage of reduction of the learning error and the learning time. In learning process, the proposed hybrid neural network reduces the number of nodes in hidden layers to reduce the calculation time. And this proposed neural network uses the fuzzy feedback values, when it updates the responding region of each node in the hidden layer. To show the effectiveness of this proposed hybrid neural network, the boolean function(XOR, 3Bit Parity) and the solution of inverse kinematics are used. Finally, this proposed hybrid neural network is applied to the visual tracking control of a PUMA560 robot, and the result data is presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.144-148
• /
• 1989

We solve the inverse kinematics problems in robotics by employing a neural network. In the practical situation. it is not easy to obtain the exact inverse kinematics solution, since there are many unforeseen errors such as the shift of a robot base the link's bending, et c. Hence difficulties follow in the trajectory planning. With the neural network, it is possible to train the robot motion so that the robot follows the desired trajectory without errors even under the situation where the unexpected errors are involved. In this work, Back-Propagation rule is used as a learning method.

• International Journal of Control, Automation, and Systems
• /
• 제4권1호
• /
• pp.17-29
• /
• 2006

A novel inverse kinematics solution based on the back propagation neural network (NN) for redundant manipulators is developed for online obstacles avoidance. A laser transducer at the end-effctor is used for online planning the trajectory. Since the inverse kinematics in the present problem has infinite number of joint angle vectors, a fuzzy reasoning system is designed to generate an approximate value for that vector. This vector is fed into the NN as a hint input vector rather than as a training vector to guide the output of the NN. Simulations are implemented on both three- and four-link redundant planar manipulators to show the effectiveness of the proposed position control system.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.172-175
• /
• 2004

Generally, the yield rate of semiconductors is the major factor that affects directly the price of semiconductors. For a high yield rate of semiconductors, the air inside clean room is needed to be purified and high efficient filters are used for this. The filter are made of super-fine fiber and certain pinholes can be easily produced on the filter's surface by inadvertent manufacturing. As these pinholes are not easily detected with the bare sight, these pinholes exert a negative impact to filtration performance of the filter. In this research, not only the automatic test equipment for detecting pinholes is proposed, but also inverse modeling scheme based on artificial neural network is applied for tuning of its important parameters.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.431-431
• /
• 2000

The modeling of 5-bar linkage robot manipulator dynamics by means of a mathematical and neural architecture is presented. Such a model is applicable to the design of a feedforward controller or adjustment of controller parameters. The inverse model consists of two parts: a mathematical part and a compensation part. In the mathematical part, the subsystems of a 5-bar linkage robot manipulator are constructed by applying Kawato's Feedback-Error-Learning method, and trained by given training data. In the compensation part, MLP backpropagation algorithm is used to compensate the unmodeled dynamics. The forward model is realized from the inverse model using the inverse of inertia matrix and the compensation torque is decoupled in the input torque of the forward model. This scheme can use tile mathematical knowledge of the robot manipulator and analogize the robot characteristics. It is shown that the model is reasonable to be used for design and initial gain tuning of a controller.

• 한국생산제조학회지
• /
• 제26권4호
• /
• pp.402-409
• /
• 2017

Selection of optimal cutting conditions is important for improving productivity and implementing efficient process control in metal machining. In this study, improvement of cutting conditions in machining using end-mills is studied by using deep-layered neural networks, which comprise an input layer, output layer, and two hidden layers. System networks are designed with inputs as cutting conditions, and they output the cutting force. A pseudo-inverse network is designed that has the adjustable cutting condition as output and cutting force and other cutting conditions as input. The combination of the system network and pseudo-inverse network enables selection or improvement of cutting conditions that results in the expected cutting force.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.41.5-41
• /
• 2001

A novel method is introduced for determining the weights of a regularization network which approximates one-to-many mapping. A conventional neural network will converges to the average value when outputs are multiple for one input. The capability of proposed network is demonstrated by an example of learning inverse mapping.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.182-186
• /
• 2004

This paper describes an advanced compensation for non-linear functions designed to remove steering aberrations from phased array antennas. This system alters the steering command applied to the antenna in a way that the appropriate angle commands are given to the array steering software for the antenna to point to the desired position instead of squinting. Artificial neural networks are used to develop the inverse function necessary to correct the aberration. Also a straightforward antenna steering function is implemented with neural networks for the 9-term polynomials of forward steering function. In all cases the aberration is removed resulting in small RMS angular errors across the operational angle space when the actual antenna position is compared with the desired position. The use of neural network model provides a method of producing a non-linear system that can correct antenna performance and demonstrates the feasibility of generating an inverse steering algorithm.

• 대한전기학회논문지
• /
• 제39권10호
• /
• pp.1121-1232
• /
• 1990

A hierarchical neural network structure is described for robot PTP trajectory planning. In the first level, the multi-layered Perceptron neural network is used for the inverse kinematics with the back-propagation learning procedure. In the second level, a saccade generation model based joint trajectory planning model in proposed and analyzed with several features. Various simulations are performed to investigate the characteristics of the proposed neural networks.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.476-479
• /
• 1992

This paper presents a neural network method for tuning PlD controller of a time-varying process. Three gains of PlD controller are tuned for a certain desirable response pattern by back-propagation neural network. The neural network is trained using changes of output features vs. changes of PlD gains. But sometimes it needs longer training time and larger structure to train the correlation between the process and controller on entire region of the process. The difficulty in system identification is that the inverse function of the system can not be clearly stated. To cope with the problem, we do not train the neural network to respond correctly for the entire regions but train for only local region where the system is heading toward by training the neural network and tuning of the PlD controller. It may be trained for fine-tuning itself. Simulation results show that the adaptive PID controller using neural network trained in the local area performs remarkably for time-varying second order process.