• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1305-1308
• /
• 2003

A new technique is presented to construct a predictive model of plasma etch process. This was accomplished by combining a backpropagation neural network (BPNN) and a genetic algorithm (GA). The predictive model constructed in this way is referred to as a GA-BPNN. The GA played a role of controlling training factors simultaneously. The training factors to be optimized are the hidden neuron, training tolerance, initial weight magnitude, and two gradients of bipolar sigmoid and linear functions. Each etch response was optimized separately. The proposed scheme was evaluated with a set of experimental plasma etch data. The etch process was characterized by a $2^3$ full factorial experiment. The etch responses modeled are aluminum (A1) etch rate, silica profile angle, A1 selectivity, and dc bias. Additional test data were prepared to evaluate model appropriateness. The GA-BPNN was compared to a conventional BPNN. Compared to the BPNN, the GA-BPNN demonstrated an improvement of more than 20% for all etch responses. The improvement was significant in the case of A1 etch rate.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.2
• /
• pp.87-93
• /
• 2019

This research deals with posture optimization for humanoid robot against external forces using genetic algorithm and neural network. When the robot takes a motion to push an object, the torque of each joint is generated by reaction force at the palm. This study aims to optimize the posture of the humanoid robot that will change this torque. This study finds an optimized posture using a genetic algorithm such that torques are evenly distributed over the all joints. Then, a number of different optimized postures are generated from various the reaction forces at the palm. The data is to be used as training data of MLP(Multi-Layer Perceptron) neural network with BP(Back Propagation) learning algorithm. Humanoid robot can find the optimal posture at different reaction forces in real time using the trained neural network include non-training data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.195-195
• /
• 2000

In this paper, intelligent control method using neural network as a nonlinear controller is presented, Neural network controller is implemented on DSP board in PC to make real time computing possible, On-line training algorithm for neural network control is proposed, As a test-bed, a large a-x table was build and interface with PC has been implemented, Experimental results under different PD controller gains show excellent position tracking for circular trajectory compared with those for PD controller only.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.997-1002
• /
• 1994

Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. Those models can effectively normalize the temporal and spatial variability of speech signals. But those models suffer from poor discrimination between acoustically similar words. In this paper, we propose a discriminative training algorithm for predictive neural network models based on a generalized probabilistic descent (GPD) algorithm and minimum classification error formulation (MCEF). The Evaluation of our training algorithm on ten Korean digits shows its effectiveness by 40% reduction of recognition error.

• Water Engineering Research
• /
• v.1 no.2
• /
• pp.129-136
• /
• 2000

Predicting water levels is a difficult task because a lot of uncertainties are included. Therefore the neural network which is appropriate to such a problem, is introduced. One day ahead forecasting of river stage in the Bocheong River is carried out by using the neural network model. Historical water levels at Snagye gauging point which is located at the downstream of the Bocheong River and average rainfall of the Bocheong River basin are selected as training data sets. With these data sets, the training process has been done by using back propagation algorithm. Then waters levels in 1997 and 1998 are predicted with the trained algorithm. To improve the accuracy, a filtering method is introduced as predicting scheme. It is shown that predicted results are in a good agreement with observed water levels and that a filtering method can overcome the lack of training patterns.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.619-623
• /
• 1993

In this paper, a neural network is appled to design a lateral autopilot for airplanes. Linearized lateral dynamics is used in training the neural network controller and verifying the performance as well. To train the neural network, back propagation algorithm is used. In this training, no information about the dynamics to be controlled except sign and rough magnitude of control derivatives is needed. It is shown by computer simulations that the performance and stability margin are satisfactory.

• Journal of information and communication convergence engineering
• /
• v.13 no.2
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.10
• /
• pp.799-807
• /
• 2002

The vibration signal can give an indication of the condition of rotating machinery, highlighting potential faults such as unbalance, misalignment and bearing defects. The features in the vibration signal provide an important source of information for the faults diagnosis of rotating machinery. When additional training data become available after the initial training is completed, the conventional neural networks (NNs) must be retrained by applying total data including additional training data. This paper proposes the fault diagnostics algorithm using the ART-Kohonen network which does not destroy the initial training and can adapt additional training data that is suitable for the classification of machine condition. The results of the experiments confirm that the proposed algorithm performs better than other NNs as the self-organizing feature maps (SOFM) , learning vector quantization (LYQ) and radial basis function (RBF) NNs with respect to classification quality. The classification success rate for the ART-Kohonen network was 94 o/o and for the SOFM, LYQ and RBF network were 93 %, 93 % and 89 % respectively.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.7
• /
• pp.1322-1331
• /
• 1992

The conventional neural networks are built without considering the underlying structure of the problems. Hence, they usually contain redundant weights and require excessive training time. A novel neural network structure is proposed for symmetric problems, which alleviate some of the aforementioned drawback of the conventional neural networks. This concept is expanded to that of the constrained neural network which may be applied to general structured problems. Because these neural networks can not be trained by the conventional training algorithm, which destroys the weight structure of the neural networks, a proper training algorithm is suggested. The illustrative examples are shown to demonstrate the applicability of the proposed idea.

• Journal of Welding and Joining
• /
• v.31 no.5
• /
• pp.35-40
• /
• 2013

In this paper, we propose the Tangible Virtual Reality Representation Method to using haptic device and feature to morphology of created bead from Flux Cored Arc Welding. The virtual reality was started to rising for reduce to consumable materials and welding training risk. And, we will expected maximize virtual reality from virtual welding training. In this paper proposed method is get the database to changing the input factor such as work angle, travelling angle, speed, CTWD. And, it is visualization to bead from extract to optimal morphological feature information to using the Neural Network algorithm. The database was building without error to extract data from automatic robot welder. Also, the Neural Network algorithm was set a dataset of the highest accuracy from verification process in many times. The bead was created in virtual reality from extract to morphological feature information. We were implementation to final shape of bead and overlapped in process by time to using bead generation algorithm and calibration algorithm for generate to same bead shape to real database in process of generating bead. The best advantage of virtual welding training, it can be get the many data to training evaluation. In this paper, we were representation bead to similar shape from generated bead to Flux Cored Arc Welding. Therefore, we were reduce the gap to virtual welding training and real welding training. In addition, we were confirmed be able to maximize the performance of education from more effective evaluation system.