• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.12
• /
• pp.106-112
• /
• 1998

A major problem in automation of turning operations is the difficulty in obtaining a sufficient and reliable chip control. The chip should be detected in order to provide a optimum chip control for unmanned turning operation. Using the difference of energy radiated from the chip, chip Patterns are estimated using pyrometer. From the initial output from the pyrometer, chips are identified according to the backpropagation algorithm developed in the research. The learning system developed in this work can be applied in real-time control of turning process with minor modification in drive system.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.615-624
• /
• 2006

The objective of this paper is to implement parallel multi-layer ANN(Artificial Neural Network) simulator based on the mobile agent system which is executed in parallel in the virtual parallel distributed computing environment. The Multi-Layer Neural Network is classified by training session, training data layer, node, md weight in the parallelization-level. In this study, We have developed and evaluated the simulator with which it is feasible to parallel the ANN in the training session and training data parallelization because these have relatively few network traffic. In this results, we have verified that the performance of parallelization is high about 3.3 times in the training session and training data. The great significance of this paper is that the performance of ANN's execution on virtual parallel computer is similar to that of ANN's execution on existing super-computer. Therefore, we think that the virtual parallel computer can be considerably helpful in developing the neural network because it decreases the training time which needs extra-time.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.3
• /
• pp.64-74
• /
• 2007

The continuous chip in turning operation deteriorates precision of workpiece and causes a hazardous condition to operator. Thus the chip form control becomes a very important task for reliable machining process. So, grooved chip breaker is widely used to obtain reliable discontinuous chip. However, developing new cutting insert having chip breaker takes long time and needs lots of research expense due to a couple of processes such as forming, sintering, grinding and coating of product and many different evaluation tests. In this paper, performance of commercial chip breaker is evaluated with neural network which is learned with a back propagation algorithm. For the evaluation, several important elements(depth of cut, land, breadth, radius) which directly influence the chip formation were chosen among commercial chip breakers and were used as input values of neural network. With the results of these input values, the performance evaluation method was developed and applied that method to the commercial tools.

• Journal of KIISE:Software and Applications
• /
• v.26 no.12
• /
• pp.1383-1392
• /
• 1999

이미 학습된 다층퍼셉트론 신경망을 디지털 VLSI 기술을 사용하여 하드웨어로 구현할 경우 신경망의 가중치 및 뉴런 출력들을 양자화해야 하는 문제가 발생한다. 이러한 신경망 변수들의 양자화는 결과적으로 주어진 입력에 대한 신경망의 최종 출력에서의 왜곡을 초래한다. 본 논문에서는 먼저 이러한 양자화로 인한 신경망 출력에서의 왜곡을 통계적으로 분석하였다. 분석 결과에 의하면 입력패턴 각 성분의 제곱들의 합과 가중치의 크기들이 양자화 영향에 주로 기여하는 것으로 나타났다. 이러한 분석 결과를 이용하여 양자화를 위한 정밀도가 주어졌을 때, 양자화 영향이 최소화된 다층퍼셉트론 신경망을 설계하는 방법을 제시하였다. 그리고 제안된 방법에 의해 얻은 신경망과 오류역전파 학습방법에 의하여 얻은 신경망의 성능을 비교함으로써 제안된 방법의 효율성을 입증하였다. 실험결과는 낮은 양자화 정밀도에서도 제안된 방법이 더 좋은 성능을 보였다.Abstract When we implement a multilayer perceptron with the digital VLSI technology, we generally have to quantize the weights and the neuron outputs. These quantizations eventually cause distortion in the output of the network for a given input. In this paper first we made a statistical analysis about the effect caused by the quantization on the output of the network. The analysis revealed that the sum of the squared input components and the sizes of the weights are the major factors which contribute to the quantization effect. We present a design method for an MLP which minimizes the quantization effect when the precision of the quantization is given. In order to show the effectiveness of the proposed method, we developed a network by our method and compared it with the one developed by the regular backpropagation. We could confirm that the network developed by our method performs better even with a low precision of the quantization.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2081-2082
• /
• 2006

본 논문에서는 지능형 로봇 시스템에서 신경 회로망을 이용한 인간 몸의 제스처 추출 기법을 제안 하였다. 지능형 로봇 시스템에서 사용된 컴퓨터 시각 기반에서는 시간상의 변화에 따른 특징 벡터 추출을 필요로 한다. 이를 위해 본 논문에서는 신경 회로망을 이용한 제스처 추출 기법을 제안 하였다. 신경 회로망을 이용한 제스처 추출은 오류 역 전파 학습방법을 사용하여 시간상에서 변화하는 영상 시퀀스에 정보를 생성하고 움직임 모델을 통해 두 정보간의 따른 제스처 추출에 가중치를 준다. 마지막으로 본 연구에서 제안한 기법은 실험을 통해 그 우수성을 확인하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.602-608
• /
• 2011

In this study, a method of designing a neurointerface using neural network (NN) is proposed for controlling nonholonomic mobile robots. According to the concept of virtual master-slave robots, in particular, a partially stable inverse dynamic model of the master robot is acquired online through the NN by applying a feedback-error learning method, in which the feedback controller is assumed to be based on a PD compensator for such a nonholonomic robot. The NN for the online feedback-error learning can composed that the input layer consists of six units for the inputs $x_i$, i=1~6, the hidden layer consists of two hidden units for hidden outputs $o_j$, j=1~2, and the output layer consists of two units for the outputs ${\tau}_k$, k=1~2. A tracking control problem is demonstrated by some simulations for a nonholonomic mobile robot with two-independent driving wheels. The initial q value was set to [0, 5, ${\pi}$].

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.4
• /
• pp.277-286
• /
• 2002

Most of the problems in dealing with the tunnel construction are the uncertainties and complexities of the stress conditions and rock strengths in ahead of the tunnel excavation. The limitations on the investigation technology, inaccessibility of borehole test in mountain area and public hatred also restrict our knowledge on the geologic conditions on the mountainous tunneling area. Nevertheless an extensive and superior geophysical exploration data is possibly acquired deep within the mountain area, with up to the tunnel locations in the case of alternative design or turn-key base projects. An appealing claim in the use of artificial neural networks (ANN) is that they give a more trustworthy results on our data based on identifying relevant input variables such as a little geotechnical information and biological learning principles. In this study, error back-propagation algorithm that is one of the teaching techniques of ANN is applied to presupposition on Rock Mass Ratings (RMR) for unknown tunnel area. In order to verify the applicability of this model, a 4km railway tunnel's field data are verified and used as input parameters for the prediction of RMR, with the learned pattern by error back propagation logics. ANN is one of basic methods in solving the geotechnical uncertainties and helpful in solving the problems with data consistency, but needs some modification on the technical problems and we hope our study to be developed in the future design work.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.585-594
• /
• 2007

The back propagation algorithm took a long time to learn the input patterns and was difficult to train the additional or repeated learning patterns. So Aleksander proposed the binary neural network which could overcome the disadvantages of BP Network. But it had the limitation of repeated learning and was impossible to extract a generalized pattern. In this paper, we proposed a dynamic 3 dimensional Neuro System which was consisted of a learning network which was based on weightless neural network and a feedback module which could accumulate the characteristic. The proposed system was enable to train additional and repeated patterns. Also it could be produced a generalized pattern by putting a proper threshold into each learning-net's discriminator which was resulted from learning procedures. And then we reused the generalized pattern to elevate the recognition rate. In the last processing step to decide right category, we used maximum response detector. We experimented using the MNIST database of NIST and got 99.3% of right recognition rate for training data.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.18 no.4
• /
• pp.430-435
• /
• 2009

The cooling stage greatly affects the product quality in the injection molding process. The cooling system that minimizes temperature variance in the product surface will improve the quality and the productivity of products. The cooling circuit optimization problem that was once solved by a response surface method with 4 design variables. It took too much time for the optimization as an industrial design tool. It is desirable to reduce the optimization time. Therefore, we tried the back-propagation algorithm of artificial neural network(BPN) to find an optimum solution in the cooling circuit design in this research. We tried various ways to select training points for the BPN. The same optimum solution was obtained by applying the BPN with reduced number of training points by the fractional factorial design.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.605-608
• /
• 2001

다층 신경망의 학습에 쓰이는 오류 역전파 학습은 매우 효과적이지만 학습 속도가 너무 느리고 최적의 은닉충의 뉴런의 수를 결정하는 해답은 아직 없는 실정이다. 또한 가끔은 국부 최소점(Local maxima)에 빠져 학습이 끝내 이루어지지 않는 경우가 있다. 이에 본 논문에서는 이러한 Local maxima 를 효과적으로 탈출 할 수 있는 방법에 대해서 연구해 보았다. 국부 최소점은 연결강도와 전체 오차 사이의 이차원 공간에서 표현할 수 있는데 본 알고리즘은 이러한 연결강도와 오차와의 관계를 인위적으로 변화시켜 결론적으로 Local maxima 를 탈출하게 하는 방법을 소개한다. 본 연구에서 사용된 방법은 네트웍이 학습중에 Local maxima 에 빠졌을 때 은닉층의 뉴런의 수를 추가하여 인위적으로 연결강도 평면의 위상을 변조시킨다. 또한 은닉충의 뉴런의 수를 동적으로 변화 시키면서 최적의 뉴런의 수를 결정할 수 있게 하였다. 위 알고리즘의 성능을 평가하기 위해서 XOR 문제와 $10{\times}8$ 영문폰트와 숫자의 학습에 적용하여 일반적인 역전파 학습과 비교 평가하였다.