• 한국생산제조학회지
• /
• 제18권4호
• /
• 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.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2006년도 추계학술대회 학술발표 논문집 제16권 제2호
• /
• pp.185-188
• /
• 2006

생체 신경세포를 모방하는 진동성 신경 셀을 아날로그 집적회로로 설계한다. 진동성 신경셀은 입력신호 취합을 위한 취합회로와 신경 펄스 발생회로, 신경펄스 발생을 위한 범프회로와 트랜스콘덕터로 이루어지는 부성저항 블록으로 구성된다. $0.35{\mu}m$ 2중 폴리 공정 파라미터를 이용하여 SPICE 모의실험을 실시하여 입력 신호 유무 및 크기변화에 따른 출력 펄스의 발생을 얻어 진동성 신경회로의 가능성을 확인한다.

• 한국정보통신학회논문지
• /
• 제6권1호
• /
• pp.14-24
• /
• 2002

본 논문에서는 학습과 정정 기능을 갖는 PWM 뉴럴네트워크를 설계하였다. 설계된 PWM 뉴럴시스템에서, 네트워크의 입력과 출력 신호들은 PWM 신호에 의해서 표현되어진다. 뉴럴네트워크에서 곱셈은 가장 많이 사용하는 동작이다. 승산과 합산의 기능은 PWM 기술과 간단한 혼합모드 회로기술에 의해서 실현된다. 그러므로 설계된 뉴럴네트워크는 단지 소규모의 칩상에서 구현될 수가 있다. 하나의 뉴런과 세개의 시냅스, 연관된 학습회로로 설계된 네트워크회로는 양호한 선형성과 넓은 범위의 동작범위를 가지고 있다. PWM을 이용한 신경망회로의 학습능력을 검증하기 위해, 델타 학습 규칙을 적용하였다. AND 기능과 OR 기능 학습 예측 HSPICE 시뮬레이션을 통해서 설계한 신경망회로의 기능이 성공적임을 증명하였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권12호
• /
• pp.804-810
• /
• 2004

There are two important things for the general purpose neural network processor. The first is a capability to build various structures of neural network, and the second is to be able to support suitable learning method for that neural network. Some way to process various learning algorithms is required for on-chip learning, because the more neural network types are to be handled, the more learning methods need to be built into. In this paper, an improved hardware structure is proposed to compute various kinds of learning algorithms flexibly. The hardware structure is based on the existing modular neural network structure. It doesn't need to add a new circuit or a new program for the learning process. It is shown that rearrangements of the existing processing elements can produce several neural network learning modules. The performance and utilization of this module are analyzed by comparing with other neural network chips.

• 제어로봇시스템학회논문지
• /
• 제2권4호
• /
• pp.337-343
• /
• 1996

In this paper, we investigate the defect detection by making use of pre-made reference image data and classify the defects by using the artificial neural network. The approach is composed of three main parts. The first step consists of a proper generation of two reference image data by using a low level morphological technique. The second step proceeds by performing three times logical bit operations between two ready-made reference images and just captured image to be tested. This results in defects image only. In the third step, by extracting four features from each detected defect, followed by assigning them into the input nodes of an already trained artificial neural network we can obtain a defect class corresponding to the features. All of the image data are formed in a bit level for the reduction of data size as well as time saving. Experimental results show that proposed algorithms are found to be effective for flexible defect detection, robust classification, and high speed process by adopting a simple logic operation.

• 생물정신의학
• /
• 제18권1호
• /
• pp.15-24
• /
• 2011

Mood disorder is unlikely to be a disease of a single brain region or a neurotransmitter system. Rather, it is now generally viewed as a multidimensional disorder that affects many neural pathways. Growing neuroimaging evidence suggests the anterior cingulate-pallidostriatal-thalamic-amygdala circuit as a putative cortico-limbic mood regulating circuit that may be dysfunctional in mood disorders. Brain-imaging techniques have shown increased activation of mood-generating limbic areas and decreased activation of cortical areas in major depressive disorder(MDD). Furthermore, the combination of functional abnormalities in limbic subcortical neural regions implicated in emotion processing together with functional abnormalities of prefrontal cortical neural regions probably result in the emotional lability and impaired ability to regulate emotion in bipolar disorder. Here we review the biological correlates of MDD and bipolar disorder as evidenced by neuroimaging paradigms, and interpret these data from the perspective of endophenotype. Despite possible limitations, we believe that the integration of neuroimaging research findings will significantly advance our understanding of affective neuroscience and provide novel insights into mood disorders.

• 제어로봇시스템학회논문지
• /
• 제7권3호
• /
• pp.246-254
• /
• 2001

In this paper, we described an approach to the automation of visual inspection of BGA solder joint defects of surface mounted components on printed circuit board by using neural network. Inherently, the BGA solder joints are located underneath its own package body, and this induces a difficulty of taking good image of the solder joints by using conventional imaging systems. To acquire the cross-sectional image of BGA sol-der joint, X-ray cross-sectional imaging method such as laminography and digital tomosynthesis has been cur-rently utilized. However, the cross-sectional image obtained by using laminography or DT methods, has inher-ent blurring effect and artifact. This problem has been a major obstacle to extract suitable features for classifi-cation. To solve this problem, a neural network based classification method is proposed int his paper. The per-formance of the proposed approach is tested on numerous samples of printed circuit boards and compared with that of human inspector. Experimental results reveal that the method provides satisfactory perform-ance and practical usefulness in BGA solder joint inspection.

• 융합신호처리학회논문지
• /
• 제2권2호
• /
• pp.111-118
• /
• 2001

본 연구에서는 패턴 인식용 다층 퍼셉트론 신경망을 순수 디지털 논리회로 모델로 구현할 수 있도록 새로운 논리뉴런의 구조, 디지털 정형 다층논리신경망 구조, 그리고 패턴인식의 응용을 위한 다단 다층논리 신경망 구조를 제안하고, 또한 제안된 구조는 매우 단순하면서도 효과적인 증가적인 가법적(Incremental Additive) 학습알고리즘이 존재함을 보였다.

• 디지털융복합연구
• /
• 제18권11호
• /
• pp.241-246
• /
• 2020

본 논문에서는 해양 전기추진 시스템과 딥러닝 알고리즘을 융합하여 전기추진 리제너레이션 시스템에서 DC/DC 컨버터 출력 전류 예측 및 리제너레이션 수행 시 배터리 충전량을 예측하기 위해 신경망 모델을 제안한다. 제안 된 신경망을 실험하기 위해 PCM의 입력 전압과 전류를 측정하고 시제품 PCM 보드의 출력 결과를 통해 데이터 세트를 구성하였다. 또한 불충분 한 데이터 세트에서 학습 결과를 향상시키기 위해 기존 데이터 세트를 데이터 피팅하여 학습을 진행하였다. 학습 후 신경망 모델의 데이터 예측 결과와 실제 측정 데이터의 차이를 그래프를 통해 확인하였다. 제안한 신경망 모델은 입력 전압과 전류 변화에 따른 배터리 충전량 예측을 효율적으로 보여주었다. 또한, DC/DC 컨버터를 구성하는 아날로그 회로의 특성변화를 신경망을 통하여 예측함으로써, 리제너레이션 시스템의 설계 시, 아날로그 회로의 특성을 고려해야 할 것으로 판단된다.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2007년도 춘계학술발표논문집
• /
• pp.147-149
• /
• 2007

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.