• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.1
• /
• pp.185-193
• /
• 1997

This paper presents the on-line monitoring of the surface roughness in a face milling operation. The cut- ting force was used to monitor the surface roughness, since the insert run-outs not only deteriorate surface roughness but also change cutting force. AR model and band energy method were taken to extract the fea- tures from the cutting force. The features extracted from AR modelling are more accurate about the moni- toring than those from band energy method, whereas, the computing speed of the former is slow. An artifi- cal neural network discriminated the level of the surface roughness by using the features extracted via signal processing.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.77-87
• /
• 2023

Wind turbines playing a critical role in renewable energy generation, accurately assessing their operational status is crucial for maximizing energy production and minimizing downtime. This study conducts a comparative analysis of different neural network models for wind turbine condition diagnosis, evaluating their effectiveness using a dataset containing sensor measurements and historical turbine data. The study utilized supervisory control and data acquisition data, collected from 2 MW doubly-fed induction generator-based wind turbine system (Model HQ2000), for the analysis. Various neural network models such as artificial neural network, long short-term memory, and recurrent neural network were built, considering factors like activation function and hidden layers. Symmetric mean absolute percentage error were used to evaluate the performance of the models. Based on the evaluation, conclusions were drawn regarding the relative effectiveness of the neural network models for wind turbine condition diagnosis. The research results guide model selection for wind turbine condition diagnosis, contributing to improved reliability and efficiency through advanced neural network-based techniques and identifying future research directions for further advancements.

• Korean Chemical Engineering Research
• /
• v.57 no.2
• /
• pp.274-282
• /
• 2019

In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.4
• /
• pp.109-117
• /
• 2019

In modern society, due to various accidents and crime threats committed to an unspecified number of people, individual security awareness is increasing throughout society and various surveillance techniques are being actively studied. Still, there is a decline in robustness due to many problems, requiring higher reliability monitoring techniques. Thus, this paper suggests a real-time change detection technique to complement the low robustness problem in various environments and dynamic/static change detection and to solve the cost efficiency problem. We used the Self-Organizing Map (SOM) applied as a data clustering technique to implement change detection, and we were able to confirm the superiority of noise robustness and abnormal detection judgment compared to the detection technique applied to the existing image surveillance system through simulation in the indoor office environment.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.28-32
• /
• 1995

Bacause the chatter vibration is a main factor to damage on the quality and integrity, The cure is required peticurity in cykinderical plunge grinding. The chatter vibration relatied with wheel speed, workpiece and infeed rate. Therefore, we expressed more credible normal signal and chatter signal Pattern in accrdiance with wheel speed and acquired RMS signal of the accelerrometer. In thos study, after finding the chatter pattern, we applied two parameters, standard deviation and Kurtosis, to Neural Network.

• JOURNAL OF ELECTRICAL WORLD
• /
• no.7 s.55
• /
• pp.72-73
• /
• 1981

공기조화기는 건물내에서 일하는 사람의 공기환경을 좋게 하기 위한 시설로서 실내작업자와는 밀접한 관계가 있다. 공기환경에서는 공기의 온도, 습도와 풍속유지 범위를 정하고 탄산가스, 일산화탄소 및 부유먼지 함유량을 규제하고 있다. 더욱 정기적 측정을 하여 그 기록을 보관해야 한다. 이상과 같이 실내환경에 대한 감시가 엄격해짐으로 실내환경에 신경을 써야 할 것이다. 이런 문제 때문에 공기기술자라 할지라도 공기조화기의 기능을 어느정도 이해해 둘 필요가 있다, 그래서 2회에 걸쳐 공기조화기의 기초지식과 실무 주안점을 소개할까 한다.

• Proceedings of the Korean Society Of Semiconductor Equipment Technology
• /
• 2006.10a
• /
• pp.72-76
• /
• 2006

본 연구에서는 웨이브릿과 신경망을 결합하여 플라즈마 고장을 감시하기 위한 시계열 모델을 개발하였다. 본 기법은 플라즈마 증착장비에 의해 수집된 18 개의 센서정보에 적용하여 평가하였다. 이산치 웨이브릿(Discrete Wavelet Transformation)은 장비에서 수집된 센서정보의 전 처리를 위해 이용되었다. 시계열 모델의 성능은 과거와 미래정보의 함수로 평가하였다. 수집된 18 개의 센서정보에 대한 모델성능 비교를 위해 표준화된 성능평가지표가 적용되었다. 평가결과, 본 기법에 의해 개발된 시계열 모델은 대략 4% 정도의 예측에러를 보였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.2
• /
• pp.35-44
• /
• 1998

This paper describes multiple fault diagnosis method in complex system with hierarchical structure. Complex system is divided into subsystem, item and component. For diagnosing this hierarchical complex system, it is necessary to implement special neural network. We introduced Modular Artificial Neural Network(MANN) for this purpose. MANN consists of four level neural network, first level for symptom classification, second level for item fault diagnosis, third level for component symptom classification, forth level for component fault diagnosis. Each network is multi layer perceptron with 7 inputs, 30 hidden node and 7 outputs trained by backpropagation. UNIX IPC(Inter Process Communication) is used for implementing MANN with multitasking and message transfer between processes in SUN workstation. We tested MANN in reactor system.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.3
• /
• pp.14-21
• /
• 1998

The in-process detection of the state of cutting tool is one of the most important technical problem in Intelligent Machining System. This paper presents a method of detecting the state of cutting tool in turning process, by using Artificial Neural Network. In order to sense the state of cutting tool. the sensor fusion of an acoustic emission sensor and a force sensor is applied in this paper. It is shown that AErms and three directional dynamic mean cutting forces are sensitive to the tool wear. Therefore the six pattern features that is, the four sensory signal features and two cutting conditions are selected for the monitoring system with Artificial Neural Network. The proposed monitoring system shows a good recogniton rate for the different cutting conditions.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.1408-1412
• /
• 2004

인구의 폭발적 증가, 산업화, 도시화의 급진적, 과학기숙의 발달 등으로 물 소비는 급증하는 반면, 이상기후현상으로 수자원의 절대량이 줄어 수자원의 양적인 문제와 하천 및 저수지의 수질오염에 대한 질적인 문제가 ,대두되고 있다. 하천의 수질현상 및 이송은 상당히 비선형적이고, 시간에 따라 변화하려, 실제로 수질의 예측은 유량의 변동, 오염물질의 이송 및 확산, 하천 구조물 등의 여러 요인에 의하여 상당히 어렵다고 알려져 왔다. 또한 한정된 수자원으로 하천의 수량과 수질목표를 동시에 달성하기 위해서는 물의 수요와 공급을 실시간으로 감시하면서 기상과 유출예측기술을 활용하여 용수의 수요와 공급을 예측하고 이를 토대로 수량과 수질을 고려한 물관리 운영시스템이 구축되어야 한다. 이를 위해 본 연구에서는 모형의 입${\cdot}$출력 구성을 자유롭게 변형할 수 있는 상태공간 모형과 신경망 모형을 이용하여 금강수계 주요 지점의 수질예측 모형을 구성하고 모형의 적용성을 파악한 후 예측력이 우수한 모형을 Web기반 모형의 수질예측 모듈의 기본모형으로 선정하고 Web 상에서 수질예측이 가능하도록 시스템을 개발하였다.