http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 김강석 (검색결과 451 건)
- 무료
- 기관 내 무료
- 유료
-
시계열 데이터를 이용한 인공신경망 기반 공작기계 가공상태 모니터링
김강석,이득우 한국정밀공학회 2024 한국정밀공학회지 Vol.41 No.8
In order to monitor the machining status of a machine tool, it is necessary to measure the signal of the machine tool and establish the relationship between the machining status and the signal. One effective approach is to utilize an AI-based analysis model. To improve the accuracy and reliability of AI models, it is crucial to identify the features of the model through signal analysis. However, when dealing with time series data, it has been challenging to identify these features. Therefore, instead of directly applying time series data, a method was used to extract the best features by processing the data using techniques such as RMS and FFT. Recently, there have been numerous reported cases of designing AI models with high accuracy and reliability by directly applying time series data to find the best features, particularly in the case of AI models combining CNN and LSTM. In this paper, time series data obtained through a gap sensor are directly applied to an AI model that combines CNN, LSTM, and MLP (Multi-Layer Perceptron) to determine tool wear. The machine tool and tool status were monitored and evaluated through an AI model trained using time series data from the machining process.
-
-
-
-
김강석,이득우,이상민,이승준,황주호 한국정밀공학회 2015 International Journal of Precision Engineering and Vol. No.
The purpose of a ball bearing is to reduce the rotational friction and support radial and axial loading. But it can't avoid the heatgeneration by the friction, the wear and the power loss it was caused by the relative motion between the metal materials. Heat isgenerated by the friction in the bearings, which causes the temperature inside the bearing to increase. If the heat is not appropriatelyremoved from the bearing, elevated temperatures may give rise to premature failure. It is, therefore, important to be able to calculatethe temperature in the bearings due to friction. Here, we describe a method to estimate the equilibrium temperature on the angularcontact ball bearing in a spindle system using a numerical approach. The frictional torque of the bearing in a spindle system wascalculated by use of a bearing analysis tool and thermal analysis of the spindle system including the bearings was achieved usingthe finite element method (FEM). The actual spindle system with the same layout of the FEA was built and the frictional torque, thebearing temperature were measured in the experiment. The bearing temperature was compared with measured data to verify thevalidity of finite element analysis.
-
-
-
무선센서네트워크를 위한 확률추론 휴리스틱기반 비주기적 전송
김강석,이동철,Kim, Gang-Seok,Lee, Dong-Cheol 한국정보통신학회 2008 한국정보통신학회논문지 Vol.12 No.9
저전력 무선 통신의 발전과 다기능, 저가의 스마트 센서는 원격에서 상태정보를 감지할 수 있는 센서네트워크의 실현을 가능하게 하였다. 센서 노드는 소형 배터리를 사용해 에너지를 공급받는데 일반적으로 배터리 교환이 용이하지 않은 위치에 설치되기 때문에 센서 노드의 평균 소모 전력을 최소화할 필요가 있다. 알려진 바에 따르면 센서 노드의 전체 소모 전력의 20-60%를 무선 통신에 사용하는 RF 모듈이 차지하고 있다. 본 논문에서는 센싱된 데이터의 송신에 소비되는 에너지를 개선하기 위해 센싱 데이터의 변동 특성에 실시간 적응하여 확률적 계산값이 임의의 랜덤값보다 클 경우 기지국 노드로 전송하는 확률추론 휴리스틱기반 비주기적 전송 방법을 제안한다. 제안하는 전송 방법에서는 확률추론 휴리스틱 알고리즘에 따라 센싱된 데이터와 직전 센싱된 데이터를 평가하여 전송 여부를 결정하며 알고리즘에 필요한 계수값은 알고리즘 검증 데이터의 재현율을 통하여 결정한다. The development of low-power wireless communication and low-cost multi-functional smart sensor has enabled the sensor network that can perceive the status information in remote distance. Sensor nodes are sending the collected data to the node in the base station through temporary communication path using the low-cost RF communication module. Sensor nodes get the energy supply from small batteries, however, they are installed in the locations that are not easy to replace batteries, in general, so it is necessary to minimize the average power consumption of the sensor nodes. It is known that the RF modules used for wireless communication are consuming 20-60% of the total power for sensor nodes. This study suggests the probability inference heuristic based non-periodic transmission to send the collected information to the base station node, when the calculated value by probability is bigger than an optional random value, adapting real-time to the variation characteristics of sensing datain order to improve the energy consumption used in the transmission of sensed data. In this transmission method suggested, transmitting is decided after evaluation of the data sensed by the probability inference heuristic algorithm and the directly sensed data, and the coefficient that is needed for its algorithm is decided through the reappearance rate of the algorithm verification data.
-
-
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
