• International Journal of Control, Automation, and Systems
• /
• 제4권6호
• /
• pp.763-768
• /
• 2006

The two-for-one(TFO) twister is precision machinery that twists fibers rapidly under constant tension. Since the quality of the twisted yarn is directly deteriorated by faults of the twister, such as the distortion of the spinning axis, bearing abrasion, and tension irregularity, it is important to detect faults of the TFO twister at an early stage. In this research, a new algorithm is proposed to detect faults of the TFO twister and their causes, by measuring the vibrations of the TFO twister and obtaining frequency components with a FFT algorithm. The TFO twister with faults showed increased vibrations and each fault generated vibrations at different frequencies. By analyzing changes of characteristics of vibrations, we can determine faulty twisters. The proposed fault detection algorithm can be implemented cheaply with a signal processor chip. It can be used to find when to repair a faulty TFO twister without much loss of yam on-line.

• 대한원격탐사학회지
• /
• 제26권3호
• /
• pp.287-295
• /
• 2010

Water level of the Tonle Sap is largely influenced by the Mekong River. During the wet season, the lacustrine landform and vegetated areas are covered with water. Change detection in this area provides information required for human activities and sustainable development around the Tonle Sap. In order to detect the changes in the Tonle Sap floodplain, fifteen ALOS-PALSAR L-band data acquired from January 2007 to January 2009 and examined in this study. Since L-band is able to penetrate into vegetation cover, it enables us to study the changes according to water level of floodplain developed in the rainforest. Four types of images were constructed and studied include 1) ratio images, 2) correlation coefficient images, 3) texture feature ratio images and 4) multi-color composite images. Change images (in each 46 day interval) extracted from the ratio images, coherence images and texture feature ratio images were formed for detecting land cover change. Two RGB images are also obtained by compositing three images acquired in the early, in the middle and at the end of the rainy season in 2007 and 2008. Combination of the methods results that the change images present the relationship between vegetation and water level, leaf fall forest as well as cultivation and harvest crop.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.337-340
• /
• 2009

Wireless tele-home-care application gives new possibilities for ECG (electrocardiogram) monitoring system with wearable biomedical sensors. Thus, continuously development of high convenient ECG monitoring system for high-risk cardiac patients is essential. This paper describes to monitor a person's ECG using wearable approach. A wearable belt-type ECG electrode with integrated electronics has been developed and has proven long-term robustness and monitoring of all electrical components. The measured ECG signal is transmitted via an ultra low power consumption wireless sensor node. ECG signals carry a lot clinical information for a cardiologist especially the R-peak detection in ECG. R-peak detection generally uses the threshold value which is fixed thus it bring errors due to motion artifacts and signal size changes. Variable threshold method is used to detect the R-peak which is more accurate and efficient. In order to evaluate the performance analysis, R-peak detection using MIT-BIH databases and Long Term Real-Time ECG is performed in this research. This concept able to allow patient to follow up critical patients from their home and early detecting rarely occurrences of cardiac arrhythmia.

• 한국기계가공학회지
• /
• 제11권4호
• /
• pp.154-159
• /
• 2012

Condition monitoring(CM) is a method based on Non-destructive test(NDT). Therefore, recently many kind of NDT were applied for CM. Acoustic emission(AE) is widely used for the early detection of faults in rotating machinery in these days also. Because its sensitivity is higher than normal accelerometers and it can detect low energy vibration signals. A machine tool consist of many parts such as the bearings, gears, process tools, shaft, hydro-system, and so on. Condition of Every part is connected with product quality finally. To increase the quality of products, condition monitoring of the components of machine tool is done completely. Therefore, in this paper, acoustic emission method is used to detect a machine fault seeded in a gearbox. The AE signals is saved, and power spectrums and feature values, peak value, mean value, RMS, skewness, kurtosis and shape factor, were determined through Matlab.

• 한국군사과학기술학회지
• /
• 제23권3호
• /
• pp.302-309
• /
• 2020

Early-detection and monitoring of toxic chemical gas cloud with chemical detector is essential for reducing the number of casualties. Conventional method for chemical detection and reconnaissance has the limitation in approaching to chemically contaminated site and prompt understanding for the situation. Stand-off detector can detect and identify the chemical gas at a long distance but it cannot know exact distance and position. Chemical detection UAV is an emerging platform for its high mobility and operation safety. In this study, we have conducted chemical gas cloud detection with the stand-off chemical detector and the chemical detection UAV. DMMP vapor was generated in the area where the cloud can be detected through the field of view(FOV) of stand-off chemical detector. Monitoring the vapor cloud with standoff detector, the chemical detection UAV moved back and forth at the area DMMP vapor being generated to detect the chemical contamination. The hybrid detection system with standoff cloud detection and point detection by chemical sensors with UAV seems to be very efficient as a new concept of chemical detection.

• Journal of Advanced Marine Engineering and Technology
• /
• 제33권5호
• /
• pp.672-678
• /
• 2009

Acoustic Emission (AE) technique is a non-destructive testing method and widely used for the early detection of faults in rotating machines in these days, because the sensitivity of AE transducers is higher than normal accelerometers. So it can detect low energy vibration signals. The faults in the rotating machines are generally occurred at bearings and gearboxes which are the principal parts of the machines. It was studied to detect the bearing faults by envelop analysis in several decade years. And the researches showed that AE had a possibility of the application in condition monitoring system(CMS) using the envelope analysis for the rolling bearing. And peak ratio (PR) was developed for expression of the bearing condition in condition monitoring system using AE. Noise level is needed to reduce to take exact PR value because the PR is calculated from total root mean square (RMS) and the harmonics peak levels of the defect frequencies of the bearing. Therefore, in this paper, the discrete wavelet transform (DWT) was added in the envelope analysis to reduce the noise level in the AE signals. And then, the PR was calculated and compared with general envelope analysis result and the result of envelope analysis added the DWT. In the experiment result about inner fault of bearing, defect frequency was difficult to find about only envelop analysis. But it's easy to find defect frequency after wavelet transform. Therefore, Envelop analysis added wavelet transform was useful method for early detection of default in signal process.

• 한국산업정보학회논문지
• /
• 제20권6호
• /
• pp.37-46
• /
• 2015

The wireless electrocardiographic monitoring system(WDMS) is designed to be long term monitoring for the early detection of cardiac disorders. The current version of the WDMS can identify two types of cardiac rhythms in real-time, such as atrial fibrillation(AF) and normal sinus rhythm(NSR), which are very important to track cardiac-rhythm disorders. In this study, we proposed the analysis method to discriminate the characteristics statistically evaluated in both time and frequency domains between AF and NSR using various parameters in the heart rate variability(HRV). And we applied various ECG detection methods (e.g., difference operation method) and compared the results with those of the discrete wavelet transform(DWT) method. From the statistically results, we found that the parameters such as STD RR, STD HR, RMSSD, NN50, pNN50, RR Trian, and TNN(p<0.05) are significantly different between the AF and NSR patients in time domain. On the other hand, the frequency domain analysis results showed a significant difference in VLF power($ms^2$), LF power($ms^2$), HF power($ms^2$), VLF(%), LF(%), and HF(%). In particular, the parameters such as STD RR, RMSSD, NN50, pNN50, VLF power, LF power and HF power were considered as the most useful parameters in both AF and NSR patient groups. Our proposed method can be efficiently applied to early detection of abnormal conditions and prevent the such abnormals from becoming serious.

• 한국컴퓨터정보학회논문지
• /
• 제28권12호
• /
• pp.67-77
• /
• 2023

본 연구는 스마트팜 환경에서 진행된 혁신적인 연구로, 딥러닝을 기반으로 한 질병 및 해충 탐지 모델을 개발하고, 이를 지능형 사물인터넷(IoT) 플랫폼에 적용하여 디지털 농업 환경 구현의 새로운 가능성을 탐색하였다. 연구의 핵심은 Pseudo-Labeling, RegNet, EfficientNet 등 최신 ImageNet 모델과 전처리 방식을 통합하여, 복잡한 농업 환경에서 다양한 질병과 해충을 높은 정확도로 탐지하는 것이었다. 이를 위해 앙상블 학습 기법을 적용하여 모델의 정확도와 안정성을 극대화했으며, 평균 정밀도(mAP), 정밀도, 재현율, 정확도, 박스 손실 등의 다양한 성능 지표를 통해 모델을 평가하였다. 또한, SHAP 프레임워크를 활용하여 모델의 예측 기준에 대한 깊은 이해를 도모하였고, 이를 통해 모델의 결정 과정을 보다 투명하게 만들었다. 이러한 분석은 모델이 어떻게 다양한 변수들을 고려하여 질병 및 해충을 탐지하는지에 대한 중요한 통찰력을 제공하였다.

• 한국동물생명공학회지
• /
• 제38권4호
• /
• pp.215-224
• /
• 2023

Background: Reproductive management practices play crucial roles to maximize the reproductive performance of cows, and thus contribute to farm profitability. We aimed to assess the reproductive management of cows currently practiced in the dairy farms in an urban farming system. Methods: A total of 62 dairy farms were randomly selected considering all size of farms such as small (1-5 cattle), medium (6-20 cattle) and large farms (> 20 cattle) from selected areas of Dhaka city in Bangladesh. The reproductive management-related parameters viz. estrus detection, breeding method, pregnancy diagnosis, dry cow and parturition management, vaccination and treatment of reproductive problems etc. were obtained in a pre-defined questionnaire during the farm visit. Results: The visual observation method was only used (100.0%; 62/62) for estrus detection irrespective of size of the farms; while farmers observed cows for estrus 4-5 times a day, but only for 20-60 seconds each time. Regardless of farm size, 89.0% (55/62) farms used artificial insemination (AI) for breeding the cows. Intriguingly, all farms (100.0%) routinely checked the cows for pregnancy at 35-40 days post-breeding using rectal palpation technique by registered veterinarian. However, only 6.5% (4/62) farms practiced dry cow management. Notably, all farms (100.0%) provided nutritional supplements (Vit D, Ca and P) during late gestation. However, proper hygiene and cleanliness during parturition was not practiced in 77.4% (48/62) farms; even though 96.7% (60/62) farms treated cows by registered veterinarian for parturition-related problems. Conclusions: While farmers used AI service for breeding and timely check their cows for pregnancy; however, they need to increase observation time (30 minutes/ observation, twice in a day: early morning and early night) for estrus detection, consider dry cow management and ensure hygienic parturition for maximizing production.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 정보화시공 학술발표회
• /
• pp.19-27
• /
• 2001

Early detection of premonitory symptom of slope movement ensures tremendous saving of lives and repair costs from catastrophic disaster. Therefore, it is essential to constantly monitor the performance and integrity of both reinforced and un-reinforced cut slopes. We developed a novel monitoring system by using tension wire sensors. It's advantages are highly sensitivity, simple installation, large displacement measurement, durability of system, capability of remote sensing. Real-time measurement of slope surface movement is shown graphically and it gives a warning when the monitored value exceeds a given threshold level so that any sign of abnormal slope movement can be easily perceived.