• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.235-238
• /
• 1998

This paper presents the detection of internal combustion engine's multiple misfire. The primary cause of air pollution by vehicles is imperfect conbustion of fuel. The CARB(California Air Resources Board) have imposed regulations for the detection of misfiring in automotive engines. The OBD-II regulations requir that misfire should be monitored by the diagnostic system, and that the goal of OBD-II is to alert the driver to the presence of a malfunction of the emission control system. Present invention based upon measurements of engine roughness as derived from crankshaft angular velocity measurements with special signal processing method. Crankshaft angular velocity signals are processed by walsh-fourier transform. Experimental work confims that it's possible to apply walsh-fourier transform for the detection of multiple misfires in no-load idle and road testing.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.989-992
• /
• 2006

The new approach to the problem of oil spill detection consisting in combined use of all available quasiconcurrent satellite information (AVHRR NOAA, TOPEX/Poseidon, Jason-1, MODIS Terra/Aqua, QuikSCAT) is suggested. We present the results of the application of the proposed approach to the operational monitoring of seawater condition and pollution in the coastal zone of northeastern Black Sea conducted in 2006. This monitoring is based on daily receiving, processing and analysis of data different in nature (microwave radar images, optical and infrared data), resolution and surface coverage. These data allow us to retrieve information on seawater pollution, sea surface and air-sea boundary layer conditions, seawater temperature and suspended matter distributions, chlorophyll a concentration, mesoscale water dynamics, near-surface wind and surface wave fields. The focus is on coastal seawater circulation mechanisms and their impact on the evolution of pollutants.

• Proceedings of the Korea Environmental Mutagen Society Conference
• /
• 2003.10a
• /
• pp.112-112
• /
• 2003

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2007.10a
• /
• pp.52-53
• /
• 2007

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• Journal of Sensor Science and Technology
• /
• v.23 no.5
• /
• pp.342-348
• /
• 2014

This paper introduced a novel multi-gas sensor detector with simple signal processing algorithm. This device was evaluated by investigating the characteristics of combustible materials using fire-generated smell and smoke. Plural sensors including TGS821, TGS2442, and TGS260X were equipped to detect carbon monoxide, hydrogen gas, and gaseous air contaminants which exist in cigarette smoke, respectively. Signal processing algorithm based on the difference of response times in fire-generated gases was implemented with early and accurately fire detection from multiple gas sensing signals. All fire experiments were performed in a virtual fire chamber. The cigarette, cotton fiber, hair, polyester fiber, nylon fiber, paper, and bread were used as a combustible material. This analyzing software and sensor controlling algorithm were embedded into 8-bit micro-controller. Also the detected multiple gas sensor signals were simultaneously transferred to the personnel computer. The results showed that the air pollution detecting sensor could be used as an efficient sensor for a fire detector which showed high sensitivity in volatile organic compounds. The proposed detecting algorithm may give more information to us compared to the conventional method for determining a threshold value. A fire detecting device with a multi-sensor is likely to be a practical and commercial technology, which can be used for domestic and office environment as well as has a comparatively low cost and high efficiency compared to the conventional device.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.3
• /
• pp.588-593
• /
• 2011

The airpollutant may accelerate degradation of power line facilities, and may reduce the life of the electric facilities. In case of korea, there are a tendency that the density of air pollution may be increased by industrial development. while lack of research activity and establishment of a countermeasure on this issue. Recently the occurrence of electricity failure have been reduced on the power transmission and distribution lines. but the occurrence of electricity failure by insulator itself has been increased. It means that we should have develop more clear technique for detection of the wrong insulator. In this study to provide a method for detection of the insulator failure or effective management of the troubled insulator, we analyze the chemical composition of the insulator which used on power distribution line at the sea side locations. To define the relation between insulation and corona intensity, we design and develop an corona detector. We define the variation of insulation by pollution changes on the insulator and verify quantitative relation between corona and insulations using the corona detector.

• International Journal of Automotive Technology
• /
• v.7 no.5
• /
• pp.637-644
• /
• 2006

The detection of engine misfire events is one of major concerns in engine control due to its negative effect on air pollution and engine performance. In this paper, a misfire detection system based on crankshaft angular speed fluctuation is developed. Synthetic variable method is adopted for the preprocessing of crankshaft angular speed. This method successfully estimates the work output of each cylinder by finding the effect of combustion energy on the crankshaft rotational speed or acceleration after virtually removing the effect of the internal inertia forces from the measured crankshaft speed signals. The detection system is developed using neural network with the revised synthetic angular acceleration as input which is derived from the preprocessing. Mathematical simulation is carried out for developing and verifying the misfire detection system. Finally, the reliability of the developed system is validated through an experiment.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.260-269
• /
• 2022

In this paper, We propose an anomaly detection model using deep neural network to automate the identification of outliers of the national air pollution measurement network data that is previously performed by experts. We generated training data by analyzing missing values and outliers of weather data provided by the Institute of Environmental Research and based on the BeatGAN model of the unsupervised learning method, we propose a new model by changing the kernel structure, adding the convolutional filter layer and the transposed convolutional filter layer to improve anomaly detection performance. In addition, by utilizing the generative features of the proposed model to implement and apply a retraining algorithm that generates new data and uses it for training, it was confirmed that the proposed model had the highest performance compared to the original BeatGAN models and other unsupervised learning model like Iforest and One Class SVM. Through this study, it was possible to suggest a method to improve the anomaly detection performance of proposed model while avoiding overfitting without additional cost in situations where training data are insufficient due to various factors such as sensor abnormalities and inspections in actual industrial sites.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2000.11a
• /
• pp.354-355
• /
• 2000

대기환경문제는 관련 환경정책의 강화와 각종 대책에도 불구하고 그 심각성이 날로 증가하고 있다. 이러한 문제를 해결하기 위해 오염현상에 대한 정확한 측정, 분석과 이를 토대로 한 효율적인 대기오염 대책 수립 및 시행이 요구된다. 그러나 기존의 측정방법으로는 대기오염변화를 신속하게 측정하거나 또는 지상 수십 km에 달하는 광범위한 영역의 농도분포를 측정하는 것이 불가능하다. 최근 들어 실시간 측정이 가능한 원격측정 방법 중의 하나인 라이다 (Light Detection And Ranging; LIDAR)에 대한 관심이 고조되면서 여러 나라에서 급속히 발전하고 있다. (중략)