• Title, Summary, Keyword: SG Measurement

Search Result 30, Processing Time 0.027 seconds

Detecting Anomalies in Time-Series Data using Unsupervised Learning and Analysis on Infrequent Signatures

  • Bian, Xingchao
    • Journal of IKEEE
    • /
    • v.24 no.4
    • /
    • pp.1011-1016
    • /
    • 2020
  • We propose a framework called Stacked Gated Recurrent Unit - Infrequent Residual Analysis (SG-IRA) that detects anomalies in time-series data that can be trained on streams of raw sensor data without any pre-labeled dataset. To enable such unsupervised learning, SG-IRA includes an estimation model that uses a stacked Gated Recurrent Unit (GRU) structure and an analysis method that detects anomalies based on the difference between the estimated value and the actual measurement (residual). SG-IRA's residual analysis method dynamically adapts the detection threshold from the population using frequency analysis, unlike the baseline model that relies on a constant threshold. In this paper, SG-IRA is evaluated using the industrial control systems (ICS) datasets. SG-IRA improves the detection performance (F1 score) by 5.9% compared to the baseline model.

An investigation on the in si.tu measurement of the oil-concentration

  • Kim, Chang-Nyeun;Park, Young-Moo
    • International Journal of Air-Conditioning and Refrigeration
    • /
    • v.9 no.1
    • /
    • pp.20-28
    • /
    • 2001
  • In order to predict thermodynamic performance of refrigeration system, it is required to know the oil concentration of the refrigerant/oil mixture. The current method is to extract the working mixture and then to measure the oil weight. In this study, oil concentration is measured in si.tu way without any extraction of the working fluid. Based on the measurement, a working equation is presented as follows, C=a +b x t +c x $t^2$ +(d + e x t +f x $t^2$) x SG. C is oil concentration, t is temperature($^{\circ}C). SG Is specific gravity of mixture and a~f is coefficients The oil concentration ranges over 0~l2 wt% and the temperature ranges over 20~50$^{\circ}C. The specific gravity and temperature are measured using the on-line densimeter and thermometer. This working equation enables to predict the oil concentration without any extraction of the mixture. This equation can be applied for R-12/Naphthenic oil and R-134a/P0E oil liquid mixtures.

  • PDF

An investigation on the in si.tu measurement of the oil-concentration

  • Kim, Chang-Nyeun;Park, Young-Moo
    • International Journal of Air-Conditioning and Refrigeration
    • /
    • v.8 no.2
    • /
    • pp.80-88
    • /
    • 2000
  • In order to predict thermodynamic performance of refrigeration system, it is required to know the oil concentration of the refrigerant/oil mixture. The current method is to extract the working mixture and then to measure the oil weight. In this study, oil concentration is measured in si.tu way without any extraction of the working fluid. Based on the measurement, a working equation is presented as follows, C=a +b x t +c x $t^2$ +(d + e x t +f x $t^2$) x SG. C is oil concentration, t is temperature($^{\circ}C). SG Is specific gravity of mixture and a~f is coefficients The oil concentration ranges over 0~l2 wt% and the temperature ranges over 20~50$^{\circ}C. The specific gravity and temperature are measured using the on-line densimeter and thermometer. This working equation enables to predict the oil concentration without any extraction of the mixture. This equation can be applied for R-12/Naphthenic oil and R-134a/P0E oil liquid mixtures.

  • PDF

An investigation on the in si·tu measurement of the oil-concentration with densimeter (밀도계를 이용한 비추출식 냉동기유농도 측정에 관한 연구)

  • Kim, S.H.;Kim, C.N.;Park, Y.M.
    • Korean Journal of Air-Conditioning and Refrigeration Engineering
    • /
    • v.11 no.1
    • /
    • pp.31-37
    • /
    • 1999
  • In order to predict thermodynamic performance of refrigeration system, it is required to know the oil concentration of the refrigerant/oil mixture. The current method to measure the oil concentration is to extract the working mixture and then to measure the oil weight. However, it is Quite necessary to estimate oil concentration without any extraction of the working fluid. In this study a new method and working equation is presented as follows. It is based on the measurement of spedific gravity and temperature : $$C=a+b{\times}t+c{\times}t^2+(d+e{\times}t+f{\times}t^2){\times}SG$$ C is oil concentration, t is temperature($^{\circ}C$), SG is specific gravity of mixture and a~f is coefficients. The oil concentration ranges over 0~12 wt% and the temperature ranges over $20{\sim}50^{\circ}C$. The specific gravity and temperature are measured using the on-line densimeter and thermometer. This working equation enables to predict the oil concentration without any extraction of the mixture. This equation can be applied for R-12/Naphthenic oil and R-134a/POE oil oiquid mixtures.

  • PDF

A Study on Pattern Recognition Technology for Inspection Automation of Manufacturing Process based Smart Camera (스마트카메라를 이용한 생산공정의 검사자동화를 위한 패턴인식기술에 관한 연구)

  • Shin, Heang-Bong;Sim, Hyun-Suk;Kang, Un-Wook
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.18 no.4
    • /
    • pp.241-249
    • /
    • 2015
  • The purpose of this research is to develop the pattern recognition algorithm based on smart camera for inspection automation, and including external surface state of molding parts or optical parts. By performance verification, this development can be applied to establish for existing reflex data because inputting surface badness degree of scratch's standard specification condition directly. And it is pdssible to distinguish from schedule error of badness product and normalcy product within schedule extent after calculating the error comparing actuality measurement reflex data and standard reflex data mutually. The proposed technology cab be applied to test for masearing of the smallest 10 pixel unit. It is illustrated the relibility pf proposed technology by an experiment.

INTERPRETATION OF ELECTROCHEMICAL NOISE PARAMETERS AS INDICATORS OF INITIATION AND PROPAGATION OF SCC OF AN ALLOY 600 SG TUBE AT HIGH TEMPERATURES

  • Kim, Sung-Woo;Kim, Hong-Pyo
    • Nuclear Engineering and Technology
    • /
    • v.41 no.10
    • /
    • pp.1315-1322
    • /
    • 2009
  • The present article is concerned with the application of an electrochemical noise (EN) monitoring technique to analyze the initiation and propagation of Pb-assisted stress corrosion cracking (SCC) of an Alloy 600 material in a simulated environment of a steam generator (SG) sludge pile at high temperatures. A typical increase of electrochemical current noise (ECN) and electrochemical potential noise (EPN) was frequently recorded from the EN measurement in a caustic solution with such impurities as PbO and CuO, indicating that there are localized corrosion events occurring. With the aid of microscopic and spectral analyses, the EN data involving information on such stochastic processes as uniform corrosion and the initiation and propagation of SCC, were analyzed based on a stochastic theory.

Establishment of strain measurement system for evaluation of strain effect in HTS tapes under magnetic field

  • Dedicatoria, Marlon J.;Shin, Hyung-Seop
    • Progress in Superconductivity and Cryogenics
    • /
    • v.13 no.4
    • /
    • pp.14-17
    • /
    • 2011
  • The evaluation of the electromechanical properties of HTS CC tapes is one of the foremost procedures to be done to ensure the applicability of superconducting wires to electric devices. A precise measurement of the stress and strain is important in deriving the mechanical properties under operating environment. Up to now, there is no standard test method yet for the electromechanical property evaluation of HTS tapes under self field and external magnetic field although there are already reports on the different devices used to evaluate these properties. Strain can be measured by adopting a strain gauge or a high resolution double extensometer. In this study, strain effect on $I_c$ in HTS CC tapes under magnetic fields was evaluated. Comparison of advantages and setback of strain measuring devices were discussed. In addition, a dual strain measurement system using both the SG and extensometer may be practical to lessen the burden in case one of the measuring devices does not work well.

Using SG Arrays for Hydrology in Comparison with GRACE Satellite Data, with Extension to Seismic and Volcanic Hazards

  • Crossley David;Hinderer Jacques
    • Korean Journal of Remote Sensing
    • /
    • v.21 no.1
    • /
    • pp.31-49
    • /
    • 2005
  • We first review some history of the Global Geodynamics Project (GGP), particularly in the progress of ground-satellite gravity comparisons. The GGP Satellite Project has involved the measurement of ground-based superconducting gravimeters (SGs) in Europe for several years and we make quantitative comparisons with the latest satellite GRACE data and hydrological models. The primary goal is to recover information about seasonal hydrology cycles, and we find a good correlation at the microgal level between the data and modeling. One interesting feature of the data is low soil moisture resulting from the European heat wave in 2003. An issue with the ground-based stations is the possibility of mass variations in the soil above a station, and particularly for underground stations these have to be modeled precisely. Based on this work with a regional array, we estimate the effectiveness of future SG arrays to measure co-seismic deformation and silent-slip events. Finally we consider gravity surveys in volcanic areas, and predict the accuracy in modeling subsurface density variations over time periods from months to years.

Suicidal Behavior, Violent Behavior, and Neurocognitive Function in Child and Adolescent Mood Disorder Patients (기분 장애 소아 청소년 환자에서 자살 행동, 공격 행동과 인지기능과의 관계)

  • Yoon, Hee Joon;Oh, Yunhye;Joung, Yoo Sook
    • Journal of the Korean Academy of Child and Adolescent Psychiatry
    • /
    • v.27 no.1
    • /
    • pp.39-47
    • /
    • 2016
  • Objectives: The aim of this study was to examine the association between current suicidal or violent behavior and deficits of specific neurocognitive variables in child and adolescent inpatient samples diagnosed with mood disorder. Methods: A retrospective review of the charts of mood disorder patients hospitalized at Samsung Medical Center between April 2004 and April 2015 was conducted. Child and adolescent patients aged between 10 and 18 years old and those who finished neurocognitive function testing during their hospitalization were included. Among them patients whose full scale IQ was between 85 and 115 were selected (N=111). Participants were first divided into two age-groups-group Y ($10{\leq}age{\leq}15$, N=54) and group O ($16{\leq}age{\leq}18$, N=57)-because neurocognitive function test tools were different according to age [Wechsler Intelligence Scale for Children (WISC) for 10 to 15-year-old patients, Wechsler Adult Intelligence Scale (WAIS) for 16 to 18-year-old patients]. They were then divided according to their suicidal or violent behavior-non suicidal/violent group (NG), suicidal group (SG), violent group (VG), and both suicidal/violent group (BG). The Child Behavior Checklist (CBCL) was checked for measurement of participants' behavior and the Gordon Diagnostic System was checked for measurement of their attention efficiency. Kruskal-Wallis Test and Tukey test was used to determine the differences in neurocognitive function between groups. Results: O-SG patients showed lower scores on the comprehension subscale of WAIS-III than O-NG patients (${\chi}^2=8.454$, p=.015). O-VG patients showed lower scores on the block design subscales of WAIS than O-SG patients (${\chi}^2=7.496$, p=.024). Y-VG patients showed higher scores in aggressive behavior, externalizing problems, and total problems scores of CBCL. Conclusion: This study showed relationship between specific neurocognitive deficits and suicidal or violent behavior. These relationships were significant in relatively older adolescents.

A study of structure modeling of the stratum corneum on the hydration (보습상태에서 피부각질의 구조 모델링에 관한 연구)

  • Kim, Jeong-Lae;Kim, Hye-Ju
    • The Journal of the Convergence on Culture Technology
    • /
    • v.3 no.3
    • /
    • pp.31-36
    • /
    • 2017
  • We are made up to the variation of the structure modeling of the stratum corneum by the skin on the hydration. The given skin structure is consist of the control level of the intercellular route and transcellular route, and is confirmed to the variation of the modeling for algorithm. Hydration condition is consisted to modeling by the size, form and combination, that skin impedance is appeared to result the value of measurement by the several layer such as forms of ${\xi}-R-SC-RH$, ${\xi}-R-SL-RH$, ${\xi}-R-SG-RH$, ${\xi}-R-SS-RH$ and ${\xi}-R-SB-RH$. Hydration condition is showed to the alteration difference value of S-Corneum, S-Lucidum, S-Granulosum, S-Spinosum and S-Basale. And, composition condition was constructed with the alteration modeling that was established to separate the division parts for conversion system. We will be possible to progress the improvement effectiveness of the skin and to consist of the continuous hydration control system for functional on the skin. We will be possible to progress the improvement effectiveness of the skin and to consist of the continuous penetration control system for functional energy on the skin.