• Title/Summary/Keyword: Inception

Search Result 636, Processing Time 0.028 seconds

Review of Stall Inception in Turbocompressors (터보압축기의 스톨 발단에 관한 연구 리뷰)

  • Kang, Jeong-Seek;Kang, Shin-Hyoung
    • The KSFM Journal of Fluid Machinery
    • /
    • v.6 no.4 s.21
    • /
    • pp.58-65
    • /
    • 2003
  • Stall inception means the phenomena of rotating stall initiation. The initiation mechanism of rotating stall, the existence of stall precursor, the behavior of stall precursor, stall warning scheme and control scheme are the main interests in stall inception research. Compared to the studies on rotating stall which has long history, the stall inception has been studied for about recent 20 years. After the first discovery of stall precursor in about 20 years ago, many studies were reported on stall inception phenomena. The inception pattern of 'mode' and 'spike' were found, and some of its characteristics are known. And now the stall inception has become one of the fascinating fields in turbomachinery. The development stall control scheme which apply the reliable stall warning scheme will play a great role in future compressor and aeroengine. This paper reviews the results and analysis methods on stall inception studies.

Review of Stall Inception in Turbocompressors (터보압축기의 스톨 발단에 관한 연구 리뷰)

  • Kang, Jeong-Seek;Kang, Shin-Hyoung
    • Proceedings of the KSME Conference
    • /
    • 2003.11a
    • /
    • pp.875-880
    • /
    • 2003
  • Stall inception means the phenomena of rotating stall initiation. The initiation mechanism of rotating stall, the existence of stall precursor, the behavior of stall precursor, stall warning scheme and control scheme are the main interests in stall inception research. Compared to the studies on rotating stall which has long history, the stall inception has been studied for about recent 20 years. After the first discovery of stall precursor in about 20 years ago, many studies were reported on stall inception phenomena. The inception pattern of "mode" and "spike" were found, and some of its characteristics are known. And now the stall inception has become one of the fascinating fields in turbomachinery. This paper reviews the results and analysis methods on stall inception studies.

  • PDF

Suppression of Glow Corona on Streamer and Influence of Thin Wire on its Inception

  • Sima, Wenxia;Fan, Shuochao;Yang, Qing;Wang, Qi
    • Journal of Electrical Engineering and Technology
    • /
    • v.10 no.4
    • /
    • pp.1759-1764
    • /
    • 2015
  • Glow corona is a kind of streamer-free corona that can suppress upward leaders in transmission lines. Thus, it has good application potential in lightning protection. This paper investigates its corona characteristics. The suppression characteristic of glow corona on streamer is studied in air gap under negative DC voltage by wrapping thin wires on the electrode. The effect of thin wire winding patterns on the gap breakdown voltage is analyzed. Results are considered to be attributed to the inception condition of glow corona. Thus an inception test of glow corona is also conducted, and the inception voltage is obtained. Results show that the inception voltage decreases with short winding pitch. Thus an investigation on the inception of glow corona influenced by thin wire is conducted, and an influential factor is proposed to evaluate the influence. The inception regular of thin wire glow corona presented in this paper has certain reference value for the application of glow corona in transmission lines.

A study on evaluation method of NIDS datasets in closed military network (군 폐쇄망 환경에서의 모의 네트워크 데이터 셋 평가 방법 연구)

  • Park, Yong-bin;Shin, Sung-uk;Lee, In-sup
    • Journal of Internet Computing and Services
    • /
    • v.21 no.2
    • /
    • pp.121-130
    • /
    • 2020
  • This paper suggests evaluating the military closed network data as an image which is generated by Generative Adversarial Network (GAN), applying an image evaluation method such as the InceptionV3 model-based Inception Score (IS) and Frechet Inception Distance (FID). We employed the famous image classification models instead of the InceptionV3, added layers to those models, and converted the network data to an image in diverse ways. Experimental results show that the Densenet121 model with one added Dense Layer achieves the best performance in data converted using the arctangent algorithm and 8 * 8 size of the image.

Characteristics and Predictions of the Cavitation Inception in a Turbopump Inducer (터보펌프 인듀서에서 캐비테이션 시작점의 특성 및 예측에 관한 연구)

  • Kang, Byung Yun;Kim, Dae-Jin;Choi, Chang-Ho
    • Journal of the Korean Society of Propulsion Engineers
    • /
    • v.23 no.1
    • /
    • pp.93-100
    • /
    • 2019
  • The cavitation of a turbopump inducer develops from the inception to a critical point, and encounters breakdown finally. In this study, we evaluated the characteristics and predictions of cavitation inception for the turbopump inducer using empirical equations. The empirical equation for the elliptical plate predicted the generation of cavitation inception of the turbopump inducer relatively well. However, in case of the marine propeller, it showed a considerable difference owing to the Reynolds number of the operating point. The cavitation inception occurred earlier as the number of blades increased. However, the solidity had no major impact on the cavitation inception because the cavitation occurred locally at the tip of the leading edge.

Experimental Study on Stall Inception in a High-Speed Centrifugal Compressor (I) - inception Type - (원심압축기 스톨 발단에 관한 실험적 연구 (I) - 스톨 발단 과정 -)

  • Gang, Jeong-Sik;Gang, Sin-Hyeong
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.25 no.10
    • /
    • pp.1436-1444
    • /
    • 2001
  • Stall inception in a high-speed centrifugal compressor has been examined. The main objective was to find stall precursor and to develop a reliable stall warning method. Eight equally spaced fast-response pressure transducers in the inducer detected the spatial structure of small amplitude perturbations, via spatial Fourier transform, as stall is approached. Near the stall inception point, the phase of spatial courier coefficients increased linearly with the speed of impeller relation for several impeller revolutions at all test speeds, and the spectrum at impeller frequency increased as stall is approached. These are the clear evidences that the impeller frequency participates in the stalling process.

Dependence of needle tip Curvature of the Inception Stress and Propagation of electrical tree (침전극의 곡율반경에 따른 트리개시전계 및 트리진전 특성)

  • 박영국;김완수;이홍규;이용희;임기조
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 1999.11a
    • /
    • pp.59-62
    • /
    • 1999
  • Inception and propagation of electrical tree and properties of Partial discharge(PD) pulses accompanying with tree as a function of needle tip radius in low density polyethylene were discussed. To study on these characteristics in different tip radius, we used specimens with needle-plane electrode system made of LDPE, observed inception and propagation of electrical tree by optical microscope with computer and investigated the characteristics of the phase resolved PD pulses accompanying with propagation of electrical tree. The PD quantities detected and analysed were PD magnitude, mean phase angle, average discharge, and the statistical characteristics of the PD pulses. As the tip radius ${\gamma}$ increases, tree inception stress E$\sub$i/ converges to constance value. This result suggests that tree inception stress E$\sub$i/ increases due to stress relaxation when the tip radius is small. Branch-type electrical tree was formed When E$\sub$i/ is 640-750[kV/mm]. bush-type electrical tree when E$\sub$i/ is 370∼400[kV/mm], branch-like electrical tree when E$\sub$i/ is 370-400[kV/mm].

  • PDF

A Study on the Explainability of Inception Network-Derived Image Classification AI Using National Defense Data (국방 데이터를 활용한 인셉션 네트워크 파생 이미지 분류 AI의 설명 가능성 연구)

  • Kangun Cho
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.27 no.2
    • /
    • pp.256-264
    • /
    • 2024
  • In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

Evaluation of Classification Performance of Inception V3 Algorithm for Chest X-ray Images of Patients with Cardiomegaly (심장비대증 환자의 흉부 X선 영상에 대한 Inception V3 알고리즘의 분류 성능평가)

  • Jeong, Woo-Yeon;Kim, Jung-Hun;Park, Ji-Eun;Kim, Min-Jeong;Lee, Jong-Min
    • Journal of the Korean Society of Radiology
    • /
    • v.15 no.4
    • /
    • pp.455-461
    • /
    • 2021
  • Cardiomegaly is one of the most common diseases seen on chest X-rays, but if it is not detected early, it can cause serious complications. In view of this, in recent years, many researches on image analysis in which deep learning algorithms using artificial intelligence are applied to medical care have been conducted with the development of various science and technology fields. In this paper, we would like to evaluate whether the Inception V3 deep learning model is a useful model for the classification of Cardiomegaly using chest X-ray images. For the images used, a total of 1026 chest X-ray images of patients diagnosed with normal heart and those diagnosed with Cardiomegaly in Kyungpook National University Hospital were used. As a result of the experiment, the classification accuracy and loss of the Inception V3 deep learning model according to the presence or absence of Cardiomegaly were 96.0% and 0.22%, respectively. From the research results, it was found that the Inception V3 deep learning model is an excellent deep learning model for feature extraction and classification of chest image data. The Inception V3 deep learning model is considered to be a useful deep learning model for classification of chest diseases, and if such excellent research results are obtained by conducting research using a little more variety of medical image data, I think it will be great help for doctor's diagnosis in future.

Study on the analysis of model propeller tip vortex cavitation inception (모형 추진기 날개 끝 보텍스 캐비테이션 초생분석 연구)

  • Seol, Hanshin;Kim, Seong-Yong
    • The Journal of the Acoustical Society of Korea
    • /
    • v.37 no.6
    • /
    • pp.387-395
    • /
    • 2018
  • In this study, the noise characteristics of the propeller tip vortex cavitation and its inception were analyzed experimentally. Generally, tip vortex cavitation is the first appeared cavity that occurs in a propeller. If propeller tip vortex cavitation is appeared, the level and characteristics of underwater radiated noise changes dramatically compared with the non-cavitating propeller. Therefore, it is very important to analyze the noise characteristics of the propeller cavitation and to detect the cavitation inception in the development of the propulsion system for military vessel and underwater weapon system. The change of noise characteristics due to the inception and growth of the propeller tip vortex cavitation was analyzed. Various imaging-noise measurement and analysis technique were used to determine the inception of propeller cavitation.