• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 춘계학술대회
• /
• pp.822-827
• /
• 2004

In this paper, an intelligent fault diagnosis system is proposed for induction motors through the combination of feature extraction, genetic algorithm (GA) and neural network (ANN) techniques. Features are extracted from motor vibration signals, while reducing data transfers and making on-line application available. GA is used to select most significant features from whole feature database and optimize the ANN structure parameter. Optimized ANN diagnoses the condition of induction motors online after trained by the selected features. The combination of advanced techniques reduces the learning time and increases the diagnosis accuracy. The efficiency of the proposed system is demonstrated through motor faults of electrical and mechanical origin on the induction motors. The results of the test indicate that the proposed system is promising for real time application.

• 한국공작기계학회논문집
• /
• 제16권6호
• /
• pp.125-132
• /
• 2007

Inherent dynamic interaction between flexible disk and workpiece creates partially non-flat surface profile. A flat zone was defined using minimum depth of engagement. Several key parameters were defined to explain the characteristics of the zone. Process conditions including disk rotation speed, initial depth of cut and feed speed were varied to produce product profile database. Correlation between key factors was examined to find the characteristic dependencies. Trends of key parameters were displayed and explained. Higher flat zone ratio was observed for lower depth of cut and higher disk rotation speed. Ratio of minimum depth of cut against target depth of cut increased for higher feed speed and disk rotation speed but was insensitive to the depth of cut variation. The process transition was visualized by continuously displaying instantaneous orientation of the deflected disk and the location of key parameters were clearly marked for comparison.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2008년도 동계학술발표대회 논문집
• /
• pp.642-648
• /
• 2008

In order to analyze the causes of fossil power plant facilities due to a degradation and corrosion, artificial degraded materials composed of the facilities were manufactured. Various experiment were performed based on mechanical test, microstructure observation, hardness test, electrochemical potentiokinetic reactivation test(EPR) and corrosion scale thickness measurement test. The master curves were write out using Larson-Miller parameter to evaluate the degree of degradation with the above diagnosis methods. These data were applied to materials database of fossil power plant diagnosis. Finally expert system on the fossil power plant diagnosis was developed using the master curves and diagnosis algorithms.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 1999년도 춘계 학술발표회 논문집 Proceedings of EESK Conference-Spring
• /
• pp.223-230
• /
• 1999

The seismic damage assessment to the postulated earthquake is attempted for the buildings in the model district of Seoul City. The capacity spectrum method is employed in which the vulnerability functions are expressed as functions of the spectral displacement. the database of the building stock is constructed and managed using Geographic Information System software. The model district is selected to represent the typical structural and residential characteristics of Seoul City The structural properties were collected from the design documents. The field inspections were carried out to find out the current status of the building. They are classified into 11 structural types. The fragility curves in HazUS are employed, The ground motions from the postulated earthquakes are simulated using the Boor's methods, The surface soil in the district is classified into 3 profiles using the depth as the parameter. The one-dimensional wave propagation method is used to calculate he filtered ground motion through surface soil layer. The average spectrum of this sample time histories is used as the demand curves. The calculated results are expressed in maps using GIS software ArcView 3.0a

• 음성과학
• /
• 제14권2호
• /
• pp.105-114
• /
• 2007

The performance of speaker identifier is severely degraded in noisy environments. A study suggested the concept of observation membership for enhancing performances of speaker identifier with noisy speech [1]. The method scaled observation probabilities of input speech by observation identification values decided by SNR. In the paper [1], the authors suggested heuristic parameter values for membership function. In this paper we attempt to apply particle swarm optimization (PSO) for obtaining the optimal parameters for speaker identification in noisy environments. With the speaker identification experiments using the ETRI database we prove that the optimization approach can yield better performance than using only the original membership function.

• 한국군사과학기술학회지
• /
• 제14권6호
• /
• pp.1091-1096
• /
• 2011

The main factors of radar signals used in electronic warfare are Radio Frequency(RF), Pulse Repetition Interval(PRI), Pulse Width(PW), Scan Parameter(SP) and so on. This radar signals may have some important information for the electronic warfare. So, there is a necessity for making a threat database to decide whether the radar signal is a threat or not. When the electronic support system collects some threat radar signals, it needs the search band to control the receivers and filter banks of the system. In this paper we propose search band implementation considering the type and center frequency of the receivers of the electronic support system.

• 대한음성학회지:말소리
• /
• 제54호
• /
• pp.63-72
• /
• 2005

The performance of speech recognition system is degraded by the mismatch between training and test environments. Many studies have been presented to compensate for noise components in the cepstral domain. Recently, higher order cepstral moment normalization method has been introduced to improve recognition accuracy. In this paper, we present real-time high order moment normalization method with post-processing smoothing filter to reduce the parameter estimation error in higher order moment computation. In experiments using Aurora2 database, we obtained error rate reduction of 44.7% with proposed algorithm in comparison with baseline system.

• 대한음성학회지:말소리
• /
• 제60호
• /
• pp.181-190
• /
• 2006

This paper describes a speech enhancement scheme that leads to significant improvements in recognition performance when used in the ASR front-end. The proposed approach is based on adaptive comb filtering and an MMSE-related parameter estimator. While adaptive comb filtering reduces noise components remarkably, it is rarely effective in reducing non-stationary noises. Furthermore, due to the uniformly distributed frequency response of the comb-filter, it can cause serious distortion to clean speech signals. This paper proposes an improved comb-filter that adjusts its spectral magnitude to the original speech, based on the speech absence probability and the gain modification function. In addition, we introduce the modified comb filtering-based speech enhancement scheme for ASR in mobile environments. Evaluation experiments carried out using the Aurora 2 database demonstrate that the proposed method outperforms conventional adaptive comb filtering techniques in both clean and noisy environments.

• Steel and Composite Structures
• /
• 제42권4호
• /
• pp.477-487
• /
• 2022

The shear stiffness of headed-stud shear connectors has no unified definition due to the nonlinear characteristics of its load-slip relationship. A unified framework was firstly adopted to develop a general expression of shear load-slip equation for headed-stud shear connectors varying in a large parameter range based on both force and energy balance. The pre- and post-yield shear stiffness were then determined through bilinear idealization of proposed shear load-slip equation. An updated and carefully selected push-out test database of 157 stud shear connectors, conducting on studs 13~30mm in diameter and on concretes 30~180 MPa in cubic compressive strength, was used for model regression and sensitivity analysis of shear stiffness. An empirical calculation model was also established for the stud shear stiffness. Compared with the previous models through statistical analysis, the proposed model demonstrates a better performance to predict the shear load-slip response and stiffness of the stud shear connectors.

• Geomechanics and Engineering
• /
• 제29권3호
• /
• pp.219-228
• /
• 2022

The most widely used parameter to represent rock abrasiveness is the Cerchar abrasivity index (CAI). The CAI value can be applied to predict wear in TBM cutters. It has been extensively demonstrated that the CAI is affected significantly by cementation degree, strength, and amount of abrasive minerals, i.e., the quartz content or equivalent quartz content in rocks. The relationship between the properties of rocks and the CAI is investigated in this study. A database comprising 223 observations that includes rock types, uniaxial compressive strengths, Brazilian tensile strengths, equivalent quartz contents, quartz contents, brittleness indices, and CAIs is constructed. A linear model is developed by selecting independent variables while considering multicollinearity after performing multiple regression analyses. Machine learning-based regression methods including support vector regression, regression tree regression, k-nearest neighbors regression, random forest regression, and artificial neural network regression are used in addition to multiple linear regression. The results of the random forest regression model show that it yields the best prediction performance.