• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.16-21
• /
• 2008

Aero-engine, as one kind of rotating machinery with complex structure and high rotating speed, has complicated vibration faults. Therefore, condition monitoring and fault diagnosis system is very important for airplane security. In this paper, a vibration data acquisition and intelligent fault diagnosis system is introduced. First, the vibration data acquisition part is described in detail. This part consists of hardware acquisition modules and software analysis modules which can realize real-time data acquisition and analysis, off-line data analysis, trend analysis, fault simulation and graphical result display. The acquisition vibration data are prepared for the following intelligent fault diagnosis. Secondly, two advanced artificial intelligent(AI) methods, mapping-based and rule-based, are discussed. One is artificial neural network(ANN) which is an ideal tool for aero-engine fault diagnosis and has strong ability to learn complex nonlinear functions. The other is data mining, another AI method, has advantages of discovering knowledge from massive data and automatically extracting diagnostic rules. Thirdly, lots of historical data are used for training the ANN and extracting rules by data mining. Then, real-time data are input into the trained ANN for mapping-based fault diagnosis. At the same time, extracted rules are revised by expert experience and used for rule-based fault diagnosis. From the results of the experiments, the conclusion is obvious that both the two AI methods are effective on aero-engine vibration fault diagnosis, while each of them has its individual quality. The whole system can be developed in local vibration monitoring and real-time fault diagnosis for aero-engine.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.4
• /
• pp.277-286
• /
• 2002

Most of the problems in dealing with the tunnel construction are the uncertainties and complexities of the stress conditions and rock strengths in ahead of the tunnel excavation. The limitations on the investigation technology, inaccessibility of borehole test in mountain area and public hatred also restrict our knowledge on the geologic conditions on the mountainous tunneling area. Nevertheless an extensive and superior geophysical exploration data is possibly acquired deep within the mountain area, with up to the tunnel locations in the case of alternative design or turn-key base projects. An appealing claim in the use of artificial neural networks (ANN) is that they give a more trustworthy results on our data based on identifying relevant input variables such as a little geotechnical information and biological learning principles. In this study, error back-propagation algorithm that is one of the teaching techniques of ANN is applied to presupposition on Rock Mass Ratings (RMR) for unknown tunnel area. In order to verify the applicability of this model, a 4km railway tunnel's field data are verified and used as input parameters for the prediction of RMR, with the learned pattern by error back propagation logics. ANN is one of basic methods in solving the geotechnical uncertainties and helpful in solving the problems with data consistency, but needs some modification on the technical problems and we hope our study to be developed in the future design work.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.11
• /
• pp.99-107
• /
• 2009

Since a long work piece influences the natural frequency of the entire system with a miniature high speed spindle, a bar-feeder is used for a long work piece to improve the vibration characteristics of a spindle system. Therefore, it is very important to design optimally support positions between a bar-feeder and a long work piece for a miniature high speed spindle system. The goal of the current paper is to present an optimization method for the design of support positions between a bar-feeder and a long work piece. This optimization method is effectively composed of the method of design of experiment (DOE), the artificial neural network (ANN) and the genetic algorithm (GA). First, finite element models which include a high speed spindle, a long work piece and the support conditions of a bar-feeder were generated from the orthogonal array of the DOE method, and then the results of natural vibration analysis using FEM were provided for the learning inputs of the neural network. Finally, the design of bar-feeder support positions was optimized by the genetic algorithm method using the neural network approximations.

• Journal of Information Technology Application
• /
• v.1
• /
• pp.173-211
• /
• 1999

The task of classification permeates all walks of life, from business and economics to science and public policy. In this context, nonlinear techniques from artificial intelligence have often proven to be more effective than the methods of classical statistics. The objective of knowledge discovery and data mining is to support decision making through the effective use of information. The automated approach to knowledge discovery is especially useful when dealing with large data sets or complex relationships. For many applications, automated software may find subtle patterns which escape the notice of manual analysis, or whose complexity exceeds the cognitive capabilities of humans. This paper explores the utility of a collaborative learning approach involving integrated models in the preprocessing and postprocessing stages. For instance, a genetic algorithm effects feature-weight optimization in a preprocessing module. Moreover, an inductive tree, artificial neural network (ANN), and k-nearest neighbor (kNN) techniques serve as postprocessing modules. More specifically, the postprocessors act as second0order classifiers which determine the best first-order classifier on a case-by-case basis. In addition to the second-order models, a voting scheme is investigated as a simple, but efficient, postprocessing model. The first-order models consist of statistical and machine learning models such as logistic regression (logit), multivariate discriminant analysis (MDA), ANN, and kNN. The genetic algorithm, inductive decision tree, and voting scheme act as kernel modules for collaborative learning. These ideas are explored against the background of a practical application relating to financial fraud management which exemplifies a binary classification problem.

• 한국전산유체공학회:학술대회논문집
• /
• 2011.05a
• /
• pp.286-290
• /
• 2011

This paper introduces the optimum macro-siting of a potential site for an offshore wind farm around Jeju Island using the RDAPS sea wind model. The statistical model was developed by analyzing the sea wind data from RDAPS model, and the meso-scale digital wind map was prepared. To develop the high resolution spatial calibration model, Artificial Neural Network(ANN) models were used to construct the wind and bathymetric maps. Accuracy and consistency of wind/bathymetric spatial calibration models were obtained using analysis of variance. The optimization problem was defined to maximize the energy density satisfying the criteria of maximum water depth and maximum distance from the coastline. The candidate site was selected through Genetic Algorithm(GA). From the results, it is possible to predict roughly a candidate site location for the installation of the offshore wind jam, and to evaluate the wind resources of the proposed site.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.6
• /
• pp.1655-1665
• /
• 2014

Dynamic displacements of structures shows general behavior of structures. Generally, It is used to estimate structure condition and trustworthy physical quantity directly. Especially, measuring vertical displacement which is affected by moving load is very important part to find or identify a problem of bridge in advance. However directly measuring vertical displacement of the bridge is difficult because of test conditions and restriction of measuring equipment. In this study, Artificial Neural Network (ANN) is used to suggest estimation method of bridge displacement to overcome constrain conditions, restriction and so on. Horizontal strain and vertical displacement which are measured by appling random moving load on the bridge are applied for learning and verification of ANN. Measured horizontal strain is used to learn ANN to estimate vertical displacement of the bridge. Numerical analysis is used to acquire learning data for axis strain and vertical displacement for applying ANN. Moving load scenario which is made by vehicle type and vehicle distance time using Pearson Type III distribution is applied to analysis modeling to reflect real traffic situation. Estimated vertical displacement in respect of horizontal strain according to learning result using ANN is compared with vertical displacement of experiment and it presents vertical displacement of experiment well.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2001.09a
• /
• pp.208-215
• /
• 2001

The vertical irregularities occurred in the structure may lessen the overall seismic capacity of the structure. Seismic capacity evaluation guidelines (e.g. FEMA 175, ATC-14) propose the criterion for the vertical irregularities of mass, stiffness and strength respectively. But, the criterion seems groundless and leads us to make a true/false decision only. This study is to draw a reasonable basis on which multi-level grading is possible based fur the evaluation of existing buildings. Time history analysis for 3-,5-, and 10-story steel frame structures has been performed using several earthquake data. ANN (Artificial Neural Network) is introduced to find the relative contribution factor of the irregularities along the irregular position. Also, the application system fur the seismic capacity evaluation can be established using the trained ANN.

• Environmental Analysis Health and Toxicology
• /
• v.19 no.1
• /
• pp.41-47
• /
• 2004

Air quality monitoring is a primary activity for industrial and social environment. The government push for pollutants that must be monitored. Especially, the VOCs (Volatile Organic Compounds), which are very harmful for human and environment, should be controlled under the government policy. We have been developed a VOCs measurement system which recognize various kinds and quantities of VOCs, such as benzene, toluene, and xylene (BTX). Especially, we designed sensor array with various kinds of gas sensor and ANN (Artificial Neural Network) algorithm. The measured values for BTX have errors of-4ppm.

• Journal of the Korean Society of Safety
• /
• v.33 no.6
• /
• pp.42-49
• /
• 2018

In this study, we have developed a prediction model for expansion and contraction behaviors of expansion joint in Gwangan Bridge using machine learning techniques and bridge monitoring data. In the development of the prediction model, two famous machine learning techniques, multiple regression analysis (MRA) and artificial neural network (ANN), were employed. Structural monitoring data obtained from bridge monitoring system of Gwangan Bridge were used to train and validate the developed models. From the results, it was found that the expansion and contraction behaviors predicted by the developed models are matched well with actual expansion and contraction behaviors of Gwangan Bridge. Therefore, it can be concluded that both MRA and ANN models can be used to predict the expansion and contraction behaviors of Gwangan Bridge without actual measurements of those behaviors.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.5
• /
• pp.19-31
• /
• 2021

Groundwater level (GWL) causes the stress state within soil and affects the bearing capacity and the settlement of foundation. In this study, the analyses of influencing factors on GWL fluctuation were performed. From the results, river stage and moving average of precipitation were main influence components for urban near large river and rural areas, respectively. In addition, the prediction performance of GWL using artificial neural network (ANN) was conducted with respect to the influence components. As a result, the effect of main component was significant on the prediction performance of GWL.