• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1069-1074
• /
• 2008

Tool condition monitoring (TCM) is crucial for improvement of productivity in manufacturing process. However, TCM techniques have not been applied to monitor tool failure in an industrial gear shaving application. Therefore, this work studied a statistical TCM method for monitoring gear shaving tool condition. The method modeled the shaving process using beta probability distribution in order to extract the effective features. Modeling includes rectifying for converting a bi-modal distribution into a unimodal distribution, estimating parameters of beta probability distribution based on method of moments. The usefulness of features obtained from the proposed method was evaluated and discussed.

• 한국생산제조학회지
• /
• 제7권1호
• /
• pp.69-74
• /
• 1998

In order to monitor the tool wear in milling operation, cutting force is measured as the tool wear increased. The digital signal processing methods are used to detect the tool wear . As AR parameter extract the feature of tool wear , it can be used as input parameter of pattern classifier. The FFT monitor the tool wear exactly , but it can not do real time signal processing. The band energy method can be used to real time monitoring of tool wear ,but int can degrade the exact monitoring.

• Journal of information and communication convergence engineering
• /
• 제7권4호
• /
• pp.551-555
• /
• 2009

This paper proposes a signal generation method for automatic control of a monitoring camera. Using the control signal, the monitoring camera can track a moving object and keep it near the image center for a longer time. The proposed method is estimated in the experiments that automatically move a maker located at the specified position to the image center.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2008년도 추계 학술발표회
• /
• pp.436-452
• /
• 2008

In this study, the settlement prediction method based on field monitoring data under preloading improvement with ramp loading is developed. Settlement behavior can be predicted with field monitored settlement throughout the entire preloading process including ramp loading followed by constant loading. The developed method is verified by comparing its predicted results with results from physical model tests and field monitoring data.

• Structural Monitoring and Maintenance
• /
• 제7권2호
• /
• pp.109-124
• /
• 2020

Benefiting from the massive monitoring data collected by the Structural health monitoring (SHM) system, scholars can grasp the complex environmental effects and structural state during structure operation. However, the monitoring data is often missing due to sensor faults and other reasons. It is necessary to study the recovery method of missing monitoring data. Taking the structural temperature monitoring data of Nanjing Dashengguan Yangtze River Bridge as an example, the long short-term memory (LSTM) network-based recovery method for missing structural temperature data is proposed in this paper. Firstly, the prediction results of temperature data using LSTM network, support vector machine (SVM), and wavelet neural network (WNN) are compared to verify the accuracy advantage of LSTM network in predicting time series data (such as structural temperature). Secondly, the application of LSTM network in the recovery of missing structural temperature data is discussed in detail. The results show that: the LSTM network can effectively recover the missing structural temperature data; incorporating more intact sensor data as input will further improve the recovery effect of missing data; selecting the sensor data which has a higher correlation coefficient with the data we want to recover as the input can achieve higher accuracy.

• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.11-21
• /
• 2020

The hinge joint is the key to the overall cooperative working performance of the assembled beam bridge, and it is also the weakest part during the service period. This paper proposes a method for monitoring and evaluating the lateral cooperative working performance of fabricated beam bridges based on dynamic strain correlation coefficient indicator. This method is suitable for monitoring and evaluation of hinge joints status between prefabricated girders and overall cooperative working performance of bridge, without interruption of traffic and easy implementation. The remote cloud monitoring and diagnosis system was designed and implemented on a real assembled beam bridge. The algorithms of data preprocessing, online indicator extraction and status diagnosis were given, and the corresponding software platform and scientific computing environment for cloud operation were developed. Through the analysis of real bridge monitoring data, the effectiveness and accuracy of the method are proved and it can be used in the health monitoring system of such bridges.

• Smart Structures and Systems
• /
• 제21권5호
• /
• pp.601-609
• /
• 2018

The estimated probabilistic model of wind data based on the conventional approach may have high discrepancy compared with the true distribution because of the uncertainty caused by the instrument error and limited monitoring data. A sequential quadratic programming (SQP) algorithm-based finite mixture modeling method has been developed in the companion paper and is conducted to formulate the joint probability density function (PDF) of wind speed and direction using the wind monitoring data of the investigated bridge. The established bivariate model of wind speed and direction only represents the features of available wind monitoring data. To characterize the stochastic properties of the wind parameters with the subsequent wind monitoring data, in this study, Bayesian inference approach considering the uncertainty is proposed to update the wind parameters in the bivariate probabilistic model. The slice sampling algorithm of Markov chain Monte Carlo (MCMC) method is applied to establish the multi-dimensional and complex posterior distribution which is analytically intractable. The numerical simulation examples for univariate and bivariate models are carried out to verify the effectiveness of the proposed method. In addition, the proposed Bayesian inference approach is used to update and optimize the parameters in the bivariate model using the wind monitoring data from the investigated bridge. The results indicate that the proposed Bayesian inference approach is feasible and can be employed to predict the bivariate distribution of wind speed and direction with limited monitoring data.

• Journal of Electrical Engineering and Technology
• /
• 제8권2호
• /
• pp.206-214
• /
• 2013

This paper proposes a new method for monitoring local voltage stability using the saddle node bifurcation set or loadability boundary in two dimensional power parameter space. The method includes three main steps. First step is to determine the critical buses and the second step is building the static voltage stability boundary or the saddle node bifurcation set. Final step is monitoring the voltage stability through the distance from current operating point to the boundary. Critical buses are defined through the right eigenvector by direct method. The boundary of the static voltage stability region is a quadratic curve that can be obtained by the proposed method that is combining a variation of standard direct method and Thevenin equivalent model of electric power system. And finally the distance is computed through the Euclid norm of normal vector of the boundary at the closest saddle node bifurcation point. The advantage of the proposed method is that it gets the advantages of both methods, the accuracy of the direct method and simple of Thevenin Equivalent model. Thus, the proposed method holds some promises in terms of performing the real-time voltage stability monitoring of power system. Test results of New England 39 bus system are presented to show the effectiveness of the proposed method.

• 대한기계학회논문집
• /
• 제19권7호
• /
• pp.1563-1572
• /
• 1995

The on-line cure monitoring during the cure process of fiber reinforced resin matrix composite material is important for the better quality and productivity. Among several cure monitoring methods, the dielectrometry that uses electrodes as its sensor is known to be the most promising method. In this study, the sensitivity of the dielectric sensor for the on-line cure monitoring was analyzed by finite element method and compared to the experimental results. Using the analytical results, the equation for the capacitance of the sensor was derived. Also, the optimal sensor design method was suggested after analyzing several different sensor shapes.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제55권1호
• /
• pp.20-25
• /
• 2006

We suggest a novel temperature detection method utilized in temperature monitoring system. Suggested method detects temperature variation by using $R_{ds(on)}$ characteristics of MOSFET, while conventional methods are using extra devices such as a temperature sensor or an over-temperature detection transistor. For voltage detection between drain and source, 10 bits resolution ADC is needed. Therefore possible measurement signal range is about ten mV. If detected temperature's voltage exceed protection temperature's voltage then controller generates OT (Over Temperature) signal to stop MOSFET's trigger signal. Whole process of measurement is controlled by software. Experimental results show that the developed temperature monitoring system can provide the suitable temperature monitoring method and difference between detected and data sheet value of the suggested system is about $3\%$.