• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 추계학술대회 논문집
• /
• pp.47-52
• /
• 2002

There are many factors in machine tool error. These are thermal deformation, geometric error, machine's part assembly error, error caused by tool bending. Among them thermal error is 70% of total error of machine tool . Prediction of thermal error is very difficult. because of nonlinear tendency of machine tool deformation. In this study, we tried thermal error prediction by using multi regression analysis.

• 한국정밀공학회지
• /
• 제25권5호
• /
• pp.52-59
• /
• 2008

The accuracy of the machine tools is degraded because of thermal error of structure due to thermal variation. To improve the accuracy of a machine tools, measurement and prediction of thermal error is very important. The main part of thermal source is spindle due to high speed with friction. The thermal error of spindle is very important because it is over 10% in total thermals errors. In this paper, the suitable thermal error prediction technology for machine tools with open architecture controller is developed and implemented to machine tools. Two thermal error prediction technologies, neural network and multi-linear regression, are investigated in several methods. The multi-linear regression method is more effective for implementation to CNC. The developed thermal error prediction technology is implemented on the internal function of CNC.

• 대한산업공학회지
• /
• 제17권2호
• /
• pp.97-105
• /
• 1991

In developing a regression relationship for a standard data system in work measurement, job characteristics are frequently measured with error when measurements are made in the field under less controlled conditions or when accurate instruments are not available. This paper concerns with the prediction of the total task time when job characteristics are measured with error. Integrated mean square error of prediction(IMSE) is developed as a measure of the effect of errors in job characteristics on the predicted total task time. By evaluating how IMSE is affected by the measurement error in each job characteristic, we can determine which error should be controlled to develop a desirable standard data system.

• International Journal of Contents
• /
• 제13권4호
• /
• pp.23-28
• /
• 2017

Of the total economic loss caused by disasters, 40% are due to floods and floods have a severe impact on human health and life. So, it is important to monitor the water level of a river and to issue a flood warning during unfavorable circumstances. In this paper, we propose a modified error function to improve a hydrological modeling using a multi-layer perceptron (MLP) neural network. When MLP's are trained to minimize the conventional mean-squared error function, the prediction performance is poor because MLP's are highly tunned to training data. Our goal is achieved by preventing overspecialization to training data, which is the main reason for performance degradation for rare or test data. Based on the modified error function, an MLP is trained to predict the water level with rainfall data at upper reaches. Through simulations to predict the water level of Nakdong River near a UNESCO World Heritage Site "Hahoe Village," we verified that the prediction performance of MLP with the modified error function is superior to that with the conventional mean-squared error function, especially maximum error of 40.85cm vs. 55.51cm.

• Journal of Advanced Marine Engineering and Technology
• /
• 제21권1호
• /
• pp.66-70
• /
• 1997

In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance.

• 한국농공학회논문집
• /
• 제47권4호
• /
• pp.65-74
• /
• 2005

AnnAGNPS model was applied to a catchment mainly occupied with bushland for modeling non-point source pollution. Since the single event model cannot handle events longer than 24 hours duration, the event-based calibration was carried out using the continuous mode. As event flows affect sediment and nutrient generation and transport, the calibration of the model was performed in three steps: Hydrologic, Sediment and Nutrient calibrations. The results from hydrologic calibration for the catchment indicate a good prediction of the model with average ARE(Absolute Relative Error) of $24.6\%$ fur the runoff volume and $12\%$ for the peak flow. For the sediment calibration, the average ARE was $198.8\%$ indicating acceptable model performance for the sediment prediction. The predicted TN(Total Nitrogen) and TP(Total Phosphorus) were also found to be acceptable as the average ARE for TN and TP were $175.5\%\;and\;126.5\%$, respectively. The AnnAGNPS model was therefore approved to be appropriate to model non-point source pollution in bushland catchments. In general, the model was likely to result in underestimation for the larger events and overestimation fur the smaller events for the water quality predictions. It was also observed that the large errors in the hydrologic prediction also produced high errors in sediment and nutrient prediction. This was probably due to error propagation in which the error in the hydrologic prediction influenced the generation of error in the water quality prediction. Accurate hydrologic calibration should be hence obtained for a reliable water quality prediction.

• 한국태양에너지학회 논문집
• /
• 제39권2호
• /
• pp.71-80
• /
• 2019

Daily ahead forecast is necessary for the electricity balance between load and supply due to the variability renewable energy. Numerical weather prediction is usually employed to produce the solar irradiance as well as electric power forecast for more than 12 hours forecast horizon. UM-LDAPS model is the numerical weather prediction operated by Korea Meteorological Administration and it generates the 36 hours forecast of hourly total irradiance 4 times a day. This study attempts to evaluate the model performance against the in situ measurements at 37 ground stations from January to May, 2013. Relative mean bias error, mean absolute error and root mean square error of hourly total irradiance are averaged over all ground stations as being 8.2%, 21.2% and 29.6%, respectively. The behavior of mean bias error appears to be different; positively largest in Chupoongnyeong station but negatively largest in Daegu station. The distinct contrast might be attributed to the limitation of microphysics parameterization for thick and thin clouds in the model.

• Nuclear Engineering and Technology
• /
• 제44권4호
• /
• pp.355-362
• /
• 2012

The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.

• 한국도로학회논문집
• /
• 제15권6호
• /
• pp.79-91
• /
• 2013

PURPOSES : The methods of measuring the sound from the noise source are Pass-by method and NCPX (Noble Close Proximity) method. These measuring methods were used to determine the linkage of TAPL (Total Acoustic Pressure Level) and SPL (Sound Pressure Level) in terms of frequencies. METHODS : The frequency analysis methods are DFT (Discrete Fourier Transform) and FFT (Fast Fourier Transform), CPB (Constant Percentage Bandwidth). The CPB analysis was used in this study, based on the 1/3 octave band option configured for the frequency analysis. Furthermore, the regression analysis was used at the condition related to the sound attenuation effect. The MPE (Mean Percentage Error) and RMSE (Root Mean Squared Error) were utilized for calculating the error. RESULTS : From the results of the CPB frequency analysis, the predicted SPL along the frequency has 99.1% maximum precision with the measured SPL, resulting in roughly 1 dB(A) error. The TAPL results have precision by 99.37% with the measured TAPL. The predicted TAPL results at this study by using the SPL prediction model along the frequency have the maximum precision of 98.37% with the vehicle velocity. CONCLUSIONS : The Predicted SPL model along the frequency and the TAPL result by using the predicted SPL model have a high level of accuracy through this study. But the vehicle velocity-TAPL prediction model from the previous study by using the log regression analysis cannot be consistent with the TAPL result by using the predicted SPL model.

• ETRI Journal
• /
• 제42권2호
• /
• pp.258-271
• /
• 2020

A correlation exists between luminance samples and chrominance samples of a color image. It is beneficial to exploit such interchannel redundancy for color image compression. We propose an algorithm that predicts chrominance components Cb and Cr from the luminance component Y. The prediction model is trained by supervised learning with Laplacian-regularized least squares to minimize the total prediction error. Kernel principal component analysis mapping, which reduces computational complexity, is implemented on the same point set at both the encoder and decoder to ensure that predictions are identical at both the ends without signaling extra location information. In addition, chrominance subsampling and entropy coding for model parameters are adopted to further reduce the bit rate. Finally, luminance information and model parameters are stored for image reconstruction. Experimental results show the performance superiority of the proposed algorithm over its predecessor and JPEG, and even over JPEG-XR. The compensation version with the chrominance difference of the proposed algorithm performs close to and even better than JPEG2000 in some cases.