• Computers and Concrete
• /
• v.30 no.3
• /
• pp.225-236
• /
• 2022

In this article, Multi-Gene Genetic Programming (MGGP) is proposed for the estimation of the compressive strength of concrete. MGGP is known to be a powerful algorithm able to find a relationship between certain input space features and a desired output vector. With respect to most conventional machine learning algorithms, which are often used as "black boxes" that do not provide a mathematical formulation of the output-input relationship, MGGP is able to identify a closed-form formula for the input-output relationship. In the study presented in this article, MGPP was used to predict the compressive strength of plain concrete, concrete with fly ash, and concrete with furnace slag. A formula was extracted for each mixture and the performance and the accuracy of the predictions were compared to the results of Artificial Neural Network (ANN) and Extreme Learning Machine (ELM) algorithms, which are conventional and well-established machine learning techniques. The results of the study showed that MGGP can achieve a desirable performance, as the coefficients of determination for plain concrete, concrete with ash, and concrete with slag from the testing phase were equal to 0.928, 0.906, 0.890, respectively. In addition, it was found that MGGP outperforms ELM in all cases and its' accuracy is slightly less than ANN's accuracy. However, MGGP models are practical and easy-to-use since they extract closed-form formulas that may be implemented and used for the prediction of compressive strength.

• International Journal of Ocean Engineering and Technology Speciallssue:Selected Papers
• /
• v.4 no.1
• /
• pp.31-37
• /
• 2001

In this paper, an integrated damage identification system (IDIS) is proposed to locate and size damage in real structures. The application of the IDIS to real structures includes the measurement of modal responses, the construction of damage-detection models, and the implementation of measurements and models into the damage-detection process. Firstly, the theory of the damage identification method is outlined. Secondly, the schematic and each component of the IDIS are described. Finally, the practicality of the IDIS is verified from experiments on two different bridge-models, a model plate-grider and a model truss.

• Journal of Biosystems Engineering
• /
• v.37 no.6
• /
• pp.411-419
• /
• 2012

Purpose: Nondestructive evaluation of seed viability is a highly demanded technique in the seed industry. In this study, hyperspectral imaging system was used for discrimination of viable and non-viable radish seeds. Method: The spectral data with the range from 400 to 1000 nm measured by hyperspectral reflectance imaging system were used. A calibration and a test models were developed by partial least square discrimination analysis (PLS-DA) for classification of viable and non-viable radish seeds. Either each data set of visible (400~750 nm) and NIR (750~1000 nm) spectra and the spectra of the combined spectral ranges were used for developing models. Results: The discrimination accuracy of calibration was 84% for visible range and 76.3% for NIR range. The discrimination accuracy of test was 84.2% for visible range and 75.8% for NIR range. The discrimination accuracies of calibration and test with full range were 92.2% and 92.5%, respectively. The resultant images based on the optimal PLS-DA model showed high performance for the discrimination of the nonviable seeds from the viable seeds with the accuracy of 95%. Conclusions: The results showed that hyperspectral reflectance imaging has good potential for discriminating nonviable radish seeds from massive amounts of viable seeds.

• Proceedings of the KSME Conference
• /
• 2001.06a
• /
• pp.553-560
• /
• 2001

Recently, ultrasonic testing simulation has becomes very important in the field of nondestructive evaluation due to its unique capability of providing testing signals without real inspection. The ultrasonic testing simulation requires three elementary models including the transducer beam radiation model, the flaw scattering model, and the reception model. In the present work, we briefly describe an approach to develop the ultrasonic testing model together with its elementary models with the multi-gaussian beam model. Based on this approach, we developed ultrasonic testing simulation program with MATLAB. The performance of the developed program is demonstrated by the predicting of ultrasonic signals from two types of flaws, circulars crack and spheres.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.33 no.3
• /
• pp.257-263
• /
• 2013

Acoustic nonlinearity of surface waves is an effective method to evaluate the micro damage on the surface of materials. In this method, the $A_1$ (magnitude of the fundamental wave) and $A_2$ (magnitude of the second-order harmonic wave) are measured for evaluation of acoustic nonlinearity. However, if there is another source of second-order harmonic wave other than the material itself, the linear relationship between $A_1{^2}$ and $A_2$ will not be guaranteed. Therefore, the second-order harmonic generation by another source should be fully suppressed. In this paper, we investigated the initial second-order harmonic generation in narrowband surface waves by multi-line laser beams. The spatial profile of laser beam was considered in the cases of Gaussian and square-like. The temporal profile was assumed to be Gaussian. In case of Gaussian spatial profile, the generation of the initial second-order harmonic wave was inevitable. However, when the spatial profile was square-like, the generation of the initial second-order harmonic wave was able to be fully suppressed at specific duty ratio. These results mean that the multi-line laser beams of square-like profile with a proper duty ratio are useful to evaluate the acoustic nonlinearity of the generated surface waves.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.20 no.5
• /
• pp.402-411
• /
• 2000

This study investigates the method to measure the viscoelastic properties of asphalt cement, one of the viscoelastic materials, using the ultrasound. The wave speed and attenuation were measured from $-20^{\circ}C$ to $60^{\circ}C$ at the frequency of 2.25MHz. Then, the storage and loss longitudinal moduli, loss tangent storage and loss longitudinal compliances were found depending on the temperatures based on the linear viscoelastic theory. Stress relaxation, creep, and viscosity were predicted using Maxwell and Voigt-Kelvin viscoelastic models. The validity of superposition principle and shift factor were verified by comparing the present results to the data reported in the literatures.

• Journal of Mechanical Science and Technology
• /
• v.20 no.10
• /
• pp.1691-1701
• /
• 2006

The scan type magnetic camera is proposed to improve the limited spatial resolution due to the size of the packaged magnetic sensor. An image of the scan type magnetic camera, ${\partial}B/{\partial}x$ image, is useful for extracting the crack information of a specimen under a large inclined mag netic field distribution due to the poles of magnetizer. The ${\partial}B/{\partial}x$ images of the cracks of different shapes and sizes are calculated by using the improved dipole model proposed in this paper. The improved dipole model uses small divided dipole models, the rotation and relocation of each dipole model and the principle of superposition. Also for a low carbon steel specimen, the experimental results of nondestructive testing obtained by using multiple cracks are compared with the modeling results to verify the effectiveness of ${\partial}B/{\partial}x$ modeling. The improved dipole model can be used to simulate the LMF and ${\partial}B/{\partial}x$ image of a specimen with complex cracks, and to evaluate the cracks quantitatively using magnetic flux leakage testing.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.6
• /
• pp.464-476
• /
• 1998

Determination of location, shape and size of a flaw from its eddy current testing signal is one of the fundamental issues in eddy current nondestructive evaluation of steam generator tubes. Here, we propose an approach to this problem; an inversion of eddy current flaw signal using neural networks trained by finite element model-based synthetic signatures. Total 216 eddy current signals from four different types of axisymmetric flaws in tubes are generated by finite element models of which the accuracy is experimentally validated. From each simulated signature, total 24 eddy current features are extracted and among them 13 features are finally selected for flaw characterization. Based on these features, probabilistic neural networks discriminate flaws into four different types according to the location and the shape, and successively back propagation neural networks determine the size parameters of the discriminated flaw.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1264-1264
• /
• 2001

The affect of surface temperatures of fruits on spectrum which measures actual sugar contents was observed. PLSR was applied to develop the sugar content evaluation system that was not affected by temperature. The reflected spectrum was used at the wavelengths of 654 and 1052nm with the separation distance of 2.5nm. To increase the conformance of a model using unknown samples, let the minimum value of PRESS be an optimum factor. 71 Shingo pears stored in a refrigerator were left in a room temperature for a while and these temperatures and reflected spectrums were measured. Reflected spectrums were measured at the wavelengths of 654 and 1052nm, 3 samples in one second. To measure these at different temperatures, the experiment was repeated hourly and four times. Starting temperatures of 2-3 were increased up to 17. The total number of measured spectrum was 284. To develop a sugar content evaluation system model using measured reflected spectrum, three groups of samples were considered. First group had 51 samples at 14 and second group had 141 samples with lower or higher temperatures than 14. Third group had 155 samples with well distributed temperatures. Other samples were used as validations to ensure the conformance. Measuring the sugar contents of samples with surface temperatures other than 14 were difficult with PLS model I, developed by using a sample temperature of 14. If the sugar contents were compensated using samples' temperatures, results of prediction would be close to the expected results and it would be one of the most important factors to develop this system. PLS models I and II could compensate the temperature but the precision would not come up to the standard. High precision was expected by using samples with wide ranges of temperatures and sugar contents. Both models showed the possibility of an improvement of a sugar content evaluation system disregarding the temperature. For practical use of a system, selecting samples should be done carefully to reduce the effect of the temperature.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2000.04a
• /
• pp.451-457
• /
• 2000

In many dynamic problems such as foundation vibrations ultrasonic nondestructive evaluation and blasting analysts are confronted with the problem of wave propagation in an infinite or semi-infinite media. In order to simulate this situation by a finite analytical model provisions must be made to absorb the stress waves arriving at the boundary. Absorbing boundaries are mathematical artifacts used to prevent wave reflections at the boundaries of discrete models for infinite media under dynamic loads. An analytical study is carried out to examine the effectiveness of Lysmer-Kuhlemeyer model one of the most widely used absorbing boundaries. Validity of the absorbing boundary conditions suggested by Lymer-Kuhlemeyer is examined by adopting the solution of Ewing et al. to the problem of plane waves from a harmonic normal force on the surface of an elastic half-space. The Ewing's problem is than numerically simulated using the finite element method on a semi-circular mesh with and without absorbing boundaries which are represented by viscous dashpots. The absorption ratios are calculated by comparing the displacements at the absorbing boundaries to those at the free field without absorbing boudaries.