• Computers and Concrete
• /
• v.19 no.6
• /
• pp.711-716
• /
• 2017

This paper presents a method using artificial neural networks (ANNs) to predict the residual moment capacity of thermally insulated reinforced concrete (RC) beams exposed to fire. The use of heat resistant insulation material protects concrete beams against the harmful effects of fire. If it is desired to calculate the residual moment capacity of the beams in this state, the determination of the moment capacity of thermally insulated beams exposed to fire involves several consecutive calculations, which is significantly easier when ANNs are used. Beam width, beam effective depth, fire duration, concrete compressive and steel tensile strength, steel area, thermal conductivity of insulation material can influence behavior of RC beams exposed to high temperatures. In this study, a finite difference method was used to calculate the temperature distribution in a cross section of the beam, and temperature distribution, reduction mechanical properties of concrete and reinforcing steel and moment capacity were calculated using existing relations in literature. Data was generated for 336 beams with different beam width ($b_w$), beam account height (h), fire duration (t), mechanical properties of concrete ($f_{cd}$) and reinforcing steel ($f_{yd}$), steel area ($A_s$), insulation material thermal conductivity (kinsulation). Five input parameters ($b_w$, h, $f_{cd}$, $f_{yd}$, $A_s$ and $k_{insulation}$) were used in the ANN to estimate the moment capacity ($M_r$). The trained model allowed the investigation of the effects on the moment capacity of the insulation material and the results indicated that the use of insulation materials with the smallest value of the thermal conductivities used in calculations is effective in protecting the RC beam against fire.

• Computers and Concrete
• /
• v.2 no.1
• /
• pp.79-96
• /
• 2005

The use of high-strength concrete (HSC) has significantly increased over the last decade, especially in offshore structures, long-span bridges, and tall buildings. The behavior of such concrete is noticeably different from that of normal-strength concrete (NSC) due to its different microstructure and mode of failure. In particular, the shear capacity of structural members made of HSC is a concern and must be carefully evaluated. The shear fracture surface in HSC members is usually trans-granular (propagates across coarse aggregates) and is therefore smoother than that in NSC members, which reduces the effect of shear transfer mechanisms through aggregate interlock across cracks, thus reducing the ultimate shear strength. Current code provisions for shear design are mainly based on experimental results obtained on NSC members having compressive strength of up to 50MPa. The validity of such methods to calculate the shear strength of HSC members is still questionable. In this study, a new approach based on artificial neural networks (ANNs) was used to predict the shear capacity of NSC and HSC beams without shear reinforcement. Shear capacities predicted by the ANN model were compared to those of five other methods commonly used in shear investigations: the ACI method, the CSA simplified method, Response 2000, Eurocode-2, and Zsutty's method. A sensitivity analysis was conducted to evaluate the ability of ANNs to capture the effect of main shear design parameters (concrete compressive strength, amount of longitudinal reinforcement, beam size, and shear span to depth ratio) on the shear capacity of reinforced NSC and HSC beams. It was found that the ANN model outperformed all other considered methods, providing more accurate results of shear capacity, and better capturing the effect of basic shear design parameters. Therefore, it offers an efficient alternative to evaluate the shear capacity of NSC and HSC members without stirrups.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.1-9
• /
• 2002

Evolutionary artificial neural networks (EANNs) are towards the near optimal ANN using the global search of evolutionary instead of trial-and-error process. However, many real-world problems are too hard to be solved by only one ANN. Recently there has been plenty of interest on combining ANNs in the last generation to improve the performance and reliability. This paper proposes a new approach of constructing multiple ANNs which complement each other by speciation. Also, we develop a multiple ANN to combine the results in abstract, rank, and measurement levels. The experimental results on Australian credit approval data from UCI benchmark data set have shown that combining of the speciated EANNs have better recognition ability than EANNs which are not speciated, and the average error rate of 0.105 proves the superiority of the proposed EANNs.

• Advances in concrete construction
• /
• v.10 no.6
• /
• pp.479-488
• /
• 2020

The experimental and numerical works were carried out on high performance fiber reinforced concrete (HPFRC) with w/cm ratios ranging from 0.25 to 0.40, fiber volume fraction (Vf)=0-1.5% and 10% silica fume replacement. Improvements in compressive and flexural strengths obtained for HPFRC are moderate and significant, respectively, Empirical equations developed for the compressive strength and flexural strength of HPFRC as a function of fiber volume fraction. A relation between flexural strength and compressive strength of HPFRC with R=0.78 was developed. Due to the complex mix proportions and non-linear relationship between the mix proportions and properties, models with reliable predictive capabilities are not developed and also research on HPFRC was empirical. In this paper due to the inadequacy of present method, a back propagation-neural network (BP-NN) was employed to estimate the 28-day compressive strength of HPFRC mixes. BP-NN model was built to implement the highly non-linear relationship between the mix proportions and their properties. This paper describes the data sets collected, training of ANNs and comparison of the experimental results obtained for various mixtures. On statistical analyses of collected data, a multiple linear regression (MLR) model with R2=0.78 was developed for the prediction of compressive strength of HPFRC mixes, and average absolute error (AAE) obtained is 6.5%. On validation of the data sets by NNs, the error range was within 2% of the actual values. ANN model has given the significant degree of accuracy and reliability compared to the MLR model. ANN approach can be effectively used to estimate the 28-day compressive strength of fibrous concrete mixes and is practical.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.393-404
• /
• 2023

Skewness and kurtosis are important higher-order statistics for simulating non-Gaussian wind pressure series on low-rise buildings, but their predictions are less studied in comparison with those of the low order statistics as mean and rms. The distribution gradients of skewness and kurtosis on roofs are evidently higher than those of mean and rms, which increases their prediction difficulty. The conventional artificial neural networks (ANNs) used for predicting mean and rms show unsatisfactory accuracy in predicting skewness and kurtosis owing to the limited capacity of shallow learning of ANNs. In this work, the deep neural networks (DNNs) model with the ability of deep learning is introduced to predict the skewness and kurtosis on a low-rise building. For obtaining the optimal generalization of the DNNs model, the hyper parameters are automatically determined by Bayesian Optimization (BO). Moreover, for providing a benchmark for future studies on predicting higher order statistics, the data sets for training and testing the DNNs model are extracted from the internationally open NIST-UWO database, and the prediction errors of all taps are comprehensively quantified by various error metrices. The results show that the prediction accuracy in this study is apparently better than that in the literature, since the correlation coefficient between the predicted and experimental results is 0.99 and 0.75 in this paper and the literature respectively. In the untrained cornering wind direction, the distributions of skewness and kurtosis are well captured by DNNs on the whole building including the roof corner with strong non-normality, and the correlation coefficients between the predicted and experimental results are 0.99 and 0.95 for skewness and kurtosis respectively.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.155-159
• /
• 2004

Recently, there are many trials about Artificial neural networks : ANNs structure and studying method of researches for forecasting traffic volume. ANNs have a powerful capabilities of recognizing pattern with a flexible non-linear model. However, ANNs have some overfitting problems in dealing with a lot of parameters because of its non-linear problems. This research deals with the application of a variety of model selection criterion for cancellation of the overfitting problems. Especially, this aims at analyzing which the selecting model cancels the overfitting problems and guarantees the transferability from time measure. Results in this study are as follow. First, the model which is selecting in sample does not guarantees the best capabilities of out-of-sample. So to speak, the best model in sample is no relationship with the capabilities of out-of-sample like many existing researches. Second, in stability of model selecting criterion, AIC3, AICC, BIC are available but AIC4 has a large variation comparing with the best model. In time-series analysis and forecasting, we need more quantitable data analysis and another time-series analysis because uncertainty of a model can have an effect on correlation between in-sample and out-of-sample.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.6
• /
• pp.176-184
• /
• 2000

Reverse engineering (RE) is a process to create computer aided design (CAD) models from the scanned data of an existing part acquired using 3D position scanners. This paper proposes a novel methodology of extracting geometric features directly from a set of 3D scanned points, which utilizes the concepts of feature-based technology and artificial neural networks (ANNs). The use of ANN has enabled the development of a flexible feature-based RE application that can be trained to deal with various features. The following four main tasks were mainly investigated and implemented: (1) Data reduction; (2) edge detection; (3) ANN-based feature recognition; (4) feature extraction. This approach was validated with a variety of real industrial components. The test results show that the developed feature-based RE application proved to be suitable for reconstructing prismatic features such as block, pocket, step, slot, hole, and boss, which are very common and crucial in mechanical engineering products.

• Journal of Electrical Engineering and Technology
• /
• v.6 no.6
• /
• pp.760-768
• /
• 2011

The performance of transmission lines and its shielding design during a lightning phenomenon are quite essential in the maintenance of a reliable power supply to consumers. The leader progression model, as an advanced approach, has been recently developed to calculate the shielding failure rate (SFR) of transmission lines using geometrical data and physical behavior of upward and downward lightning leaders. However, such method is quite time consuming. In the present paper, an effective method that utilizes artificial neural networks (ANNs) to create a metamodel for calculating the SFR of a transmission line based on shielding angle and height is introduced. The results of investigations on a real case study reveal that, through proper selection of an ANN structure and good training, the ANN prediction is very close to the result of the detailed simulation, whereas the Processing time is by far lower than that of the detailed model.

• Journal of Mechanical Science and Technology
• /
• v.19 no.3
• /
• pp.846-859
• /
• 2005

Support vector machines (SVMs) have become one of the most popular approaches to learning from examples and have many potential applications in science and engineering. However, their applications in fault diagnosis of rotating machinery are rather limited. Most of the published papers focus on some special fault diagnoses. This study covers the overall diagnosis procedures on most of the faults experienced in rotating machinery and examines the performance of different SVMs strategies. The excellent characteristics of SVMs are demonstrated by comparing the results obtained by artificial neural networks (ANNs) using vibration signals of a fault simulator.

• Earthquakes and Structures
• /
• v.8 no.5
• /
• pp.1171-1190
• /
• 2015

Enhancement of strength and ductility is the main reason for the extensive use of FRP jackets to provide external confinement to reinforced concrete columns especially in seismic areas. Therefore, numerous researches have been carried out in order to provide a better description of the behavior of FRP-confined concrete for practical design purposes. This study presents a new approach to obtain strength enhancement of CFRP (carbon fiber reinforced polymer) confined concrete cylinders by applying artificial neural networks (ANNs). The proposed ANN model is based on experimental results collected from literature. It represents the ultimate strength of concrete cylinders after CFRP confinement which is also given in explicit form in terms of geometrical and mechanical parameters. The accuracy of the proposed ANN model is quite satisfactory when compared to experimental results. Moreover, the results of the proposed ANN model are compared with five important theoretical models proposed by researchers so far and considered to be in good agreement.