• Computers and Concrete
• /
• 제10권6호
• /
• pp.557-573
• /
• 2012

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

• Smart Structures and Systems
• /
• 제26권2호
• /
• pp.241-251
• /
• 2020

Due to the undeniable importance of approximating the concrete compressive strength (CSC) in civil engineering, this paper focuses on presenting four novel optimizations of multi-layer perceptron (MLP) neural network, namely artificial bee colony (ABC-MLP), grasshopper optimization algorithm (GOA-MLP), shuffled frog leaping algorithm (SFLA-MLP), and salp swarm algorithm (SSA-MLP) for predicting this crucial parameter. The used dataset consists of 103 rows of information concerning seven influential parameters (cement, slag, water, fly ash, superplasticizer, fine aggregate, and coarse aggregate). In this work, the best-fitted complexity of each ensemble is determined by a population-based sensitivity analysis. The GOA distinguished its self by the least complexity (population size = 50) and emerged as the second time-effective optimizer. Referring to the prediction results, all tested algorithms are able to construct reliable networks. However, the SSA (Correlation = 0.9652 and Error = 1.3939) and GOA (Correlation = 0.9629 and Error = 1.3922) performed more accurately than ABC (Correlation = 0.7060 and Error = 4.0161) and SFLA (Correlation = 0.8890 and Error = 2.5480). Therefore, the SSA-MLP and GOA-MLP can be promising alternatives to laboratorial and traditional CSC evaluative methods.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 추계 학술발표회 3차
• /
• pp.11-17
• /
• 2010

Numerical analysis was carried out in order to simulate the development of the large deformation that took place on the reinforced earth wall, a part of the Tottori expressway planned to pass Hyogo, Japan. Since this reinforced earth wall had experienced unexpected deformation of the wall during construction, the wall was re-constructed twice. However, the wall deformation showed no sign to cease even at the final stage of the construction. Countermeasures to re-stabilize the wall were demanded. In part I of this paper, it was manifested that subsidence of a 3-meter weak soil due to seepage flow was responsible for the large deformation. A part of concrete panel wall was severely damaged due to extremely large pulling force of geotextile induced by the hammock state. As for the countermeasures, "grouting with slag system" was applied to fill voids of the backfill, and also to prevent further development of settlement in the weak soil layer. "Ground anchor" was also considered to achieve the prescribed factor of safety.

• Structural Engineering and Mechanics
• /
• 제70권6호
• /
• pp.671-681
• /
• 2019

This paper examines the applicability of artificial neural network (ANN) and multivariate adaptive regression splines (MARS) to predict the compressive strength of bacteria incorporated geopolymer concrete (GPC). The mix is composed of new bacterial strain, manufactured sand, ground granulated blast furnace slag, silica fume, metakaolin and fly ash. The concentration of sodium hydroxide (NaOH) is maintained at 8 Molar, sodium silicate ($Na_2SiO_3$) to NaOH weight ratio is 2.33 and the alkaline liquid to binder ratio of 0.35 and ambient curing temperature ($28^{\circ}C$) is maintained for all the mixtures. In ANN, back-propagation training technique was employed for updating the weights of each layer based on the error in the network output. Levenberg-Marquardt algorithm was used for feed-forward back-propagation. MARS model was developed by establishing a relationship between a set of predictors and dependent variables. MARS is based on a divide and conquers strategy partitioning the training data sets into separate regions; each gets its own regression line. Six models based on ANN and MARS were developed to predict the compressive strength of bacteria incorporated GPC for 1, 3, 7, 28, 56 and 90 days. About 70% of the total 84 data sets obtained from experiments were used for development of the models and remaining 30% data was utilized for testing. From the study, it is observed that the predicted values from the models are found to be in good agreement with the corresponding experimental values and the developed models are robust and reliable.

• Smart Structures and Systems
• /
• 제30권2호
• /
• pp.195-207
• /
• 2022

Computational drawbacks associated with regular predictive models have motivated engineers to use hybrid techniques in dealing with complex engineering tasks like simulating the compressive strength of concrete (CSC). This study evaluates the efficiency of tree potential metaheuristic schemes, namely shuffled complex evolution (SCE), multi-verse optimizer (MVO), and beetle antennae search (BAS) for optimizing the performance of a multi-layer perceptron (MLP) system. The models are fed by the information of 1030 concrete specimens (where the amount of cement, blast furnace slag (BFS), fly ash (FA1), water, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA2) are taken as independent factors). The results of the ensembles are compared to unreinforced MLP to examine improvements resulted from the incorporation of the SCE, MVO, and BAS. It was shown that these algorithms can considerably enhance the training and prediction accuracy of the MLP. Overall, the proposed models are capable of presenting an early, inexpensive, and reliable prediction of the CSC. Due to the higher accuracy of the BAS-based model, a predictive formula is extracted from this algorithm.

• Structural Monitoring and Maintenance
• /
• 제2권1호
• /
• pp.35-48
• /
• 2015

The main objective of this study is to evaluate the long-term performance of various concrete composites in natural marine environment prevailing in the Gulf region. Durability assessment studies of such nature are usually carried out under aggressive environments that constitute seawater, chloride and sulfate laden soils and wind, and groundwater conditions. These studies are very vital for sustainable development of marine and off shore reinforced concrete structures of industrial design such as petroleum installations. First round of testing and evaluation, which is presented in this paper, were performed by standard tests under laboratory conditions. Laboratory results presented in this paper will be corroborated with test outcome of ongoing three years field exposure conditions. The field study will include different parameters of investigation for high performance concrete including corrosion inhibitors, type of reinforcement, natural and industrial pozzolanic additives, water to cement ratio, water type, cover thickness, curing conditions, and concrete coatings. Like the laboratory specimens, samples in the field will be monitored for corrosion induced deterioration signs and for any signs of failureover initial period ofthree years. In this paper, laboratory results pertaining to microsilica (SF), ground granulated blast furnace slag (GGBS), epoxy coated rebars and calcium nitrite corrosion inhibitor are very conclusive. Results affirmed that the supplementary cementing materials such as GGBS and SF significantly impacted and enhanced concrete resistivity to chloride ions penetration and hence decrease the corrosion activities on steel bars protected by such concretes. As for epoxy coated rebars applications under high chloride laden conditions, results showed great concern to integrity of the epoxy coating layer on the bar and its stability. On the other hand corrosion inhibiting admixtures such as calcium nitrite proved to be more effective when used in combination with the pozzolanic additives such as GGBS and microsilica.

• 한국세라믹학회지
• /
• 제39권3호
• /
• pp.259-264
• /
• 2002

본 연구에서는 석탄회로 제조된 인공경량골재에 석회석을 첨가하였을 때 소성온도 및 시간에 따른 소성특성을 관찰하였다. 소성온도의 증가에 따라 quartz($SiO_2$)가 감소한 반면 mullite($3Al_2O_3{\cdot}2SiO_2$)가 증가되었으며, 석회석의 첨가에 의해 clinoptiolite와 pagioclase와 같은 소성에 의한 소성광물이 생성되었다. 석탄회 및 석회석으로 제조된 경량골재의 소성성은 주로 소성시간보다는 소성온도에 의해서 좌우되는 것으로 확인되었다. 또한 소성온도 및 시간의 증가는 골재내 형성된 거대기공의 미세화 및 폐기공의 형성으로 전체 기공부피를 축소시키는 경향을 나타냈다. 1000$^{\circ}$C에서 5분가 소성시킨 경량골재의 표면은 용융 슬래그 층의 융착현상에 의해 개기공이 거의 없었으나 내부는 발포가스에 의해 수 ${\mu}$의 미세기공이 폐기공 형태로 균일하게 분포하였다. 이로부터 석회석이 첨가된 소성 경량골재의 적정 소성조건은 소성온도는 약 1000$^{\circ}$C, 소성시간은 5분이 바람직한 것으로 나타났다.

• 자원리싸이클링
• /
• 제28권4호
• /
• pp.44-50
• /
• 2019

국내 전기로 공정에서 산화 반응열 및 탄소 연소열 등으로 인한 화학에너지는 전체 투입 에너지 대비 30%정도로 알려져 있다. 전기로에서 $CO_2$를 저감하기 위해서는 전기로 용해 구간 중에 사용되는 전력에너지를 줄이고 화학에너지 사용을 높여야 한다. 일반적으로 용강 중 탄소를 단독으로 투입할 경우, 탄소가 용강에 용해되기 전 낮은 밀도로 인해 슬래그 층으로 부유한다. 용강 중 탄소 농도가 높을 시 취입하는 산소와 용강 중 탄소의 연소반응으로 인해 전력에너지를 낮추며 화학에너지 사용량을 높일 수 있다. 따라서 탄소 연소열의 효율을 높이기 위해서는 용강 중 새로운 탄재 장입 조건이 필요하다. 한편, Al 제련 후의 부산물로 알려져 있는 Al 드로스는 금속성 Al을 25 mass% 이상 함유하고 있으며 Al은 탄소와 비교하여 높은 산화열을 가지고 있다. 그러나 Al 드로스는 재활용이 어려워 거의 매립하고 있으며, Al 드로스 내 Al의 산화열을 효과적으로 활용하기 위해서는 철강 공정 적용에 대한 연구가 필요하다. 본 연구에서는 화학 에너지의 활용 증대를 위한 기반연구로서, 분코크스와 Al 드로스를 화학에너지 연료로서 활용하여 다양한 배합비 및 반응 온도에서 용강 중 탄소 및 알루미늄의 용해 농도와 용해효율을 조사하였다.

• 한국토양비료학회지
• /
• 제13권2호
• /
• pp.57-63
• /
• 1980

시판(市販)되고 있는 광재규산질비료를 사별(篩別)하여 10목이하(目以下) 20-35목(目) 및 100목이상(目以上)의 3개입자군(個粒子群)으로 분리(分離)하고 그들을 토양(土壤)에 처리했을 때 토양용액(土壤溶液)의 규산함량변화(珪酸含量變化), 토양(土壤)에서의 이동성(移動性) 등을 조사(調査)한바 다음과 같은 결과(結果)를 얻었다. 1. 규산질비료(珪酸質肥料) 20mg을 증류수50ml로 침출(浸出) 했을 때 용액(溶液)의 규산농도(珪酸濃度)는 10목이하(目以下), 20-35목(目), 100목이상(目以上) 입자(粒子)에 처하여 각각 0.3, 1.0, 3.2ppm 이었으며 1N-Na-acetate용액(溶液)으로 침출(浸出)했을 때의 농도(濃度)는 각각 24.5, 126.2, 225.5ppm 이었다. 2. 규산질비료(珪酸質肥料) 20mg을 첨가(添加)한 상양(上壤)20g을 증류수 50ml로 침출(浸出)했을 때 10목이하(目以下), 20-35목(目), 100목이상(目以上) 입자(粒子)의 규산질비료(珪酸質肥料)를 처리한 토양용액중(土壤溶液中)의 규산농도(珪酸濃度)는 규산(珪酸)을 첨가(添加)하지 않았을 때 보다 각각 0.25, 0.97, 3.28ppm 증가하였다. 3. 토양용액(土壤溶液)의 pH는 규산질비료(珪酸質肥料)의 첨가(添加) 여부와 관계(關係)없이 담수일수(湛水日數)와 함께 2~4주(週)까지는 상승(上昇)하고 그 후(後) 6~10주(週)까지 하강(下降)하였다. 이때 수용액중(水溶液中)의 규산농도(珪酸濃度)는 pH와 역상관(逆相關)을 냐타내었으나 담수(湛水) 6~10주이후(週以後)에는 pH와 관계(關係)없이 수용액중(水溶液中)의 규산농도(珪酸濃度)는 증가하였다. 4. 토양투하수(土壤透下水)의 분액별(分液別) 규산농도(珪酸濃度)는 규산질비료(珪酸質肥料)를 첨가(添加)하지 않았을 경우 투과수(透過水)의 양(量)이 0.88 pore volume에 달(達)했을 때 최고치(最高値)를 나타내었으며 20-35목(目), 100목이상(目以上)의 규산질비료(珪酸質肥料)를 첨가(添加)하였을 때에는 각 각 0.94, 1.03pore volume에서 최고농도(最高濃度)를 나타내었다. 5. 1.5pore volume의 증류수를 투하(透下)시킨 후(後) 토양(土壤) column의 부위별(部位別) 규산함량(珪酸含量)을 분석(分析)한 바 수용성(水溶性) 규산(珪酸) 함량(含量)은 6~9cm이하에서는 깊이에 관계없이 일정(一定)하나 그 위 부위(部位)에서는 위로 갈수록 낮은 함량(含量)을 나타내었다. 그러나 1N-Na-acetate 가용규산(可溶珪酸)은 이동(移動)되지 않고 규산(珪酸) 처리부위에 집적(集積)되어 있었다.