scholarly journals Developing a forecasting model of concrete compressive strength using relevance vector machines

2014 ◽  
Vol 3 (2) ◽  
pp. 224 ◽  
Author(s):  
Mohammad Awwad

We analyze results of two experiments that tested effect of adding Silica on the compressive strength of concrete at early stage and after long period. The two experiments evaluated different silica/cement ratios for different mixing periods. Adding Silica to concrete mix produce high early strength material which is highly desirable in airports and highways. More than 90 samples of different silica/cement ratios are tested for compressive strength at 3 and 28 days. Test results showed high early up to 60 MPa. Strength increase is proportional with the increase of silica/cement ratio and mixing time with maximum at ratio of 15/100 and 30 minutes mixing time. A relevance Vector Machine (RVM) model is developed to predict concrete compressive strength using concrete mixture inputs information. RVM model predictions matched experimental data closely. The developed model can be used to predict compressive strength in future periods based on initial information related to cement mixture. Keywords: Relevance Vector Machine, Silicate Percent, Prediction Model, Milling Time, Compressive Strength, Concrete.

2019 ◽  
Vol 9 (10) ◽  
pp. 2064 ◽  
Author(s):  
Yang Liu ◽  
Yicheng Ye ◽  
Qihu Wang ◽  
Xiaoyun Liu ◽  
Weiqi Wang

By applying the Wavelet Relevance Vector Machine (WRVM) method, this research proposes the loose zone of roadway surrounding rock prediction. Based on the theory of relevance vector machine (RVM), the wavelet function is introduced to replace the original Gauss function as the model kernel function to form the WRVM. Five factors affecting the loose zone of roadway surrounding rock are selected as the model input, and the prediction model of the loose zone of roadway surrounding rock based on WRVM is established. By using cross-validation method, the kernel parameters of three kinds of wavelet relevance vector machines (RVMs) are calculated. By comparing and analyzing the root mean square (RMS) error of the test results of each predictive model, the advantages and accuracy of the model are verified. In practical engineering applications, the average relative prediction errors of the Mexican relevance vector machine, the Morlet relevance vector machine and the difference of Gaussian (DOG) relevance vector machine models are accordingly 4.581%, 4.586% and 4.575%. The square correlation coefficient of the predicted samples is 0.95 > 0.9, which further verifies the accuracy and reliability of the proposed method.


Materials ◽  
2019 ◽  
Vol 12 (11) ◽  
pp. 1861 ◽  
Author(s):  
Liming Zhang ◽  
Songbai Liu ◽  
Dongsheng Song

This study investigates the effect of micr-oaggregate filling with copper tailing on the pore structure of cement paste containing copper tailing (CPCT). The particle size of the CPCT and the pore structure of CPCT were analyzed by laser particle size analysis and mercury instruction porosimetry (MIP). Results showed that at the early stage of curing time, with increasing copper tailing content, the compressive strength of cement mortar with copper tailing (CMCT) was lower, and the porosity and pore diameter of CPCT were higher and greater; with the extension of curing age, when the content of copper tailing was less than 30%, the compressive strength of CMCT and the porosity of CPCT changed slightly with the increase of the content of copper tailing. However, the maximum hole diameter of CPCT decreased gradually (a curing age between 7 d and 365 d under standard conditions). Scanning electron microscopy analysis showed that at the early stage of cement hydration in the CPCT, the copper tailing did not fill the pores in CPCT well, while in the later stage of cement hydration, the microaggregates of copper tailing filled the pores well and closely combined with the surrounding hydration products. In the later stage of cement hydration, the microaggregate filling of copper tailing was primarily responsible for the strength increase of the CMCT.


2019 ◽  
Vol 3 (2) ◽  
pp. 41 ◽  
Author(s):  
Osama Youssf ◽  
Reza Hassanli ◽  
Julie E. Mills ◽  
William Skinner ◽  
Xing Ma ◽  
...  

This research extensively investigates how to enhance the mechanical performance of Rubcrete, aiming to move this type of concrete from the laboratory research level to a more practical use by the concrete industry. The effects of many different mixing procedures, chemical pre-treatments on the rubber particles, and the use of fibre additives, have been investigated for their impact upon Rubcrete workability, compressive strength, tensile strength, and flexural strength. The mixing procedure variables included mixing time and mixing order. The rubber pre-treatments utilized chemicals such as Sodium Hydroxide (NaOH), Hydrogen Peroxide (H2O2), Sulphuric acid (H2SO4), Calcium Chloride (CaCl2), Potassium Permanganate (KMnO4), Sodium Bisulphite (NaHsO3), and Silane Coupling Agent. Soaking rubber particles in tap water, or running them through water before mixing, were also tried as a pre-treatment of rubber particles. In addition, the effects of fibre additives such as steel fibres, polypropylene fibres, and rubber fibres, were assessed. X-ray photoelectron spectroscopy (XPS) analysis was utilised to examine some of the pre-treated rubber particles. The results showed that doubling the net mixing time of all mix constituents together enhanced the Rubcrete slump by an average of 22%, and the compressive strength by up to 8%. Mixing rubber with dry cement before adding to the mix increased the compressive strength by up to 3%. Pre-treatment using water was more effective than other chemicals in enhancing the Rubcrete workability. Regardless of the treatment material type, the longer the time of the treatment, the more cleaning of rubber occurred. Significant Rubcrete flexural strength increase occurred when using 1.5% fibre content of both steel fibre and polypropylene fibre.


Teknika ◽  
2017 ◽  
Vol 12 (1) ◽  
pp. 16
Author(s):  
Hani Purwanti ◽  
Galih Widyarini

<p align="center"><strong><em>Abstract</em></strong></p><p><em>Cement which is the main ingredient in making concrete contains non-renewable natural ingredients, potassium silicate. This causes an increase in cement prices every year. In overcoming these problems, there needs to be a modification in concrete mixes that are more environmentally friendly. Mixtures that are able to reduce the need for cement and contain potassium silicate such as charcoal are selected in modified concrete mix material by reviewing compressive strength. The purpose of this study was to determine how much influence the composition of charcoal as a substitute for cement in the preparation of concrete material was observed from compressive strength. The composition of the cement mixture will be replaced with charcoal by 0%, 5% and 10% with concrete compressive strength which is expected to have K200 quality. The research method uses an experimental method for sampling data. There are 3 (three) specimens in each percentage of addition of charcoal. The results of concrete compressive strength with a concrete age of 7 days, 22 days and 28 days under normal conditions without mixture are 31 Mpa, 35 Mpa, and 38 Mpa. The compressive strength of concrete mixed with charcoal as much as 5% is 30 Mpa, 31 Mpa, 36 Mpa. In 10% charcoal mixed concrete is 20 MPa, 27 MPa, and 29 MPa. The results of the compressive strength of the three conditions each showed a decrease in the trend of concrete age 7 days, 21 days and 28 days. Even though the trend has decreased, the compressive strength of the concrete produced still meets K200. This shows that charcoal ash can be used as an alternative to a partial replacement of cement in the concrete mixture for K200 concrete quality.</em></p><p align="center"> </p><p align="center"><strong>Abstrak</strong></p><p>Semen yang merupakan bahan utama pembuatan beton mengandung bahan dasar alam yang tidak dapat diperbarui yaitu kalium silikat. Hal ini menyebabkan adanya peningkatan harga semen setiap tahun. Dalam mengatasi permasalahan tersebut, perlu adanya suatu modifikasi pada campuran beton yang lebih ramah lingkungan. Bahan campuran yang mampu mengurangi kebutuhan semen serta mengandung kalium silikat seperti abu arang dipilih dalam bahan campuran beton modifikasi dengan meninjau kuat tekan.Tujuan penelitian ini adalah untuk mengetahui seberapa besar pengaruh komposisi abu arang sebagai pengganti semen dalam penyusunan material beton ditinjau dari kuat tekan. Adapun komposisi campuran semen yang akan digantikan dengan abu arang sebesar 0%, 5% dan 10% dengan kuat tekan beton yang diharapkan memiliki mutu K200. Adapun metode penelitian ini menggunakan metode eksperimen untuk pengambilan sampel data. Terdapat masing – masing 3 (tiga) benda uji di setiap persentase penambahan abu arang.Hasil kuat tekan beton dengan usia beton 7 hari, 22 hari dan 28 hari dalam kondisi normal tanpa campuran adalah 31 Mpa, 35 Mpa, dan 38 Mpa. Kuat tekan beton yang dicampur abu arang sebanyak 5 % adalah 30 Mpa, 31 Mpa, 36 Mpa. Pada beton campuran abu arang 10% adalah 20 Mpa, 27 Mpa, dan 29 Mpa. Hasil kuat tekan dari ketiga kondisi tersebut masing – masing menunjukkan adanya penurunan trend dari usia beton 7 hari, 21 hari dan 28 hari. Walaupun trend mengalami penurunan, akan tetapi nilai kuat tekan beton yang dihasilkan masih memenuhi K200.Hal tersebut menunjukkan bahwa abu arang dapat digunakan sebagai alternatif pengganti sebagian semen pada campuran beton untuk mutu beton K200.</p><p> </p>


2018 ◽  
Vol 10 (1) ◽  
Author(s):  
Jorge Luis Santamaria ◽  
Vanessa Valentin

Structured and unstructured factors affect concrete product. Structured factors are related to concrete production and unstructured factors are related to the construction process. This study focuses on examining the perceived importance of unstructured factors (i.e., construction-related factors) on concrete compressive strength, concrete costs and production rates on the jobsite and understanding the influence of construction experts’ characteristics, such as profession, on their perceptions. A comprehensive literature review was performed to identify unstructured factors. A survey was then designed and deployed to 297 experts from the construction industry and academia to examine the importance of the identified factors through the relative importance index (RII) method and to further identify additional unstructured factors. Likert aggregation and tests for equality of odds were used to compare and analyze responses of two groups of participants, namely architects and engineers. Curing humidity, crew experience and compaction method are the top three factors perceived to affect concrete compressive strength, whereas crew experience, mixing time and compaction method are the factors perceived to affect concrete costs and production rates the most. Crew experience, compaction method and mixing time dominate the global ranking of perceived affecting factors for concrete compressive strength, costs and production rates. Architects were found to be more likely to perceive high or very high impacts of these factors on concrete. The present study increases our understanding of construction-related factors to facilitate project management and preserve concrete characteristics.


2013 ◽  
Vol 853 ◽  
pp. 600-604 ◽  
Author(s):  
Yu Ren Wang ◽  
Wen Ten Kuo ◽  
Shian Shien Lu ◽  
Yi Fan Shih ◽  
Shih Shian Wei

There are several nondestructive testing techniques available to test the compressive strength of the concrete and the Rebound Hammer Test is among one of the fast and economical methods. Nevertheless, it is found that the prediction results from Rebound Hammer Test are not satisfying (over 20% mean absolute percentage error). In view of this, this research intends to develop a concrete compressive strength prediction model for the SilverSchmidt test hammer, using data collected from 838 lab tests. The Q-values yield from the concrete test hammer SilverSchmidt is set as the input variable and the concrete compressive strength is set as the output variable for the prediction model. For the non-linear relationships, artificial intelligence technique, Support Vector Machines (SVMs), are adopted to develop the prediction models. The results show that the mean absolute percentage errors for SVMs prediction model, 6.76%, improves a lot when comparing to SilverSchmidt predictions. It is recommended that the artificial intelligence prediction models can be applied in the SilverSchmidt tests to improve the prediction accuracy.


2018 ◽  
Vol 162 ◽  
pp. 02018 ◽  
Author(s):  
Dhiyaa Mohammed ◽  
Sameh Tobeia ◽  
Faris Mohammed ◽  
Sarah Hasan

Increasing amount of construction waste and, concrete remnants, in particular pose a serious problem. Concrete waste exist in large amounts, do not decay and need long time for disintegration. Therefore, in this work old demolished concrete is crashed and recycled to produce recycled concrete aggregate which can be reused in new concrete production. The effect of using recycled aggregate on concrete compressive strength has been experimentally investigated; silica fume admixture also is used to improve recycled concrete aggregate compressive strength. The main parameters in this study are recycled aggregate and silica fume admixture. The percent of recycled aggregate ranged from (0-100) %. While the silica fume ranged from (0-10) %. The experimental results show that the average concrete compressive strength decreases from 30.85 MPa to 17.58 MPa when the recycled aggregate percentage increased from 0% to 100%. While, when silica fume is used the concrete compressive strength increase again to 29.2 MPa for samples with 100% of recycled aggregate.


Sign in / Sign up

Export Citation Format

Share Document