Experimental investigation on fresh concrete properties of high strength and durable concrete with prediction models using artificial neural networks | |
| Author | Subedi, Bishnu Prasad |
| Call Number | AIT Thesis no.ST-05-21 |
| Subject(s) | High strength concrete neural networks (Computer science) Concrete--Mixing |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. ST-05-21 |
| Abstract | Several experiments were conducted in the laboratory to determine the fresh concrete properties of high-strength and durable concrete (HSDC) having 28 days compressive strength of 40-150MPa containing different percentage of fly ash, silica fume and superplasticizer. In total, 65 mixes having wide ranges of concrete constituents were cast in order to investigate the influence of different constituent materials of HSDC on its workability which includes slump and slump loss, and setting times. A data base of HSDC was created using experimental results to predict the neural networks model. A slump model and initial setting time model of HSDC were proposed by using Artificial Neural Networks (ANN) and compared these models with actual results obtained from the laboratory as well as multiple regression analysis to check the performance and accuracy of the predicted models. The sensitivity analyses of predicted models were also performed. The test results showed that replacement of cement with fly ash in high-strength and durable concrete accelerates setting times, increases workability and decrease the water demand of the mixture whereas, replacements of cement with silica fume decreases workability and increase the water demand but shows negligible effect on setting times. The loss of workability due to presence of silica fume can be compensated for by incorporating fly ash and superplasticizer. It was observed that the superplasticizer based on modified polycarboxilic ethers (PCE) polymer shows excellent results to produce highly workable high-strength and durable concrete while allowing the use of low water/binder ratio and high silica fume content. However, the setting times are found to increase rapidly while using high dosages of superplasticizer. It was noticed that the use of the combination of fly ash, silica fume and superplasticizer can produce highly workable high-strength and durable concrete. It was found that the predicted slump and setting time models based on artificial neural networks perform better than the multiple regression analysis. From the sensitivity analysis conducted in this study it is concluded that in addition to the fly ash and water content, slump is most sensitive to the content of silica fume and high dosages of superplasticizer whereas, the setting times are most sensitive to fly ash and cement in addition to the superplasticizer and water content. |
| Year | 2005 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. ST-05-21 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Civil and Infrastucture Engineering (DCIE) |
| Academic Program/FoS | Structural Engineering (STE) /Former Name = Structural Engineering and Construction (ST) |
| Chairperson(s) | Pichai Nimityongskul; |
| Examination Committee(s) | Pennung Warnitchai;Thanakorn Pheeraphan; |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2005 |