TY  - CONF
AV  - none
KW  - Cements; Compressive strength; Environmental engineering; Forecasting; Neural networks; Offshore oil well production; Tensile strength
KW  -  Academic fields; Coarse aggregates; Correlation coefficient; Neural network parameters; Prediction tools; Splitting tensile strength; Strength prediction; Water-cement ratio
KW  -  Aggregates
SP  - 531
ID  - scholars7602
TI  - Mix design proportion for strength prediction of rubbercrete using artificial neural network
N1  - cited By 0; Conference of 3rd International Conference on Civil, offshore and Environmental Engineering, ICCOEE 2016 ; Conference Date: 15 August 2016 Through 17 August 2016; Conference Code:180169
N2  - Data on the mix design of rubbercrete experiments are available throughout the literature and utilized in this paper to provide a platform for prediction of strength to obtained predetermined mix design. Using artificial neural network (ANN), the strengths of rubbercrete are predicted using literature data with water-cement ratio, percentage of CR, cement, fine aggregates, coarse aggregates and water as inputs. The desired output are identified as the compressive strength, flexural strength, splitting tensile strength and modulus elasticity of rubbercrete. From the result, it is concluded that different data set, different neural network parameters are required. The overall regression plot for the prediction achieved a correlation coefficient, R of 0.99157. With this prediction tool, the neural network can be used as mix design for selection of rubbercrete mix proportions to facilitate the application and utilization of rubbercrete, not only the academic field, but also in the industry. © 2016 Taylor & Francis Group, London.
SN  - 9781138029781
PB  - CRC Press/Balkema
Y1  - 2016///
EP  - 536
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009725360&doi=10.1201%2fb21942-108&partnerID=40&md5=5abe5deefffdb77cf4719cd71a23e8e3
A1  - Awang, A.
A1  - Mohammed, B.S.
A1  - Mustafa, M.R.
ER  -