Mehr lesen
This book presents the prediction of concrete mix ratio using Artificial Neural Network model. An artificial neural network model was developed, trained and tested with 359 concrete mix data sets. These data sets was gotten from concrete companies, sorted and used, for which 70%, 15% and 15% has been used for training, validation and testing phases respectively. A 3-layered feed-forward neural network model with a back-propagation algorithm was adopted. Input layer comprises of 5 nodes representing the Compressive strength (28 days),Fineness Modulus, Coarse Aggregate ratio, Water cement ratio, and Maximum aggregate size and five output parameters which is compressive strength, water, fine aggregate, coarse aggregate and cement contents which are the expected output. The ANN model result was compared with other approach of concrete mix design and was considered adequate. The error from the comparison between the actual output data and the Artificial Neural Network predicted data for the entire output parameters was -0.00083. The results indicate the utility, reliability and usefulness of the artificial neural network (ANN) for accurately predicting concrete mix ratio.
Über den Autor / die Autorin
Munachiso Ogbodo lecciona na Universidade de Port Harcourt, Nigéria. É licenciado em Engenharia Civil e Mestre em Estruturas. Dumde Dinebari é licenciado pela Universidade de Port Harcourt com um bacharelato em Engenharia Civil.
