Evaluation of the Productivity of Ready Mixed Concrete Batch Plant Using Artificial Intelligence Techniques

An accurate prediction of the productivity of the batch plant is considered an essential element for control and planning the construction project. The actual productivity values of construction equipment in the site not consistent with the nominal ones. Therefore, it is necessary to make a comprehensive evaluation of the nominal productivity of equipment concerning the effected factors and then re-evaluate them according to the actual values. This research involved investigation of the ready mixed concrete batch plant to evaluate the productivity with the actual values. Artificial intelligence techniques that are represented by Artificial Neural Network (ANN) and Support Vector Machine (SVM), in addition to the statistical technique, represented by multi-linear regression (MLR), were used as tools for modeling the actual productivity and produce the predicted model for the productivity. Three of accuracy measurements, correlation coefficient (R), mean absolute error (MAE) and root mean square error (RMSE), were used to develop the model and to make a comparison between the actual and predicted productivity. The researcher developed three mathematical models of MLR, ANN, and SVM used to predict the productivity of ready mixed concrete batch plant and also the results showed that the artificial intelligence techniques were more precise than those calculated by the conventional techniques, and SVM model was the best generalization than ANN model in both the training and the validation data.