| News Details |
Participation in a scientific discussion committee
2023-10-31
The Head of the Planning and Databases Department at the Upper Euphrates Basin Developing Centre, Dr. (Ahmed Saud Mohammad), participated in the public scientific discussion committee for the master's thesis of the researcher (Omar Munther Jameel) in the Department of Civil Engineering / College of Engineering / University of Anbar, on Thursday, 26/10/2023, on the discussion hall in the college and tagged:
((Modelling response of piles using Artificial Neural Networks - ANNs))))
The study submitted by the student aims to predict the piles load tests from the data of the piles load tests and soil investigation examination tests, as it is considered one of the costly and time-consuming examinations, as well as simulating the relationship (LOAD - SETTLEMENT) of the piles and comparing the presentation of the (ANN) model with the experimental results of the pile load tests, in addition to conducting sensitivity analysis to find out which of the input variables has the greatest impact on the model's output, in addition to using several statistical tests to know the accuracy and reliability of the model.
The discussion committee consisted of:
§ Assoc. Prof. Dr. Adnan Chaid Zeidan, Chairman
§ Prof. Dr. Muayad Abdul-Jabbar Ahmed, Member
§ Dr. Ahmed Saud Mohammed, Member
§ Prof. Dr. Khaled Rasem Mahmoud, Member and Supervisor
The thesis included the development of a predictive model consisting of the inputs and outputs of the model, the determination of data volume, the identification and optimization of the optimal network architecture, the optimal performance of the model and its verification and the conduct of sensitivity analysis.
The results of the study indicated that the model that contains one hidden layer with four nodes is the most accurate model in prediction, in addition to the results of statistical tests of the (ANN) model; we can conclude that the model is a reliable and accurate way to predict the average settlement of piles based on the input parameters.
The model has relatively low RMSE for both test and training data, suggesting that it can accurately predict average settlement values and explain a large portion of the variance in average settlement values. The correlation coefficient (R) and the coefficient of determination (R2) are both high, indicating a strong positive relationship between the average of the expected and actual adjustment values. A comparison was also made in the curves of the values (predicted, measured) and showed a good match and the results of the sensitivity analysis indicate that the log lad has the greatest effect on the output of the model.
The discussion was attended by the Dean of the College of Engineering, Prof. Dr. Ameer Abdul Rahman Hilal, the Assistant Dean for Scientific Affairs and Graduate Studies, Assistant Professor Dr. Muhammad Abdul Ahmed, and the Head of the Civil Engineering Department, Assistant Professor Dr. Ahmed Tariq Noman. Congratulations to the student for obtaining the certificate and for the discussion committee to reconcile and success.
#Upper_Euphrates_Basin_Developing_Center
