Search In this Thesis
   Search In this Thesis  
العنوان
Using Genetic Programming to Predict (CPT) Soil Cohesion from Laboratory Tests Results /
المؤلف
El-bosraty,Ahmed Hamdy Mahmoud Ahmed.
هيئة الاعداد
باحث / Ahmed Hamdy Mahmoud Ahmed El-bosraty
مشرف / Hesham Araffat Mahdi
مشرف / Ayman Lotfy Fayed
مشرف / Ahmed Mohamed Ebid
تاريخ النشر
2019
عدد الصفحات
160p.;
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
الهندسة المدنية والإنشائية
تاريخ الإجازة
1/1/2019
مكان الإجازة
جامعة عين شمس - كلية الهندسة - إنشاءات
الفهرس
Only 14 pages are availabe for public view

from 160

from 160

Abstract

Static cone penetration test (CPT) is a widely acceptable and reliable geotechnical in-situ tool that provides quick and truthful large amount of data about soil classification, stratification and properties. Undrained shear strength of clay (cu) is one of the main soil parameters that could be reasonably estimated from the CPT results, as it is directly correlated to the tip resistance through the empirical cone factor (Nk). During the last decades, several studies have been carried out to determine reliable values of the Nk factor that change with the variation of the soil type, nature and stress history conditions.
Due to the movement of the construction activities in Egypt towards the east of Port Said region, located at the eastern side of the Nile Delta, and that is characterized, at some locations, with thick deposits of soft to very soft clays, to benefit from its unique location of high economic impact, extensive analyses have been carried out to define the reasonable value of the Nk factor for the prevailing clay at this zone. The performed study focused on using the genetic programming technique (GP) to determine a reliable correlation between the Nk value of east Port Said clay and the consistency limits that can be easily determined in the laboratory. Records of 102 sets of data gathered from the site investigation campaign carried out at the area under study and comprising CPT, U-U triaxial tests, unconfined compression tests, consistency limits and physical properties experiments, were used for the developed GP models. The collected data were divided into training set and validation set. Twelve trials were performed to correlate the (Nk) factor with the clay consistency limits, water content (wc) and unit weight (γ) using training data set, while the produced correlations were tested using the validation data set. The twelve tested formulas show accuracies ranging between 93% and 96% in predicting the Nk factor values
compared to the values back calculated from the CPT and the corresponding shear tests results. The accuracy of the developed correlations was compared to the accuracy of the published correlations in the literature and found to have, in general, higher accuracies in predicting the Nk values for East Port Said clay.
Keywords: Static cone penetration test (CPT), Consistency Limits, Genetic Programming (GP), Cone Factor (Nk).