Predicting blast-induced ground vibration using various types of neural networks     

M. Monjezi  M. Ahmadi  M. Sheikhan  A. Bahrami  A.R. Salimi 《Soil Dynamics and Earthquake Engineering》2010

Prediction of vibration is very important in mining operations as well as civil engineering projects. In this paper, multi layer perceptron neural network (MLPNN), radial basis function neural network (RBFNN) and general regression neural network (GRNN) were utilized to predict ground vibration level in a Sarcheshmeh copper mine, Iran. It was observed that the MLPNN gives the best results. For this technique root mean square error and coefficient of correlation were found 0.03 and 0.954, respectively. Sensitivity analysis showed that distance from the blast, number of holes per delay and maximum charge per delay are the most effective parameters in making ground vibration in the blasting operation.  相似文献   

Predicting Formation Pore-Pressure from Well-Log Data with Hybrid Machine-Learning Optimization Algorithms     

Farsi  Mohammad  Mohamadian  Nima  Ghorbani  Hamzeh  Wood  David A.  Davoodi  Shadfar  Moghadasi  Jamshid  Ahmadi Alvar  Mehdi 《Natural Resources Research》2021,30(5):3455-3481

Natural Resources Research - Accurate prediction of pore-pressures in the subsurface is paramount for successful planning and drilling of oil and gas wellbores. It saves cost and time and helps to...  相似文献   

Stability of elastic frames subjected to earthquake excitations     

Goodarz Ahmadi  Samir Abdel-Rahman 《地震工程与结构动力学》1986,14(3):455-474

Dynamic stability of elastic multistorey frame structures subjected to vertical earthquake ground accelerations is studied. Different stationary, non-stationary, white and non-white random models for earthquake strong motion are considered. The concepts of mean-square and almost-sure stability are reviewed and the corresponding stability theorems are presented. Several general criteria regarding the dynamic stability of the equilibrium state of multistorey frames subjected to random excitations are developed. A few examples concerning the stability of single and multi-degree-of-freedom structures under earthquake excitations are presented. The stability of motion of frames under combined horizontal–vertical acceleration is also briefly discussed.  相似文献   

Bounds on earthquake response of elastic columns     

Goodarz Ahmadi  Naser Mostaghel 《地震工程与结构动力学》1982,10(6):769-777

The dynamics of an elastic column subjected to vertical as well as horizontal ground acceleration during an earthquake strong motion is considered. The Liapunov method of stability analysis is employed and several bounds on the maximum lateral displacement and bending stress are obtained and discussed.  相似文献   

ANN-Based Prediction of Laboratory-Scale Performance of CO2-Foam Flooding for Improving Oil Recovery     

Moosavi  Seyedeh Raha  Wood  David A.  Ahmadi  Mohammad Ali  Choubineh  Abouzar 《Natural Resources Research》2019,28(4):1619-1637

Natural Resources Research - Improving oil recovery by CO2 injection continues to gain momentum in mature oil fields due to its favorable industrial and environmental benefits. One remediation for...  相似文献   

Numerical modeling of MDOF structures with sliding supports using rigid‐plastic link     

A. Vafai  M. Hamidi  G. Ahmadi 《地震工程与结构动力学》2001,30(1):27-42

In this paper, the responses of multi‐degree‐of‐freedom (MDOF) structures on sliding supports subjected to harmonic or random base motions are investigated. Modeling of the friction force under the foundation raft is accomplished by using a fictitious rigid link which has a rigid–perfectly plastic material. This will result in identical equations of motion for the sliding structure, both in the sliding and non‐sliding (stick) phases which greatly simplifies the implementation of the method into a numerical algorithm. In this model the phase transition times are determined with high accuracy. This has two advantages: first, it prevents the so‐called high‐frequency oscillation of the relative velocity at the end of the sliding phase, and second, the time steps can be selected so that each falls exactly within one phase of motion. In this case, the stiffness matrix of the structure remains constant throughout each phase and thus any method for solving the non‐linear differential equations of motion (e.g. Newmark method) can be used without iteration. The proposed method, besides its simplicity, is numerically very efficient and considerably reduces the required analysis time compared with most of the other methods. Copyright © 2001 John Wiley & Sons, Ltd.  相似文献   

Optimisation of deep mixing technique by artificial neural network based on laboratory and field experiments     

Seyed Adel Ahmadi Hosseini  S. Farid F. Mojtahedi 《Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards》2020,14(2):142-157

ABSTRACT

Ground improvement techniques are inevitable for weak soils that cannot endure the design load imposed by superstructures. Deep mixing technique (DMT) as one of these methods is promising and effective when a deep soil layer with low bearing capacity is encountered. Such deposits are quite common in the South-west of Iran where the studied site is located. In order to validate the influence of DMT on the enhancement of strength, both in-situ and laboratory tests were conducted. Afterwards, a parametric study was carried out to investigate the influence of key factors including cement content, water–cement ratio, curing time and plasticity index (PI) on the performance of DMT. In summary, a total of 192 different conditions were examined in this study by using two methods of 3D plotting and artificial neural networks (ANNs) as the optimisation tool. Results proved the importance of water–cement ratio as a key parameter in DMT. Based on the trained networks, ANN was revealed to give satisfactory predictions on the strength of an improved soil with different admixture conditions. More important, the optimisation made by ANN could determine the specific values for selected key admixture factors to reach a desired strength level with the coefficient of determination higher than 0.85.  相似文献   

Particle creation in the framework of $$ gravity     

R. Rashidi  F. Ahmadi  M. R. Setare 《Astrophysics and Space Science》2018,363(9):196

In this paper, we study the problem of massless particle creation in a flat, homogeneous and isotropic universe in the framework of \(f(G)\) gravity. The Bogolyubov coefficients are calculated for the accelerating power-law solutions of the model in a matter dominated universe, from which the total number of created particle per unit volume of space can be obtained. It is proved that the total particle density always has a finite value. Therefore, the Bogolyubov transformations are well-defined and the Hilbert spaces spanned by the vacuum states at different times are unitarily equivalent. We find that the particles with small values of the mode \(k\) are produced in the past and particles with large values of \(k\) are produced only in the future. The negative pressure resulting from the gravitational particle creation is also determined. It is then argued that this pressure even in the presence of energy density and thermal pressure may affect significantly the cosmic expansion.  相似文献