Projects
Updates about recent works
On the current page, some additional explanations about my recent works (including articles and thesis) are mentioned.
Chisel bits cutting force estimation using XGBoost and different optimization algorithms
Abstract
The design and selection of tools for mechanized excavations is a crucial topic in the field of tunneling. Chisel bits are commonly used tools for soft ground, with the required cutting force being a vital factor in tool design. However, current methods either lack accuracy or fail to consider all necessary parameters. To address this issue, a new cutting force prediction model was developed to improve response quality and consider the most effective parameters. 206 data points were collected from studies on rock cutting with different strength, including information such as Uniaxial compressive strength, Brazilian tensile strength, Depth, Width, Rake angle, and clearance angle. Five different algorithms were then used to optimize the Hyperparameters in the XGBoost method, including Grid Search, Random Search, Bayesian Algorithm, Differential Evolution, and Optuna. Results showed that while most algorithms provided appropriate responses, the Grid Search and Bayesian Algorithm methods were the most effective, with R2 values (in test and train) of 0.876 and 0.93 in GS and 0.872 and 0.926 in BO, respectively. Upon comparison of the two methods, it was discovered that the GS approach yields a superior solution; however, it is also more sensitive to tuning, requires more calculations, and takes longer to provide a solution. When assessing the newly presented approach against existing methods, it was noted that the Evans and Roxborough methods produced R2 values of 0.48 and 0.53, respectively, which are notably lower than those of the new method. Lastly, the parametric analysis revealed that the cutting force is primarily affected by the depth, width, and rake angle in that order.
also, it was mentioned in NewsRx-Computer News Today-01 Aug 2024
A Review: Applications of Fuzzy Theory in Rock Engineering
Abstract
One of the sub-disciplines of geo-engineering is rock engineering, which studies the behavior of rocks against internal and external factors. Fuzzy theory can be used to solve many geotechnical problems due to the uncertainty of geotechnical data and environmental characteristics. This research review aims to briefly examine the application of the fuzzy approach in the field of Rock engineering. The origin of the research in 1985 and the scope of its applications recorded in international journals were considered. The articles were reviewed based on approaches such as the year of publication, the author’s nationality, the field of application, and the credibility of the published journal. The applications of fuzzy theory have been studied in seven groups, such as mechanized excavation, underground structures design, rock slope stability, rock mass properties, rock mass engineering classification, and other secondary fields of classification, and the most used tools in each stage were introduced. The research results show an attitude toward applying fuzzy theory in rock mechanics and suggest potential directions for further work.
Investigate the potential of using fuzzy similarity in decision-making under uncertainty for mining projects
Abstract
Multi criteria decision-making methods are used in mining engineering, in which various aspects are involved, such as selecting mining methods, mineral processing sites, etc. Decisions in this field can be made using a variety of techniques. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method is one of the most widely used decision-making methods based on multi criteria to make a decision. As part of this research, an attempt was made to investigate how fuzzy measurements can be applied to mining projects to improve the TOPSIS methods’ efficiency. A full investigation of the mining method selection process, the waste dump site selection process at Gol-e-Ghar mine Area 3, the location of Bahabad Pelletizing plant, the appropriate site selection for crusher machine Sarcheshmeh copper mine, and loading-haulage equipment selection for Sungun copper mine has been carried out in order to achieve this goal. Accordingly, an area north of the pit was selected as the best location for the waste dump, open-pit mining was selected as the best mining method for the Gol-e-Gohar mine, Cite Number 2 was selected as the best location for the Bahabad Pelletizing Plant, the East side of the Sarcheshmeh copper mine is presented as the most suitable one, and shovel-truck-belt conveyor selected as the transportation method for Sungun copper mine. For mining projects, fuzzy similarity logic in the TOPSIS method provides both accurate and efficient results, as well as reducing the number of calculations. It also provides accurate results based on linguistic, numeric, and fuzzy values and determines whether all alternatives are feasible. Finally, it is shown that the TOPSIS based on fuzzy similarity for considering uncertainty in mining projects that are involved the decision-making process can be practical and useful.
Evaluation of the effect of injection pressure on Surface Settlement in Excavation with Earth Pressure Balanced Shield Machine
Abstract
- Summary Earth Pressure Balance Machines (EPB) were used to excavate the Tabriz metro line 2. A critical section of the tunnel Has modeled in this study. The model has been verified by the monitoring data using the installed instruments on site. In addition, some crucial operational parameters of the Earth Pressure Balance Tunnel Boring Machine (EPBM) have also been studied to determine their effect on ground deformation and subsidence during tunnel excavation.
- Introduction Tunneling in shallow urban areas and on soft ground is always associated with risks that can have unpleasant consequences if ignored. Tunnel excavation removes a mass of soil and rock, leading to significant changes in strength around them, and causing the Earth to move. The tunnel has been excavated in a shallow soil environment; these effects will transfer to the ground. An earth pressure balance shield (EPB) is one of the most suitable methods to control the pressure in the tunnel front, decreasing the surface subsidence by controlling this pressure.
- Methodology and Approaches The study applied three-dimensional (3D) numerical modeling to study the effects of TBM-EPB operating parameters on the deformation and subsidence of soft soils using FlAC3D software.
- Results and Conclusions According to the obtained numerical results, it seems that these slurry injection pressures did not have a significant effect on the improvement of stresses. The study investigated the influence of overburden pressure, adhesion, density, and diameter on injection pressure. The results indicate that decreasing or increasing the injection pressure in environments with different parameters has little effect on vertical displacement. To investigate how geomechanical factors of the environment influence deformation of the Earth’s surface, models were constructed by keeping all the parameters constant according to which, with increasing adhesion and internal friction angle, the rate of subsidence decreases. While increasing the specific gravity of the soil, the amount of vertical displacements increases.
MSc Thesis: Comparative study of the results of existing models and numerical modeling for the forces applied to conventional TBM cutting tools on soft grounds
Abstract
Over the years, and by increasing the demand for building mechanized tunnels, designing the Tunnel Boring Machines (TBM) become increasingly sensitive. Engineers and scientists are increasingly interested in optimizing the layout of cutterheads to reduce investment and maintenance expenses. One of the vital factors for this purpose is the geometry of the dragbit. In other words, by optimizing the geometry parameters of dragbits, it is possible to lower investment and maintenance costs. On the other hand, cutting force is declared the most important factor affected by dragbits geometry and rocks strengthen parameters. The first step of this study is to review the current methods used for estimating the cutting force. Secondly, numerical models were made to investigate the effect of each parameter on the cutting force. In the very next step, a comparison study was done between the results of the numerical models’ cutting force and the existing forces. Thus, Rake angle, Clearance angle, width, bezel width, attack angle, and tilt angle were studied in this thesis. The results show that the cutting force is reduced by increasing the rake, clearance, attack, and tilt angles; However, the cutting force registered a significant increase when the width and bezel width are increased. Compared to the previous models, it was observed that although these methods can take into account the changes in the width, rake, and clearance angles, they are not able to show the sensitivity of force to other geometric parameters. In addition, the supplementary research indicates that the Evans, Nishimatsu, and CEIT models provided similar results to the numerical models in rock. The tear and shear types showed noteworthy outcomes compared to the numerical model.
Class Project: FEM coding with Matlab (for Numerical Methods in Geomechanics course)
The final project of this course involved the coding of a tunnel and ground situation using FEM and the verification of the coding by modeling the tunnel using UDEC and FLAC 2D.
Tools: MATLAB, FLAC 2D, UDEC.
Class Project: NATM tunnels Final lining design (for Steel and Concrete Structures course)
The final project of this course involves designing an optimal ”steel reinforced concrete support system” for a tunnel using SAP2000 and verifying the design using FLAC 2D and PLAXIS 3D.
Tools: FLAC 2D, SAP2000, PLAXIS 3D.