Loading...
Search for:
khodaygan--saeed
0.007 seconds
Total 31 records
A Path Planning Method Based on Basic RRT* Algorithm and Cagd-Based Curves Ffor Non-Holonomic Wheeled Mobile Robots
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
Throughout recent decades, one of the most important and challenging problems in robotics has been robot's path planning. Path planning means a robot must find its way from start to the goal point and track it without any collision to the obstacles. For this aim during the recent decades a wide variety of algorithms such as A*, Dijkstra and … have been proposed that some of which generate an optimal path as their output while others tend to create only a path regardless of its optimality. One of the most practical path planning methods is RRT algorithm which is executable in real-world applications, and by generating some nodes randomly then creating a tree-based graph, thereby outputting a...
Robust Orientation Estimation Using Imu and Online Machine Learning Based Calibration in the Presence of Distortions
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
In this project an optimized and robust orientation estimation method using IMU and magnetic sensors is presented. Magnetic distortion effects in orientation estimation is also one of the main purposes. Proposed sensor fusion algorithm is based on a complementary filter which provides a quaternion estimation as the algebraic solution of a system from inertial/magnetic observations. To develop the basic sensor fusion algorithm some procedures including a simple calculation to deal better with non-gravitational accelerations, decrease the effect of magnetometer in the presence of distortions and online gyroscope bias estimation is added. Also, a method for classification the different types of...
Optimal Process Planning for Automated Robotic Assembly of Mechanical Assembles based on Reinforcement Learning Method
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
Nowadays, the assembly process is planned by an expert and requires knowledge and it is time-consuming. The flexibility and optimality of the assembly plan depend on the knowledge and creativity of the expert, and therefore expertise is an important parameter in developing the assembly plan. Therefore, the use of intelligent methods to plan the assembly process has been considered by many researchers. . The reinforcing learning approach has the potential to solve complex problems due to the use of experience gained from interacting with the environment and Has been successfully implemented in controlling many robotic tasks. However, due to the inherent complexity of the assembly, as well as...
Design and Optimization of Gears Using Lattice Structure for Additive Manufacturing
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
Gears are a major component of many transmission systems. nowadays, improving the operating conditions and reducing the weight of the gears is one of the most needed issues in the industry. This dissertation aims to find the optimal structure of gear under different load cases and reduce its weight optimally. In this regard, topology optimization is used to develop the gear structure.In this research, two areas of bio-inspired design and additive manufacturing are used to achieve goals. These two areas can make good use of each other's potentials and achieve results that were not previously possible with traditional methods of design and manufacturing. First, an introduction and history of...
Experimental Study and Optimization of Laser Assisted Machining of Particle Reinforced Aluminum Matrix Composite
, M.Sc. Thesis Sharif University of Technology ; Movahhedy, Mohammad Reza (Supervisor) ; Khodaygan, Saeed (Co-Supervisor)
Abstract
In this thesis, the process of laser assisted machining (LAM) of metal matrix composites (MMC) is experimentally studied. The effects of process parameters (cutting speed, feed rate and depth of cut), laser parameters (laser power, laser frequency and laser beam angle), and the percentage of reinforcing particles on the tool wear and the surface roughness are investigated. Furthermore, the effects of these parameters on the built-up edge (BUE), chip shape, and workpiece temperature are explored.The experiments were performed using uncoated tungsten carbide and PCD tools under dry conditions. In order to analyze the sensitivity of the process parameters, the Plackett-Burman method was used...
Robotic Arm Manipulation Learning from Demonstration based on Reinforcement Learning
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
The field of learning from demonstration is the field in which researchers seek to create methods by which a robot can learn and reproduce a skill simply by using the demonstration of the skill. One of the main drawbacks of learning from demonstration methods is their inability to improve the learned skills. To answer this question, the reinforcement learning method can be used. The reinforcement learning approach has the potential to improve the initial skill due to the use of the experience of interacting with the environment. In this project, the dynamic movement primitives algorithm is considered as the learning from demonstration method. The research approach is that first, the dynamic...
Process Capability Analysis of Additive Manufacturing Process through Predictive Model of Dimensional and Geometric Errors based on Machine Learning
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
Additive manufacturing (AM)has gained extensive industrial and research attention in recent years. Reducing manufacturing waste, lead-time and costs and the ability to build surfaces and parts with complex shapes, assemblies all at once or parts with internal features are some benefits of AM. However, complex error generation mechanisms underlying AM digital physical chains are likely to result in geometrical inaccuracies of the final product, thus posing significant challenges to design and tolerancing for AM. Therefore, predictive modeling of shape deviations is critical for AM. With increasing volumes and varieties of data, machine learning has gained extraordinary popularity due to its...
A Framework for the Optimal and Robust Tolerance Design of Compressor Blades Under Functional Uncertainties”
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
Improving the performance of compressors plays a key role in saving energy in industries. The presence of aleatory and epistemic uncertainties, such as dimensional, geometrical and environmental uncertainties, causes the tolerances that are within the allowed ranges in normal assembly conditions to violate the assembly requirements in operational conditions and cause a drop in compressor efficiency. In order to reach the dimensional and geometrical tolerances of the components of a compressor, especially in the design of the rotor and stator blades, that guarantees the optimal and stable performance while not increasi the production costs, there is a need for an optimal and robust tolerance...
Automation of Vision Measurement Machine to Develop Parts Profile Dimensional Measurement Algorithm based on Machine Vision and Image Processing Technique Algorithms
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
Automated dimensional inspection is commonly expensive because of the requirement for high-precision measurement devices. To perform a precision measurement, the technician must be highly skilled and fully understands the operation of the equipment. Moreover, automation of the mentioned process to reduce dimensional measurement time is a complicated task due to restrictions of precise equipment such as CMM. With the expansion of the use of cameras in the industry, the measurement method with the help of machine vision systems is one of the cost-effective methods that can be achieved with the development of a suitable image processing algorithm to achieve acceptable accuracy compared to...
Topology optimization for manufacturability of Additive Manufacturing based on Deep Learning and Generative Adversarial Network
, M.Sc. Thesis Sharif University of Technology ; Khodaygan, Saeed (Supervisor)
Abstract
In recent years, Additive Manufacturing has been extensively used by various industries. These manufacturing processes produce components in a layer-by-layer manner; therefore, they do not impose any geometric constrains to engineers and provide designers with the freedom to design components. Nowadays, one of the primary goals of all industries is to utilize as few raw materials as possible; this way they can deal with the shortage of raw materials and improve their efficiency. Consequently, they implement topology optimization algorithms to design and produce their components. However, topology optimization algorithms result in complicated geometries that can only be fabricated by AM....
Modeling Geometrical Deviations and Tolerance Analysis Based on NURBS and Isogeometric Method
, Ph.D. Dissertation Sharif University of Technology ; Movahhedy, Mohammad Reza (Supervisor) ; Khodaygan, Saeed (Supervisor)
Abstract
Non-uniform rational B-spline (NURBS) curves and surfaces are one of the most powerful tools of computer-aided design, which are able to model both free-form and analytic shapes. In this dissertation, the idea of using NURBS curves as a tool for modeling geometrical deviations and tolerance analysis of mechanical assemblies is presented and evaluated. In the first step the effect of changing the defining variables of NURBS on shape of the curve is investigated. After that, by establishing a relationship between profile tolerance and random NURBS curves, two concepts of tolerance zone width and correlation function are introduced, and a method based on regression algorithms and covariance of...