Papers by yaser salehinia
Journal of Petroleum Science and Engineering, 2016
Accurate predictions of fluid properties, such as density, oil formation volume factor and bubble... more Accurate predictions of fluid properties, such as density, oil formation volume factor and bubble point pressure, are essentials for all reservoir engineering calculations. In this paper, an approach based on nonlinear system identification modeling; Nonlinear ARX (NARX) and Hammerstein-Wiener (HW) predictive model, is proposed for forecasting the pressure/volume/temperature (PVT) properties of crude oil systems. To this end, two datasets; one containing 168 PVT samples from different Iranian oil reservoirs and other a databank containing 755 data from various geographical locations, were employed to construct (i.e. train) and evaluate (i.e. test) the models. Simulation results demonstrate that the proposed NARX and HW models outperform previously employed methods including three types of artificial neural networks models (committee machine, multilayer perceptron and radial basis function), two types of ANFIS models (grid partition and fuzzy c-mean) and several empirical correlations with the smallest prediction error, and that they are reliable models for predicting the oil properties in reservoirs engineering among other soft computing approaches.
Solving Forward Kinematics Problem of Stewart Robot Using Soft Computing
in this paper, we consider the problem of efficient computation of the forward kinematics of a 6 ... more in this paper, we consider the problem of efficient computation of the forward kinematics of a 6 DOF robot manipulator built to use in rehabilitation purpose. Forward kinematics problem (FKP) of parallel robots is very difficult to solve in comparison to the serial manipulators. This problem is almost impossible to solve analytically. Numerical methods are one of the common solutions for this problem. But, accuracy, speed and convergence of these methods are fully dependent on the initial guess vector that is fed to the numerical algorithm. In this paper, soft computing approach like Artificial Neural Networks, fuzzy-neural network and nonlinear Auto Regressive eXogenous (NARX) identification method is used to solve the FKP of the Stewart robot. This problem is solved in the typical workspace of this robot. The results show the advantages of Nonlinear ARX identification method in providing very small modeling errors and provide excellent position and orientation angle estimation.
Procedia Engineering, 2012
Dynamic gait planning for humanoid robots encounters difficulties such as stability, speed, and s... more Dynamic gait planning for humanoid robots encounters difficulties such as stability, speed, and smoothness. In most of previous studies, joints' trajectories are calculated in 3D Cartesian space, then, introducing boundary conditions and using polynomials, the first and second derivatives of the motion are ensured to be continuous. Then, the stability of the motion is guaranteed using Zero Moment Point (ZMP) stability criterion. In this study, a trajectory planner is presented using the semi-ellipse equations of the motion; the continuity of the derivatives is preserved. Stabilization of motion is attained through using ZMP criterion and 3d inverted pendulum equations in three slope conditions. The effectiveness of the proposed approach is investigated using Webots software. Implementing proposed approach, smoothness, stability, and convenient speed (rather than 17 cm/s in flat condition) are achieved.
Journal of Mechanical Science and Technology, 2013
Biped locomotion has attracted much attention in recent years. The most successful implemented me... more Biped locomotion has attracted much attention in recent years. The most successful implemented methods in this area are based on two approaches, central pattern generator (CPG) and zero moment point (ZMP). Unfortunately, neither of these concepts can solely solve the movement challenge completely. In this study, we introduce a hybrid controller to combine the advantages of these methods. The proposed controller is based on two major approaches, CPG and ZMP. This hybrid controller is composed of a trajectory control system and a trajectory generator system. The trajectory control system applied to keep the robot stable uses ZMP as a real time control feedback. The trajectory generator system, which is composed of nonlinear oscillators, generates stable motions. The parameters of CPG are tuned by a new two-stage approach using differential evolution (DE) and bees algorithm (BA). Furthermore, performance of the proposed controller is verified using the robotic simulation software Webots.
The fuzzy expert system for hip motion enhancement in gait trainer robot
2014 Second RSI/ISM International Conference on Robotics and Mechatronics (ICRoM), 2014
In this paper, an efficient gait training robot with a fuzzy expert system is presented. Subject&... more In this paper, an efficient gait training robot with a fuzzy expert system is presented. Subject's leg joints are tracked in each gait cycle with a few markers using a 3D camera. The inputs to the fuzzy system include the 3D kinematics of initial trajectory and the hip joint spasm. The output of the fuzzy system is the trajectory of movements in two degrees of freedom for hip joint in sagittal and frontal planes. The commands used to design the expert system are obtained from professional therapists. They are customized for patients with different ranges of motion and joint spasms for hip movement in a gait cycle. They present enhanced and safe trajectory of the hip for patient's gait with different initial spasm and range of motion of hip joint.
Uploads
Papers by yaser salehinia