scholarly journals Modeling Identification of the Nonlinear Robot Arm System Using MISO NARX Fuzzy Model and Genetic Algorithm

Robot Arms ◽  
10.5772/16422 ◽  
2011 ◽  
Author(s):  
Ho Pham Huy Anh ◽  
Kyoung Kwan ◽  
Nguyen Thanh
Keyword(s):  
Genetic Algorithm ◽  
Fuzzy Model ◽  
Robot Arm

scholarly journals Calibration of Kinematic Parameters of Robot Arm Using Laser Tracking System: Compensation for Non-Geometric Errors by Neural Networks and Selection of Optimal Measuring Points by Genetic Algorithm

2012 ◽  
Vol 6 (1) ◽  
pp. 29-37 ◽  
Author(s):  
Seiji Aoyagi ◽  
◽  
Masato Suzuki ◽  
Tomokazu Takahashi ◽  
Jun Fujioka ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Tracking System ◽  
Kinematic Model ◽  
Three Dimensional ◽  
Geometric Parameters ◽  
Geometric Errors ◽  
Robot Arm ◽  
Positioning Accuracy ◽  
Laser Tracking

Offline teaching based on high positioning accuracy of a robot arm is desired to take the place of manual teaching. In offline teaching, joint angles are calculated using a kinematic model of the robot arm. However, a nominal kinematic model does not consider the errors arising in manufacturing or assembly, not to mention the non-geometric errors arising in gear transmission, arm compliance, etc. Therefore, a method of precisely calibrating the parameters in a kinematic model is required. For this purpose, it is necessary to measure the three-dimensional (3-D) absolute position of the tip of a robot arm. In this paper, a laser tracking system is employed as the measurement apparatus. The geometric parameters in the robot kinematic model are calibrated by minimizing errors between the measured positions and the predicted ones based on the model. The residual errors caused by non-geometric parameters are further reduced by using neural networks, realizing high positioning accuracy of sub-millimeter order. To speed up the calibration process, a smaller number of measuring points is preferable. Optimal measuring points, which realize high positioning accuracy while remaining small in number, are selected using Genetic Algorithm (GA).

scholarly journals An improved Genetic Algorithm For Fuzzy Production PlanningProblems with Application

2015 ◽  
Vol 1 (3) ◽  
pp. 390
Author(s):  
Jalal Abdulkareem Sultan ◽  
Omar Ramzi Jasim ◽  
Sarmad Abdulkhaleq Salih
Keyword(s):  
Genetic Algorithm ◽  
Customer Service ◽  
Fundamental Problem ◽  
Demand Forecasting ◽  
Fuzzy Model ◽  
Main Idea ◽  
Production Schedule ◽  
Improved Genetic Algorithm ◽  
Customer Service Level ◽  
Master Production Schedule

Production Planning or Master Production Schedule (MPS) is a key interface between marketing and manufacturing, since it links customer service directly to efficient use of production resources. Mismanagement of the MPS is considered as one of fundamental problem in operation and it can potentially lead to poor customer satisfaction.  In this paper, an improved Genetic Algorithm (IGA) is used to solving fuzzy multi-objective master production schedule (FMOMPS). The main idea is to integrate GA with local search operator. The FMOMPS was applied in the Cotton and medical gauzes plant in Mosul city. The application involves determine the gross requirements by demand forecasting using artificial neural networks. The IGA proved its efficiency in solving MPS problems compared with the genetic algorithm for fuzzy and non-fuzzy model, as the results clearly showed the ability of IGA to determine intelligently how much, when, and where the additional capacities (overtimes) are required such that the inventory can be reduced without affecting customer service level.

Sign in / Sign up

Export Citation Format

Share Document