Improvement of robot accuracy by calibrating kinematic model using a laser tracking system-compensation of non-geometric errors using neural networks and selection of optimal measuring points using genetic algorithm-

2010 ◽  
Author(s):  
S Aoyagi ◽  
A Kohama ◽  
Y Nakata ◽  
Y Hayano ◽  
M Suzuki
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Tracking System ◽  
Kinematic Model ◽  
Geometric Errors ◽  
Laser Tracking ◽  
Robot Accuracy ◽  
System Compensation ◽  
Selection Of

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 Evolutionary Artificial Neural Networks as Tools for Predicting the Internal Structure of Microemulsions

2008 ◽  
Vol 11 (1) ◽  
pp. 67 ◽  
Author(s):  
M. Gašperlin ◽  
F. Podlogar ◽  
R. Šibanc
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Drug Delivery Systems ◽  
Drug Carrier ◽  
Computer Language ◽  
Development Cost ◽  
Scanning Calorimetry ◽  
Evolutionary Neural Networks ◽  
Further Development ◽  
Selection Of

PURPOSE. The purpose of this study was to predict microemulsion structures by creating two artificial evolutionary neural networks (ANN) combined with a genetic algorithm. The first ANN would be able to determine the type of microemulsion from the desired composition, and the second to determine the type of microemulsion directly from a differential scanning calorimetry (DSC) curve. METHODS. The algorithms and the structures for each ANN were constructed and programmed in C++ computer language. The ANNs had a feed forward structure with one hidden level and were trained using a genetic algorithm. DSC was used to determine the microemulsion type. RESULTS. The ANNs showed very encouraging accuracy in predicting the microemulsion type from its composition and also directly from the DSC curve. The percentage success, calculated over the tested data, was over 90%. This enabled us, with satisfactory accuracy, to construct several pseudoternary diagrams that could facilitate the selection of the microemulsion composition to obtain the optimal desired drug carrier. CONCLUSIONS. The ANN constructed here, enhanced with a genetic algorithm, is an effective tool for predicting the type of microemulsion. These findings provide the basis for reducing research time and development cost for characterizing microemulsion properties. Its application would stimulate the further development of such colloidal drug delivery systems, exploit their advantages and, to a certain extent, avoid their disadvantages.

scholarly journals Modeling of Duck Density and Complex Stocking Time in Rice-Duck Agroecosystems in Terms of Economic and Ecological Benefits

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Dahong Xiong ◽  
Kui Fang ◽  
Ying Luo ◽  
Xiaopeng Dai
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Quantitative Assessment ◽  
Intelligent Algorithm ◽  
Ecological Benefits ◽  
Hybrid Intelligent Algorithm ◽  
Numerical Examples ◽  
The Neural Networks ◽  
Fitting Ability ◽  
Selection Of

Rice-duck integrated farming is an effective step under today’s sustainable development background. To make better economic and ecological benefits, a rice-duck agroecosystem is established and kept, in which the paddy field, rice, and the duck mutually promote one another. But the duck density and complex stocking time must be rationally selected. Aiming to attain quantitative assessment and optimal selection of the duck density and complex stocking time in this kind of systems, a methodology based on proposed mathematical models in terms of comparative economic and ecological benefits is addressed. Then the models are solved by a hybrid intelligent algorithmNN-GAthat integrates the Neural Networks (NN) and Genetic Algorithm (GA), making use of the fitting ability in nonlinear fitness context of Neural Networks and the optimization ability of the Genetic Algorithm. Besides, numerical examples are demonstrated in order to test the proposed models. Results reveal that the methodology is reasonable and feasible.

Sign in / Sign up

Export Citation Format

Share Document