Approach for Solving Nonlinear Equation Group Based on Adaptive Genetic Algorithm

2012 ◽  
Vol 532-533 ◽  
pp. 1636-1639
Author(s):  
Hong Lian Shen ◽  
Feng Lin Cheng ◽  
Huan Ru Ren
Keyword(s):  
Genetic Algorithm ◽  
Nonlinear Equation ◽  
Accurate Solution ◽  
Initial Solution ◽  
Function Optimization ◽  
Adaptive Genetic Algorithm ◽  
Time Efficiency ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Equation Group

A numeric method of solving nonlinear equation group is proposed. The problem of solving nonlinear equation group is equivalently changed to the problem of function optimization, and then a solution is obtained by adaptive genetic algorithm, considering it as the initial solution of Levenberg-Marquardt algorithm, a more accurate solution can be obtained, as a result, time efficiency is improved.

Three methods of training multi-layer perceptrons to model a robot sensor

Robotica ◽  
1995 ◽  
Vol 13 (5) ◽  
pp. 531-538 ◽  
Author(s):  
D. T. Pham ◽  
S. Sagiroglu
Keyword(s):  
Genetic Algorithm ◽  
Degrees Of Freedom ◽  
Natural Vibration ◽  
Inertial Sensor ◽  
Input Pattern ◽  
Training Methods ◽  
Six Degrees Of Freedom ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Working Principle

SummaryThis paper discusses three methods of training multi-layer perceptrons (MLPs) to model a six-degrees-of- freedom inertial sensor. Such a sensor is designed for use with a robot to determine the location of objects it has to pick up. The sensor operates by measuring parameters related to the inertia of an object and computing its location from those parameters. MLP models are employed for part of the computation. They are trained to output the orientation of the object in response to an input pattern that includes the period of natural vibration of the sensor on which the object rests. After reviewing the working principle of the sensor, the paper describes the three MLP training methods (backpropagation, optimisation using the Levenberg-Marquardt algorithm, evolution based on the genetic algorithm) and presents the experimental results obtained.

An Improved Fuzzy Adaptive Genetic Algorithm for Function Optimization

2011 ◽  
Vol 403-408 ◽  
pp. 2598-2601
Author(s):  
Lan Yao ◽  
Yu Lian Jiang ◽  
Jian Xiao
Keyword(s):  
Genetic Algorithm ◽  
Population Diversity ◽  
Function Optimization ◽  
Adaptive Genetic Algorithm ◽  
Adaptive Selection ◽  
Mutation Probability ◽  
Individual Fitness ◽  
Fitness Value ◽  
Crossover Probability ◽  
Fuzzy Adaptive

The critical operators for genetic algorithms to avoid premature and improve globe convergence is the adaptive selection of crossover probability and mutation probability. This paper proposed an improved fuzzy adaptive genetic algorithm in which the variance of population and individual fitness value are used to measure the overall population diversity and individual difference, meanwhile, both of them are applied to design fuzzy reference system for adaptively estimation of crossover probability and mutation probability. Simulation results of function optimization show that the new algorithm can converge faster and is more effective at avoiding premature convergence in comparison with standard genetic algorithm.

Sign in / Sign up

Export Citation Format

Share Document