Abstract

In engineering problems, variables such as temperature, speed, location are noisy variables that are included in the system, and they become objective function variables. Because these variables are noisy, the objective functions are also noisy. Because there is more than one objective in multi-objective optimization problems, these variables may not affect each objective. Not all variables may be included for each objective function as variables. Therefore, in multi-objective optimization problems, it may be known to know both the noisy and noiseless states of one or more purposes. In this case, noise of the objective function may be extracted. In this case, the noise of other objective functions can be reduced by using the statistical properties of the known noise signal. The aim of this study is to reduce the noise in the objective functions as explained by using the statistical properties of the noise. For this purpose, two optimization algorithms and eight test problems will be used. In addition, statistical properties will be obtained from the data recorded with different window sizes.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call