A novel hybrid artificial intelligence technique for colpitts oscillator design
Loading...
Date
2014-02-01
Journal Title
Journal ISSN
Volume Title
Publisher
Springer US
Abstract
In the design of the common base Colpitts oscillator, the resistance values of Thevenin’s resistors
significantly influenced the transient time and steady state response of the resulting circuit. Various
traditional approaches such as intuitive reasoning, mathematical calculation, and simulation-based
techniques have been proposed in the literature for this purpose. Some of the aforementioned
techniques involve rigorous mathematics, intuition, and experimentation in determining
appropriate component values for optimal performance, stable steady state performance, and short
transient response time from the resulting oscillator. In this paper, a new method of designing
Colpitts oscillator using hybrid artificial intelligence comprising evolutionary-based Genetic
Algorithm (GA) and artificial neural network (ANN) has been proposed. GA has been used in
selecting various optimum resistance values of Thevenin’s resistors for maximizing long-term
stability of the output waveform thus ensuring stable steady response of the designed circuit. ANN
has been utilized in learning the nonlinear relationship between Thevenin’s resistors and transient
time response of the Colpitts oscillator. Upon ANN convergence, optimum resistance values of
obtained from GA process are fed into the trained ANN in predicting transient response time of
each circuit. Optimized values with the shortest transient response time are finally selected for the
Colpitts oscillator. The designed circuit successfully achieved optimization between its transient
time response and steady state response. Hence, successfully reducing computation associated with
existing traditional techniques in designing similar optimum Colpitts oscillator and achieving
stable steady state output. Furthermore, this work has also demonstrated that ANN is capable of
predicting the transient time of circuit with reasonable accuracy.
Description
Keywords
Artificial neural network (ANN), Colpitts oscillator, Genetic Algorithm (GA), Transient response time
Citation
Amsa, M. G. B. A., Aibinu, A. M., & Salami, M. J. E. (2014). A novel hybrid artificial intelligence technique for colpitts oscillator design. Journal of Control, Automation and Electrical Systems, 25(1), 10-21.