A Feedback Scheme for Improving Dynamic Response of Neuro-Controllers
1993pp. 84–88
Abstract
A neural network controller designed solely to realize maximum acceptable steady state error may have unsatisfactory transient response such as excessive overshoot and large rise time. Conversely, a controller designed to realize very good transient response may have unacceptable steady state characteristic. In this paper we investigate the effectiveness of adding velocity reference feedback for simultaneously improving the transient and steady state response of a neural network controller. Using the direct control scheme on the nonlinear dynamics of an underwater vehicle, we show that specific improvements in overshoot, rise time and settling time could be achieved with this method. The control scheme and results are discussed in detail.
Related Papers
- → Optimal PID tuning for controlling the temperature of electric furnace by genetic algorithm(2019)86 cited
- → Analisa Perbandingan Pengendali PID pada Motor DC Menggunakan Metode Ziegler-Nichols dan Trial and Error(2023)3 cited
- → Modeling and Optimal Classical Control of Blending Tank Level System in Cement Plant(2021)1 cited
- → Analisa Perbandingan Kontroler PID Terhadap Motor BLDC Menggunakan Penalaran Cohen-Coon dan Trial & Error(2023)