M. Djukanovic et al., NEURAL-NET BASED COORDINATED STABILIZING CONTROL FOR THE EXCITER AND GOVERNOR LOOPS OF LOW HEAD HYDROPOWER PLANTS, IEEE transactions on energy conversion, 10(4), 1995, pp. 760-767
This paper presents a design technique of a new adaptive optimal contr
oller of the low head hydropower plant using artificial neural network
s (ANN). The adaptive controller is to operate in real time to improve
the generating unit transients through the exciter input, the guide v
ane position and the runner blade position. The new design procedure i
s based on self-organization and the predictive estimation capabilitie
s of neural-nets implemented through the cluster-wise segmented associ
ative memory scheme. The developed neural-net based controller (NNC) w
hose control signals are adjusted using the on-line measurements, can
offer better damping effects for generator oscillations over a wide ra
nge of operating conditions than conventional controllers. Digital sim
ulations of hydropower plant equipped with low head Kaplan turbine are
performed and the comparisons of conventional excitation-governor con
trol, state-space optimal control and neural-net based control are pre
sented. Results obtained on the non-linear mathematical model demonstr
ate that the effects of the NNC closely agree with those obtained usin
g the state-space multivariable discrete-time optimal controllers.