Abstract: In this paper, application of artificial neural networks
in typical disease diagnosis has been investigated. The real procedure
of medical diagnosis which usually is employed by physicians was
analyzed and converted to a machine implementable format. Then
after selecting some symptoms of eight different diseases, a data set
contains the information of a few hundreds cases was configured and
applied to a MLP neural network. The results of the experiments and
also the advantages of using a fuzzy approach were discussed as
well. Outcomes suggest the role of effective symptoms selection and
the advantages of data fuzzificaton on a neural networks-based
automatic medical diagnosis system.
Abstract: Power system stabilizers (PSS) must be capable of providing appropriate stabilization signals over a broad range of
operating conditions and disturbance. Traditional PSS rely on robust
linear design method in an attempt to cover a wider range of operating
condition. Expert or rule-based controllers have also been proposed.
Recently fuzzy logic (FL) as a novel robust control
design method has shown promising results. The emphasis in fuzzy
control design center is around uncertainties in the system parameters
& operating conditions. In this paper a novel Robust Fuzzy Logic Power
System Stabilizer (RFLPSS) design is proposed The RFLPSS
basically utilizes only one measurable Δω signal as input
(generator shaft speed).
The speed signal is discretized resulting in three inputs to the
RFLPSS. There are six rules for the fuzzification and two rules for
defuzzification. To provide robustness, additional signal namely,
speed are used as inputs to RFLPSS enabling appropriate gain
adjustments for the three RFLPSS inputs. Simulation studies
show the superior performance of the RFLPSS compared
with an optimally designed conventional PSS and discrete mode FLPSS.