Geoscience Reference
In-Depth Information
Fig. 10.4 The ESAILS
model
i¼1
w
j
¼ f
a1
u
i
.
f
a0
u
i
Li ¼
X
/
is compared with its ultimate values L
i,min
and L
i,max
At the
rst stage, these
values are chosen arbitrarily, but then they change till reaching a maximum
accurate recognition of the hypotheses H
0
and H
1
. We have L
i,min
→
L*
i,min
and
L
i,max
→
L
i,max
. The values L*
i,min
and L
i,max
are memorized in ED.
After the learning procedure, the functioning of the expert system is limited only
by the volume of measurements
fixed by the operator, proceeding from statistical
reliability and the real-time regime. The operator has two possibilities to regulate
this regime: establishing the volume of the series {
i
j
}or
n
fixing the time of their
accumulation. Usually, the latter characteristic that is equal to 1 s is chosen.
Fig.
10.4
explains this procedure. The operator is combined with the ESAILS units
through the man-machine interface IIC, which provides the selective control of
operations in all units.
A knowledge of spectrums allows the recognition of two alternative hypotheses:
H
0
(liquid solution is normal) and H
1
(liquid solution is defective). The CS algo-
rithms have more sweeping functions allowing the more detailed diagnostics of
liquid solutions. These algorithms are based on cluster analysis and recognition
of spectral images. Recognition of liquid solution structure or receive of content of
chemical elements is possible after creation of spectral etalons in the ED. This stage
can be realized in the Earth
s conditions and on orbital space station taking into
consideration knowledge about weightlessness effects on liquid solution.
'
10.4.3 Conclusion
The discussion above showed that the ESAILS technology version can carry out the
task of liquid solution diagnostics in conditions where the use of chemical analysis
is not feasible. Such situation occurs both on Earth and in the space. This version is
Search WWH ::
Custom Search