Abstract: A study to estimate the size of the cabin and major
aircraft components as well as detect and avoid interference between
internally placed components and the external surface, during the
conceptual design synthesis and optimisation to explore the design
space of a BWB, was conducted. Sizing of components follows the
Bradley cabin sizing and rubber engine scaling procedures to size
the cabin and engine respectively. The interference detection and
avoidance algorithm relies on the ability of the Class Shape Transform
parameterisation technique to generate polynomial functions of the
surfaces of a BWB aircraft configuration from the sizes of the
cabin and internal objects using few variables. Interference detection
is essential in packaging of non-conventional configuration like
the BWB because of the non-uniform airfoil-shaped sections and
resultant varying internal space. The unique configuration increases
the need for a methodology to prevent objects from being placed in
locations that do not sufficiently enclose them within the geometry.
Abstract: The one-class support vector machine “support vector
data description” (SVDD) is an ideal approach for anomaly or outlier
detection. However, for the applicability of SVDD in real-world
applications, the ease of use is crucial. The results of SVDD are
massively determined by the choice of the regularisation parameter C
and the kernel parameter of the widely used RBF kernel. While for
two-class SVMs the parameters can be tuned using cross-validation
based on the confusion matrix, for a one-class SVM this is not
possible, because only true positives and false negatives can occur
during training. This paper proposes an approach to find the optimal
set of parameters for SVDD solely based on a training set from
one class and without any user parameterisation. Results on artificial
and real data sets are presented, underpinning the usefulness of the
approach.