Abstract: Deciding the numerous parameters involved in
designing a competent artificial neural network is a complicated task.
The existence of several options for selecting an appropriate
architecture for neural network adds to this complexity, especially
when different applications of heterogeneous natures are concerned.
Two completely different applications in engineering and medical
science were selected in the present study including prediction of
workpiece's surface roughness in ultrasonic-vibration assisted turning
and papilloma viruses oncogenicity. Several neural network
architectures with different parameters were developed for each
application and the results were compared. It was illustrated in this
paper that some applications such as the first one mentioned above
are apt to be modeled by a single network with sufficient accuracy,
whereas others such as the second application can be best modeled
by different expert networks for different ranges of output.
Development of knowledge about the essentials of neural networks
for different applications is regarded as the cornerstone of
multidisciplinary network design programs to be developed as a
means of reducing inconsistencies and the burden of the user
intervention.
Abstract: Development of artificial neural network (ANN) for
prediction of aluminum workpieces' surface roughness in ultrasonicvibration
assisted turning (UAT) has been the subject of the present
study. Tool wear as the main cause of surface roughness was also
investigated. ANN was trained through experimental data obtained
on the basis of full factorial design of experiments. Various
influential machining parameters were taken into consideration. It
was illustrated that a multilayer perceptron neural network could
efficiently model the surface roughness as the response of the
network, with an error less than ten percent. The performance of the
trained network was verified by further experiments. The results of
UAT were compared with the results of conventional turning
experiments carried out with similar machining parameters except for
the vibration amplitude whence considerable reduction was observed
in the built-up edge and the surface roughness.
Abstract: Hexapod Machine Tool (HMT) is a parallel robot
mostly based on Stewart platform. Identification of kinematic
parameters of HMT is an important step of calibration procedure. In
this paper an algorithm is presented for identifying the kinematic
parameters of HMT using inverse kinematics error model. Based on
this algorithm, the calibration procedure is simulated. Measurement
configurations with maximum observability are decided as the first
step of this algorithm for a robust calibration. The errors occurring in
various configurations are illustrated graphically. It has been shown
that the boundaries of the workspace should be searched for the
maximum observability of errors. The importance of using
configurations with sufficient observability in calibrating hexapod
machine tools is verified by trial calibration with two different
groups of randomly selected configurations. One group is selected to
have sufficient observability and the other is in disregard of the
observability criterion. Simulation results confirm the validity of the
proposed identification algorithm.