Abstract:
Intense competition and the requirement to continually drive down costs
within a mature mobile telephone infrastructure market calls for new and
innovative solutions to process improvement. One particular challenge is
to improve the quality and reliability of the diagnostic process for systems
testing of GSM and UMTS products. In this thesis, we concentrate on a
particularly important equipment type – the Base Transceiver Station
(BTS). The BTS manages the radio channels and transfers signalling
information to and from mobile stations (i.e. mobile phones). Most of the
diagnostic processes are manually operated and rely heavily on individual
operators and technicians' knowledge for their performance. Hence, there
is a high cost associated with trouble-shooting in terms of time and
manpower. To address this issue, we employ Bayesian networks (BNs) to
model the domain knowledge that comprises the operations of the System
Under Test (SUT), Automated Test Equipment (ATE) and the diagnostic
skill of experienced engineers, in an attempt to enhance the efficiency and
reliability of the diagnostic process. The proposed automated diagnostic
tool (known as Wisdom) consists of several modules. An intelligent user interface will provide possible solutions to test operators
/ technicians; to capture their responses, and to activate the automated
test programme. Server and client software architecture will be used to
integrate Wisdom with the ATE seamlessly and to maintain Wisdom as an
independent module. A local area network will provide the infrastructure
for managing and deploying the multimedia and text information in real
time. We describe how a diagnostic model can be developed and
implemented using a Bayesian network approach. We also describe how
the resulting process of diagnosis following failure, advice generation and
subsequent actions by the operator are handled interactively by the
prototype system.
