Structural deterioration of pipes is the continuing
reduction of load bearing capacity, which can be
characterized through structural defects. Structural deterioration
has been a major concern for asset managers
in maintaining the required performance of stormwater
drainage systems in Australia. Condition assessment
using closed circuit television (CCTV) inspection is often
carried out to assess the deteriorating condition of
individual pipes. In this study, two models were developed
using ordered probit and neural networks (NNs)
techniques for predicting the structural condition of individual
pipes. The predictive performances were compared
using CCTV data collected for a local government
authority in Melbourne, Australia. The significant input
factors to the outputs of both models were also identified.
The results showed that the NN model was more
suitable for modeling structural deterioration than the ordered
probit model. The hydraulic condition, pipe size,
and pipe location were found to be significant factors for
this case study.