TIS condition monitoring using ANN integration: an overview

Transportation Infrastructures Systems (TIS) are expected to provide reliable services to last for long periods of time. This period could further be tested due to dramatic environmental changes, improved technologies and extreme asset usage. Accordingly, the condition monitoring of these assets is pivotal to ensure their prolonged life. Although there are many tools available for the purpose of the condition monitoring of Transportation Infrastructure Systems, Artificial Neural Networks (ANNs) are the most methodical of these instruments. Conventionally, although not a new concept, ANNs epitomize the inclusive interconnection of the systems jointly with the numeric weighting that can be tweaked based on engineering practice, system inputs, processing and outputs. Moreover, the real advantage of ANNs is their capability to solve complex system problems such as ones, which are found within the TIS. Likewise, ANNs for TIS need to incorporate specific system engineering techniques such as damage monitoring techniques that will be durable for future years and would guide the maintenance of TIS so that they could operate at acceptable levels. Aptly, this paper will review the concept of ANNs and its core functions for the optimization (to manage the asset in such a way that the condition does not fall below an acceptable minimum condition) of Transportation Infrastructure Systems, in particular, the maintenance processes. In doing so, a specific and factual example of performance and condition measurement for roads will be also instigated.