Date: Thursday 11th May 2017 (10:30 – 16:30),
Location: Edgbaston Cricket Ground, Birmingham, B5 7QU
Register your interest here
Buried utility networks (such as water mains, gas pipes, electricity cables and sewer pipes) form essential elements of cities and modern civilisations, and play a significant role in the quality of life of citizens, growth of the economy, and health and well-being of society. A greater understanding of their behaviour in their particularly complex context and being able to more accurately predict the residual life of these utility assets would enable designers, asset managers and decision makers to plan their resources more efficiently and operate more proactively in their maintenance and management, resulting in multiple economic, social and environmental benefits. However, the complexity of the streetworks environment and numerous (inter)dependencies – influenced by physical factors (such as pipe types, strength, diameter, and burial depth; ground type and condition), social factors (such as land use change, myriad people and vehicle movements at the surface and traffic loading) and environmental factors (temperature, weather, and accommodating street trees) – affect their performance. The development of an advanced methodology to predict the remaining safe life of assets would help to eliminate scenarios where, for example, a pipeline collapses unexpectedly or is replaced unnecessarily on the basis of age rather than functional competence.
This workshop aims to create a unique opportunity to discuss and explore ideas from those in industry and academia interested in addressing the above issues in relation to the rapidly-changing expectations and ambitions of the 21 st century city. The workshop will use the opportunity to investigate and discuss other common difficulties in modelling and predicting the behaviour of buried utility networks raised by the workshop participants. In addition, the workshop will focus on exploring potential methodologies and opportunities to develop advanced models to understand deterioration and predict incipient failure of buried utilities using machine learning techniques and artificial intelligence, identifying constraints, key parameters, modelling space and industrial needs.