• Artificial Neural Network Model for a Low Cost Failure Sensor: Performance Assessment in Pipeline Distribution

      Khan, Asar; Widdop, Peter D.; Day, Andrew J.; Wood, Alastair S.; Mounce, Steve R.; Machell, James (2006)
      This paper describes an automated event detection and location system for water distribution pipelines which is based upon low-cost sensor technology and signature analysis by an Artificial Neural Network (ANN). The development of a low cost failure sensor which measures the opacity or cloudiness of the local water flow has been designed, developed and validated, and an ANN based system is then described which uses time series data produced by sensors to construct an empirical model for time series prediction and classification of events. These two components have been installed, tested and verified in an experimental site in a UK water distribution system. Verification of the system has been achieved from a series of simulated burst trials which have provided real data sets. It is concluded that the system has potential in water distribution network management.
    • Low-cost failure sensor design and development for water pipeline distribution systems

      Khan, Asar; Widdop, Peter D.; Day, Andrew J.; Wood, Alastair S.; Mounce, Steve R.; Machell, James (2002)
    • Measured Water Temperature Characteristics in a Pipeline Distribution System

      Khan, Asar; Widdop, Peter D.; Day, Andrew J.; Wood, Alastair S.; Mounce, Steve R.; Machell, James (2006)
      This paper describes the design, development, deployment and performance assessment of a prototype system for monitoring the 'health' of a water distribution network based on the temperature distribution and time-dependent variations in temperature across the network. It has been found that the water temperature can reveal unusual events in a water distribution network, indicated by dynamic variations in spatial temperature differential. Based on this indication it is shown how patterns of changes in the water temperature can be analysed using AQUIS pipeline distribution software and used in conjunction with hydraulic (e.g. flow and pressure) sensors to indicate the state of ¿health¿ of the network during operation.
    • A neural network approach to burst detection

      Mounce, Steve R.; Day, Andrew J.; Wood, Alastair S.; Khan, Asar; Widdop, Peter D.; Machell, James (2002)
    • Performance assessment of leak detection failure sensors used in a water distribution system

      Khan, Asar; Widdop, Peter D.; Day, Andrew J.; Wood, Alastair S.; Mounce, Steve R.; Machell, James (2005)
    • Sensor-fusion of hydraulic data for burst detection and location in a treated water distribution system

      Mounce, Steve R.; Khan, Asar; Day, Andrew J.; Wood, Alastair S.; Widdop, Peter D.; Machell, James (2003)