INGENIEUR
system should be able to alert the person in charge to quickly mitigate the risk before exposure to the toxic chemical vapour . Similar to the case studies above , sensor locations can be optimised to detect the vapour concentration in the air effectively . In addition , an emergency response plan can be formulated .
Conclusion
ML models can be implemented for sensor optimisation and source localisation to achieve fast detection of toxic gases and localisation of dispersion sources , thereby protecting public health and the environment . CFD can be used to simulate gas dispersion patterns with varying source locations , wind speeds , and wind directions . Furthermore , CFD takes into account environmental factors , building design , as well as ventilation systems , which all have different degrees of effect on gas dispersion . The optimisation of sensor placement can also be achieved through the incorporation of algorithms with specific use constraints to optimise the coverage and the number of sensors . After sensor optimisation , the concentration data from the sensors along with the wind direction and wind speed can be collected as datasets to be inputted into the ANN models for training purposes . Once the ANN-based sensor optimisation method and the source localisation model are trained and tested for real-world scenarios , they can be used in various settings for fast detection of gas dispersion or leakages , protecting public health , safety , and the environment . The ML model is crucial to close the gap in current air pollution detection technologies to achieve fast detection of leak sources and implement effective emergency responses .
The optimisation of sensor placement for use in source localisation allows for the reduction of the number of sensors needed for a particular monitoring system while maintaining or even improving coverage and sensor performance . Effective deployment of sensors also allows for energy savings which may be significant when considering that the application of sensor optimisation methods extends outside the industrial sector and that sensors will play a vital part in the development of smart cities .
REFERENCE
Chourabi , H ., Nam , T ., Walker , S ., Gil-Garcia , J . R ., Mellouli , S ., Nahon , K ., Pardo , T . A ., & Scholl , H . J . ( 2012 , 4-7 Jan . 2012 ). Understanding Smart Cities : An Integrative Framework . 2012 45th Hawaii International Conference on System Sciences ,
Forti , V ., Baldé , C . P ., Kuehr , R ., & Bel , G . The Global E-waste Monitor 2020 . 120 .
Huang , X ., Zhang , J ., Sresakoolchai , J ., & Kaewunruen , S . ( 2021 ). Machine Learning Aided Design and Prediction of Environmentally Friendly Rubberised Concrete . Sustainability , 13 , 1691 .
https :// doi . org / 10.3390 / su13041691
Yu , H . L ., Chen , B . H ., Kim , K . S ., Siwayanan , P ., Choong , S . Y . T ., & Ban , Z . H . ( 2022 ). Source localization for illegal plastic burning in Malaysia via CFD-ANN approach . Digital Chemical Engineering , 3 , 100029 .
https :// doi . org / 10.1016 / j . dche . 2022.100029
32 VOL 93 JANUARY-MARCH 2023