Applying Neural Networks for Tire Pressure Monitoring Systems

A proof-of-concept indirect tire-pressure monitoring system is developed using artificial neural networks to identify the tire pressure of a vehicle tire.A quarter-car model was developed with MATLAB and Simulink to generate simulated accelerometer output data.Simulation data are used to train and evaluate a recurrent neural network with long short-term memory blocks(RNN-LSTM)and a convolutional neural network(CNN)developed in Python with Tensorflow.Bayesian Optimization via SigOpt was used to optimize training and model parameters.The predictive accuracy and training speed of the two models with various parameters are compared.Finally,future work and improvements are discussed.

Laboratory investigation of axisymmetric single vacuum well point

Vacuum well point is a new but faint soft ground treatment method. This work focuses on the consolidation behavior of a reconstituted soft clayey specimen under vacuum well point combined with surcharge loading. The laboratory test was conducted through a vacuum-surcharge consolidation apparatus, and the vacuum loading scheme was adopted for vacuum pressure application to investigate the vacuum effect on soil consolidation. In the testing process, some key parameters such as vacuum pressure, pore water pressure and settlement deformation were timely recorded. Furthermore, the water content, void ratio and permeability coefficient of samples collected after loading were measured to reflect the consolidation characteristics. By comparing with the membrane system and membraneless system, something different was found for the vacuum well point method. The results indicate that the consolidation behavior of an axisymmetric single vacuum well point is almost identical to the behavior of vacuum preloading combined with prefabricated vertical drain(PVD), except for the distribution of the vacuum pressure along the well drain due to the structure of the vacuum well point. And the vacuum well point method may be useful for the improvement of soft clayey deposit in a certain depth.

A Climatology of Heavy Rain and Major Flood Events in Victoria 1876-2019 and the Effect of the 1976 Climate Shift

An extensive search has been carried out to find all major flood and very heavy rainfall events in Victoria since 1876 when Southern Oscillation(SOI)data became available.The synoptic weather patterns were analysed and of the 319 events studied,121 events were found to be East Coast Lows(ECLs)and 82 were other types of low-pressure systems.Tropical influences also played a large role with 105 events being associated with tropical air advecting down to Victoria into weather systems.Examples are presented of all the major synoptic patterns identified.The SOI was found to be an important climate driver with positive SOIs being associated with many events over the 144 years studied.The 1976 Climate Shift and its influence on significant Victorian rainfall events is studied and negative SOI monthly values were shown to dominate following the Shift.However,one of the most active periods in 144 years of Victorian heavy rain occurred after the shift with a sustained period of positive SOI events from 2007 to 2014.Therefore,it is critical for forecasting future Victorian heavy rainfall is to understand if sequences of these positive SOI events continue like those preceding the Shift.Possible relationships between the Shift and Global Temperature rises are also explored.Upper wind data available from some of the heaviest rainfall events showed the presence of anticyclonic turning of the winds between 850hPa and 500hPa levels which has been found to be linked with extreme rainfall around the Globe.