METHOD FOR DETECTING A FAILURE IN A VEHICLE PNEUMATIC SYSTEM

Method (100) for detecting a failure in a pneumatic system (PNS) of a vehicle, the pneumatic system PNS comprising a supply pneumatic subsystem comprising supply lines (FSL, RSL, FVSL), a control pneumatic subsystem comprising control lines (CL), a delivery pneumatic subsystem comprising delivery lines (FDL, RDL), the vehicle comprising an electronic control unit (ECU), configured to implement a trained supply recurrent neural network (SRNN), a trained control recurrent neural network (CRNN), a trained delivery recurrent neural network (DRNN), and a trained main recurrent neural network (MRNN); the method (100) comprising collect (101), during a first period of time, and provide (102) the input parameters as input to the trained recurrent neural networks (SRNN, CRNN, DRNN) to get a output from recurrent neural networks; provide, (103) as input to the trained main recurrent neural network (MRNN), the input parameters, and the output parameters from recurrent neural networks (SRNN, CRNN, DRNN), to get a main output indicative of a pneumatic system health parameter (PHP) indicative of a presence and a severity, or of an absence, of a failure in one of the supply pneumatic subsystem, or the control pneumatic subsystem, or the delivery pneumatic subsystem of the pneumatic system (PNS).