Neural Network for statistical process control of a multiple stream binomial process with an application to HVAC systems in passenger rail vehicles

A multiple stream binomial process (MSBP) is a process at a point in time that generates several output streams that can be modelled as binomial processes. A multilayer perceptron is embedded in a control charting scheme and is trained to classify whether each sample is drawn from the in-control process distri bution or not. The performance of the proposed scheme is evaluated through a wide Monte Carlo simulation and is compared with the Wludyka and Jacobs’s MSBP control charts in terms of out-of-control average run length. Finally, the practical applicability of the proposed approach is illustrated through real operational data from heating, ventilation and air conditioning (HVAC) systems installed on-board modern passenger trains