System identification and fault reconstruction in solar plants via extended Kalman filter-based training of recurrent neural networks.

This article proposes using the extended Kalman filter (EKF) for recurrent neural network (RNN) training and fault estimation within a parabolic-trough solar plant. The initial step involves employing an RNN to model the system. Given the challenge of fault discernibility in the collectors, parallel EKFs are employed to reconstruct the parameters of the faults.

Stockout risk analysis and minimization applied to hospital pharmacy management.

Objective: To determine how many dispensary drugs should be in the safety stock in a tertiary hospital in accordance with the risk level and the number of days that the hospital is able to withstand a stockout.

Methods: We statistically analysed the infliximab order recorded over a period of 120 days. This drug is relevant for this study as it is costly and is immediately supplied to the clinic.