We consider the problem of supervised learning of a multi-model based controller for non-linear systems. Selected multiple linear controllers are used for different operating points and combined with a local weighting scheme, whose weights are predicted by a deep neural network trained online. The network uses process and model outputs to drive the controller towards a suitable mixture of operating points.The proposed approach, which combines machine learning and classical control of linear processes, consists in the design of a controller for a waste heat recovery system (WHRS) mounted on a Heavy-Duty (HD) truck engine to decrease fuel consumption and meet the future pollutant emissions standard.The proposed control scheme, which can be applied to any nonlinear system with an existing linear controller bank, is successfully evaluated on an Organic Rankine Cycle (ORC) process simulator and compared to a standard linear controller and to several strong multi-model baselines without learning.

Biosecurity in poultry farms represents the first line of defense against the entry and spread of pathogens that may have animal health, food safety, and economic consequences. The aim of this study was to assess biosecurity compliance in poultry farms located in a densely populated poultry area in North East Italy. A total of 259 poultry farms (i.e., broilers, turkeys, and layers) were surveyed between 2018 and 2019 using standardized checklists, and differences in biosecurity compliance between the poultry sectors and years (only for turkey farms) were tested for significance. Among the three sectors, turkey farms showed the highest compliance. Farm hygiene, infrastructure condition, cleaning and disinfection tools, and procedures were the biosecurity measures most complied with. Some deficiencies were observed in the cleanliness of the farm hygiene lock in broiler farms, as well as the presence of the house hygiene lock in broiler and layer farms and an adequate coverage of built-up litter in turkey and broiler farms. In conclusion, this study highlighted a generally high level of biosecurity in the visited poultry farms (probably due to the stringent national regulation and the integration of the poultry industry) and identified some measures that still need to be improved.

No abstract

No abstract

No abstract