Optimal control of non-linear systems through hybrid cell-mapping/artificial-neural-networks techniques

In this paper, a real-time optimal control technique for non-linear plants is proposed. The control system makes use of the cell-mapping (CM) techniques, widely used for the global analysis of highly non-linear systems. The CM framework is employed for designing approximate optimal controllers via a control variable discretization. Furthermore, CM-based designs can be improved by the use of supervised feedforward artificial neural networks (ANNs), which have proved to be universal and efficient tools for function approximation, providing also very fast responses. The quantitative nature of the approximate CM solutions fits very well with ANNs characteristics. Here, we propose several control architectures which combine, in a different manner, supervised neural networks and CM control algorithms. On the one hand, different CM control laws computed for various target objectives can be employed for training a neural network, explicitly including the target information in the input vectors. This way, tracking problems, in addition to regulation ones, can be addressed in a fast and unified manner, obtaining smooth, averaged and global feedback control laws. On the other hand, adjoining CM and ANNs are also combined into a hybrid architecture to address problems where accuracy and real-time response are critical. Finally, some optimal control problems are solved with the proposed CM, neural and hybrid techniques, illustrating their good performance.

Inhibition of nitro-oxidative stress attenuates pulmonary and systemic injury induced by high-tidal volume mechanical ventilation

Mechanisms contributing to pulmonary and systemic injury induced by high tidal volume (VT) mechanical ventilation are not well known. We tested the hypothesis that increased peroxynitrite formation is involved in organ injury and dysfunction induced by mechanical ventilation. Male Sprague-Dawley rats were subject to low- (VT, 9 mL/kg; positive end-expiratory pressure, 5 cmH2O) or high- (VT, 25 mL/kg; positive end-expiratory pressure, 0 cmH2O) VT mechanical ventilation for 120 min, and received 1 of 3 treatments: 3-aminobenzamide (3-AB, 10 mg/kg, intravenous, a poly adenosine diphosphate ribose polymerase [PARP] inhibitor), or the metalloporphyrin manganese(III) tetrakis(1-methyl-4-pyridyl)porphyrin (MnTMPyP, 5 mg/kg intravenous, a peroxynitrite scavenger), or no treatment (control group), 30 min before starting the mechanical ventilation protocol (n = 8 per group, 6 treatment groups). We measured mean arterial pressure, peak inspiratory airway pressure, blood chemistry, and gas exchange. Oxidation (fluorescence for oxidized dihydroethidium), protein nitration (immunofluorescence and Western blot for 3-nitrotyrosine), PARP protein (Western blot) and gene expression of the nitric oxide (NO) synthase (NOS) isoforms (quantitative real-time reverse transcription polymerase chain reaction) were measured in lung and vascular tissue. Lung injury was quantified by light microscopy. High-VT mechanical ventilation was associated with hypotension, increased peak inspiratory airway pressure, worsened oxygenation; oxidation and protein nitration in lung and aortic tissue; increased PARP protein in lung; up-regulation of NOS isoforms in lung tissue; signs of diffuse alveolar damage at histological examination. Treatment with 3AB or MnTMPyP attenuated the high-VT mechanical ventilation-induced changes in pulmonary and cardiovascular function; down-regulated the expression of NOS1, NOS2, and NOS3; decreased oxidation and nitration in lung and aortic tissue; and attenuated histological changes. Increased peroxynitrite formation is involved in mechanical ventilation-induced pulmonary and vascular dysfunction.