RESUMEN
In the paper the usability of the Multiway PCA (MPCA) method for early detection of leakages in the pipeline system of a steam boiler in a thermal-electrical power plant is presented. A long segment of measurements of selected process variables was divided into a series of "batches" (representing daily recordings of normal behavior of the plant) and used to create the MPCA model of a "healthy" system in a reduced space of three principal components (PC). The periodically updated MPCA model was used to establish the confidence ellipsoid for the "healthy" system in the PC coordinates. [d=replaced]The staff's decision of the probable leak detection is supported by comparison of the current location of the operating point (on the "fault trajectory") with the boundaries of the confidence ellipsoid.The location of the process operating point created the "fault trajectory," which (if located outside the confidence ellipsoid) supported the decision of probable leak detection. It must be emphasized that due to daily and seasonal changes of heat/electricity demands, the process variables have substantially greater variability than in the examples of batch processes studied in literature. Despite those real challenges for the MPCA method, numerical examples confirmed that the presented approach was able to foresee the leaks earlier than the operator, typically 3-5 days before the boiler shutdown. The presented methodology may be useful in implementation of an on-line system, developed to improve safety and maintenance of boilers in a thermal-electrical power plant.
RESUMEN
BACKGROUND: A persistent progress in perinatal care and a large increase in infants' survival rate have been observed recently. As a result, the number of neonates requiring ophthalmologic examinations due to retinopathy of prematurity (ROP) increased as well. METHOD: A retrospective survey including 206 neonates with mean birth weight 1342 g and mean gestational age 30 weeks. MATERIAL: Three groups: 1) without ROP--165 infants (80.1%); 2) with ROP not requiring treatment--13 infants (6.3%); 3) with prethreshold and threshold ROP requiring cryotherapy--28 infants (13.6%) were analysed. RESULTS: Threshold ROP was not observed in infants with gestational age > 32 weeks and/or birth weight > 1500 g. Cryotherapy was applied between the 6th and 18th weeks of life (Mo: 12). The procedure was applied at postmenstrual age between the 34th and 45th weeks of life (Mo: 38). The correlation of ROP with the following factors was observed: length of mechanical ventilation (Me in the studied groups: 6; 22; 33 days respectively; p < 0.01), length of oxygen therapy (Me: 27; 58; 70 days; p < 0.01), number of blood transfusions in first month of life (Me: 2; 4; 4; p < 0.01), minimum pO2 (average: 37.2; 30.2; 29.2 mmHg p < 0.01), pO2 oscillation (measured as SD) (Me: 10.25; 13.2; 15.4 mmHg p < 0.016) and maximal pCO2 (average: 52.5; 56.8; 66.5 p < 0.01) between the 2nd and 4th weeks of life. CONCLUSION: Monitoring of pO2 and pCO2 in infants in the 1st month of life reduce the risk of ROP development. Infants born before the 32nd week of gestational age belong to high risk group and require very systematic ophthalmologic examination. The current prophylactic examination schedule for ROP for more mature infants may be changed.