Abstract:It was important to ensure the temperature control of medical equipment with the heat preservation function within an acceptable range of the setting value. The temperature monitoring was traditionally carried out by artificial judgment, which mainly depended on subjective experiences. Also, it was not easy to make an accurate decision in case of complex situations. In this paper, a PCA-based (Principal-Component-Analysis-Based) multivariate statistical model was proposed and applied for temperature monitoring of the medical equipment. In the new model, connections between the monitoring data of temperature sensors was constructed on the basis of PCA model so as to monitor the status of the temperature of medical equipment through use of corresponding statistical data. After application of the new model to analysis of the temperature of the blue light box, it demonstrated its effectiveness, quick responses and alert to the abnormal conditions, which could ensure the abnormalities are found and processed in the shortest time. In practice, the proposed model had strong practicality and could also be used in various medical equipment that needed to monitor the temperature data.
吴蕴蕴,郑彩仙. 基于主成分分析模型的医疗设备温度监测模型及其应用[J]. 中国医疗设备, 2015, 30(4): 15-17.
WU Yun-yun, ZHEN Cai-xian. APCA-Based Medical Equipment Temperature Monitoring Model and its Application. China Medical Devices, 2015, 30(4): 15-17.
Russell EL,Chiang LH,Braatz RD.Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis[J].Chemometr Intell Lab Syst,2000,51(1):81-93.
[6]
Bishop CM.Pattern recognition and machine learning[M].New York:Springer,2006.
[11]
Jackson JE.A user's guide to principal components[M].New York: John Wiley & Sons,Inc,1991.
Joe Qin S.Statistical process monitoring: basics and beyond[J].J Chemometr,2003,17(8-9):480-502.
[3]
张智荣.蓝光治疗新生儿黄疸的护理[J].临床医学,2011,31(4):124-125.
[8]
Qin SJ.Survey on data-driven industrial process monitoring and diagnosis[J].Amw Rev Control,2012,36(2):220-234.
[10]
Tipping ME,Bishop CM.Probabilistic principal component analysis[J].J R Stat Soc B,1999,61(3):611-622.
[2]
Click R,Dahl-Smith J,Fowler L,et al.An osteopathic approach to reduction of readmissions for neonatal jaundice[J].Osteopathic Family Physician,2013,5(1):17-23.
Tracy N,Young J,Mason R.Multivariate control charts for individual observations[J].J Qual Technot,1992,24(2):88-95.
[4]
何丽丽.蓝光治疗新生儿黄疸的护理体会[J].中外健康文摘,2014,(21):292.
[5]
Murphy KP.Machine learning: a probabilistic perspective[M].MIT Press,2012.
[9]
Ku W,Storer RH,Georgakis C.Disturbance detection and isolation by dynamic principal component analysis[J].Chemometr Intell Lab Syst,1995,30(1):179-196.