Turbopump condition monitoring is a significant approach to ensure the safety of liquid rocket engine （LRE）.Because of lack of fault samples,a monitoring system cannot be trained on all possible condition patterns.T...Turbopump condition monitoring is a significant approach to ensure the safety of liquid rocket engine （LRE）.Because of lack of fault samples,a monitoring system cannot be trained on all possible condition patterns.Thus it is important to differentiate abnormal or unknown patterns from normal pattern with novelty detection methods.One-class support vector machine （OCSVM） that has been commonly used for novelty detection cannot deal well with large scale samples.In order to model the normal pattern of the turbopump with OCSVM and so as to monitor the condition of the turbopump,a monitoring method that integrates OCSVM with incremental clustering is presented.In this method,the incremental clustering is used for sample reduction by extracting representative vectors from a large training set.The representative vectors are supposed to distribute uniformly in the object region and fulfill the region.And training OCSVM on these representative vectors yields a novelty detector.By applying this method to the analysis of the turbopump＇s historical test data,it shows that the incremental clustering algorithm can extract 91 representative points from more than 36 000 training vectors,and the OCSVM detector trained on these 91 representative points can recognize spikes in vibration signals caused by different abnormal events such as vane shedding,rub-impact and sensor faults.This monitoring method does not need fault samples during training as classical recognition methods.The method resolves the learning problem of large samples and is an alternative method for condition monitoring of the LRE turbopump.展开更多
背景日常活动量减少和运动功能受限是心力衰竭患者的特征性表现之一,体位/体动信息与心衰患者疾病严重程度和预后密切相关。通过可穿戴生理监测系统量化体位/体动信息或可作为一种潜在的心衰病情严重程度定量评价手段,其与纽约心脏病协...背景日常活动量减少和运动功能受限是心力衰竭患者的特征性表现之一,体位/体动信息与心衰患者疾病严重程度和预后密切相关。通过可穿戴生理监测系统量化体位/体动信息或可作为一种潜在的心衰病情严重程度定量评价手段,其与纽约心脏病协会(New York Heart Association,NYHA)心功能分级的关系需进一步研究。目的探讨心衰患者体位/体动信息定量分析结果与NYHA分级的相关性。方法纳入2021年5月—2022年11月在四川大学华西医院心内科住院的心衰患者,通过可穿戴生理监测系统采集患者入院当天和出院前1 d各24 h的连续生理监测数据,同步收集临床数据。通过对可穿戴生理监测系统内的三轴加速传感器信息进行处理分析,计算卧床时间、活动时间、步数、睡眠翻身次数4个体位/体动指标。基于患者入院时NYHA分级、入院和出院情况、出院时NYHA分级改善与否进行分组,分析体位/体动指标与NYHA分级的关联性。结果纳入心衰患者69例,平均年龄(60.90±14.24)岁,其中男性40例,NYHAⅡ、Ⅲ、Ⅳ级的患者分别有9例、24例、36例。随着NYHA分级的升高,心衰患者全天的卧床时间占比逐渐增多,而全天的活动时间占比、平均每小时步数逐渐降低,以上3个指标在NYHAⅡ、Ⅲ、Ⅳ级间均有统计学差异(P均<0.05);其中卧床时间占比(r_(s)=0.319,P=0.008)与NYHA分级呈正相关,活动时间占比(r_(s)=-0.312,P=0.009)、平均每小时步数(r_(s)=-0.309,P=0.010)与NYHA分级存在负相关。出院时的卧床时间占比显著低于入院时(96.25%vs 97.63%,P=0.026);出院时的活动时间占比显著高于入院时(3.32%vs 1.78%,P<0.001);出院时的平均每小时步数显著高于入院时(97.17步/h vs 35.58步/h,P<0.001);其中出院时NYHA改善组患者的体位/体动指标变化趋势同上,未改善组仅出院时的平均每小时步数显著高于入院时,NYHA改善组的出入院平均每小时步数变化值显著高于未改善组(71.21步/h vs 21.31步/h,P=0.003)。结论可穿戴生理监测系统能够对心衰患者的体位/体动信息进行客观长程的监测,心衰患者的卧床时间与NYHA分级呈正相关关系;活动时间、步数与NYHA分级呈负相关关系,这些体位/体动指标或可作为心衰患者疾病严重程度分级和状态监测评估的有用指标,未来可进一步延伸到对患者的居家和长程监测。展开更多
基金supported by National Natural Science Foundation of China (Grant No. 50675219)Hu’nan Provincial Science Committee Excellent Youth Foundation of China (Grant No. 08JJ1008)
文摘Turbopump condition monitoring is a significant approach to ensure the safety of liquid rocket engine （LRE）.Because of lack of fault samples,a monitoring system cannot be trained on all possible condition patterns.Thus it is important to differentiate abnormal or unknown patterns from normal pattern with novelty detection methods.One-class support vector machine （OCSVM） that has been commonly used for novelty detection cannot deal well with large scale samples.In order to model the normal pattern of the turbopump with OCSVM and so as to monitor the condition of the turbopump,a monitoring method that integrates OCSVM with incremental clustering is presented.In this method,the incremental clustering is used for sample reduction by extracting representative vectors from a large training set.The representative vectors are supposed to distribute uniformly in the object region and fulfill the region.And training OCSVM on these representative vectors yields a novelty detector.By applying this method to the analysis of the turbopump＇s historical test data,it shows that the incremental clustering algorithm can extract 91 representative points from more than 36 000 training vectors,and the OCSVM detector trained on these 91 representative points can recognize spikes in vibration signals caused by different abnormal events such as vane shedding,rub-impact and sensor faults.This monitoring method does not need fault samples during training as classical recognition methods.The method resolves the learning problem of large samples and is an alternative method for condition monitoring of the LRE turbopump.
文摘背景日常活动量减少和运动功能受限是心力衰竭患者的特征性表现之一,体位/体动信息与心衰患者疾病严重程度和预后密切相关。通过可穿戴生理监测系统量化体位/体动信息或可作为一种潜在的心衰病情严重程度定量评价手段,其与纽约心脏病协会(New York Heart Association,NYHA)心功能分级的关系需进一步研究。目的探讨心衰患者体位/体动信息定量分析结果与NYHA分级的相关性。方法纳入2021年5月—2022年11月在四川大学华西医院心内科住院的心衰患者,通过可穿戴生理监测系统采集患者入院当天和出院前1 d各24 h的连续生理监测数据,同步收集临床数据。通过对可穿戴生理监测系统内的三轴加速传感器信息进行处理分析,计算卧床时间、活动时间、步数、睡眠翻身次数4个体位/体动指标。基于患者入院时NYHA分级、入院和出院情况、出院时NYHA分级改善与否进行分组,分析体位/体动指标与NYHA分级的关联性。结果纳入心衰患者69例,平均年龄(60.90±14.24)岁,其中男性40例,NYHAⅡ、Ⅲ、Ⅳ级的患者分别有9例、24例、36例。随着NYHA分级的升高,心衰患者全天的卧床时间占比逐渐增多,而全天的活动时间占比、平均每小时步数逐渐降低,以上3个指标在NYHAⅡ、Ⅲ、Ⅳ级间均有统计学差异(P均<0.05);其中卧床时间占比(r_(s)=0.319,P=0.008)与NYHA分级呈正相关,活动时间占比(r_(s)=-0.312,P=0.009)、平均每小时步数(r_(s)=-0.309,P=0.010)与NYHA分级存在负相关。出院时的卧床时间占比显著低于入院时(96.25%vs 97.63%,P=0.026);出院时的活动时间占比显著高于入院时(3.32%vs 1.78%,P<0.001);出院时的平均每小时步数显著高于入院时(97.17步/h vs 35.58步/h,P<0.001);其中出院时NYHA改善组患者的体位/体动指标变化趋势同上,未改善组仅出院时的平均每小时步数显著高于入院时,NYHA改善组的出入院平均每小时步数变化值显著高于未改善组(71.21步/h vs 21.31步/h,P=0.003)。结论可穿戴生理监测系统能够对心衰患者的体位/体动信息进行客观长程的监测,心衰患者的卧床时间与NYHA分级呈正相关关系;活动时间、步数与NYHA分级呈负相关关系,这些体位/体动指标或可作为心衰患者疾病严重程度分级和状态监测评估的有用指标,未来可进一步延伸到对患者的居家和长程监测。
