由于电离层电子密度随时间变化,且空间分布不均匀,对不同频段的无线电波产生延缓和折射,因此电离层电子密度变化是影响短波通信、卫星通信、全球导航卫星系统和其他空间通信质量的一个主要因素,本文对全球电离层电子密度(Number of elec...由于电离层电子密度随时间变化,且空间分布不均匀,对不同频段的无线电波产生延缓和折射,因此电离层电子密度变化是影响短波通信、卫星通信、全球导航卫星系统和其他空间通信质量的一个主要因素,本文对全球电离层电子密度(Number of electron,Ne)的预测工作对短波通信设备三维射线实时追踪定位提供必要条件。本文采用国际电离层参考模型提供的2016年电离层Ne数据,根据数据的三维空间时间序列特征,搭建了自编码器和卷积长短期记忆(Convolutional Long Short-Term Memory Network,Conv LSTM)网络组成的网络结构,在不引入地球自转周期之外任何先验知识的条件下,对Ne数据进行深度学习并实现预测,首先通过实验对比了SGD、Adagrad、Adadelta、Adam、Adamax和Nadam六种优化算法的性能,又对比了三种预测策略的均方根误差(Root Mean Square Error, RMSE),1h-to-1h预测策略的全球平均RMSE为1.0 NEU(最大值的0.4%),1h-to-24h和24h-to-24h预测策略的全球平均RMSE为6.3 NEU(2.6%)。由实验结果得出以下结论,一是Nadam优化算法更适合电离层Ne的深度学习,二是1h预测策略的性能与之前类似的电离层TEC预测工作(RMSE高于1.5 TECU,最大值的1%)相比有竞争力,但预测时间太短且对数据的实时性要求较高,三是两种24h预测策略虽能实现长期预测但性能不理想,要实现三维空间时间序列的长期高精度预测需要进一步改善神经网络、模型结构和预测策略。展开更多
As the demand for wind energy continues to grow at exponential rate, reducing operation and maintenance (O & M) costs and improving reliability have become top priorities in wind turbine maintenance strategies. Pr...As the demand for wind energy continues to grow at exponential rate, reducing operation and maintenance (O & M) costs and improving reliability have become top priorities in wind turbine maintenance strategies. Prediction of wind turbine failures before they reach a catastrophic stage is critical to reduce the O & M cost due to unnecessary scheduled maintenance. A SCADA-data based condition monitoring system, which takes advantage of data already collected at the wind turbine controller, is a cost-effective way to monitor wind turbines for early warning of failures. This article proposes a methodology of fault prediction and automatically generating warning and alarm for wind turbine main bearings based on stored SCADA data using Artificial Neural Network (ANN). The ANN model of turbine main bearing normal behavior is established and then the deviation between estimated and actual values of the parameter is calculated. Furthermore, a method has been developed to generate early warning and alarm and avoid false warnings and alarms based on the deviation. In this way, wind farm operators are able to have enough time to plan maintenance, and thus, unanticipated downtime can be avoided and O & M costs can be reduced.展开更多
The Hong Kong Observatory （HKO） has been developing a suite of nowcasting systems to support op- erations of the forecasting center and to provide a variety of nowcasting services for the general public and speciali...The Hong Kong Observatory （HKO） has been developing a suite of nowcasting systems to support op- erations of the forecasting center and to provide a variety of nowcasting services for the general public and specialized users. The core system is named the Short-range Warnings of Intense Rainstorm of Localized Systems （SWIRLS）, which is a radar-based nowcasting system mainly for the automatic tracking of the movement of radar echoes and the short-range Quantitative Precipitation Forecast （QPF）. The differential, integral （or variational）, and object-oriented tracking algorithms were developed and integrated into the nowcasting suite. In order to predict severe weather associated with intense thunderstorms, such as high gust, hail, and lightning, SWIRLS was enhanced to SWIRLS-II by introduction of a number of physical models, especially the icing physics as well as the thermodynamics of the atmosphere. SWIRLS-Ⅱ was further enhanced with non-hydrostatic, high resolution numerical models for extending the forecast range up to 6h ahead. Meanwhile, SWIRLS was also modified for providing nowcasting services for aviation community and specialized users. To take into account the rapid development of lightning events, ensemble nowcasting techniques such as time-lagged and weighted average ensemble approaches were also adopted in the nowcasting system. Apart from operational uses in Hong Kong, SWIRLS/SWIRLS-Ⅱ was also exported to other places to participate in several international events such as the WMO/WWRP Forecast Demon- stration Project （FDP） during the Beijing 2008 Olympics Games and the Shanghai Expo 2010. Meanwhile, SWIRLS has also been transferred to various regional meteorological organizations for establishing their nowcasting infrastructure. This paper summarizes the history and the technologies of SWIRLS/SWIRLS-Ⅱ and its variants and the associated nowcasting applications and services provided by the HKO since the mid 1990s.展开更多
AIM To explore the risk factors of developing chronic pan-creatitis （CP） in patients with acute pancreatitis （AP） and develop a prediction score for CP.METHODS Using the National Health Insurance Research Database...AIM To explore the risk factors of developing chronic pan-creatitis （CP） in patients with acute pancreatitis （AP） and develop a prediction score for CP.METHODS Using the National Health Insurance Research Database in Taiwan, we obtained large, population-based data of 5971 eligible patients diagnosed with AP from 2000 to 2013. After excluding patients with obstructive pancreatitis and biliary pancreatitis and those with a follow-up period of less than 1 year, we conducted a multivariate analysis using the data of 3739 patients to identify the risk factors of CP and subsequently develop a scoring system that could predict the development of CP in patients with AP. In addition, we validated the scoring system using a validation cohort.RESULTS Among the study subjects, 142 patients （12.98%） developed CP among patients with RAP. On the other hand, only 32 patients （1.21%） developed CP among patients with only one episode of AP. The multivariate analysis revealed that the presence of recurrent AP （RAP）, alcoho-lism, smoking habit, and age of onset of 〈 55 years were the four important risk factors for CP. We developed a scoring system （risk score 1 and risk score 2） from the derivation cohort by classifying the patients into low-risk, moderate-risk, and high-risk categories based on similar magnitudes of hazard and validated the performance using another validation cohort. Using the prediction score model, the area under the curve （AUC） [95% confdence interval （CI）] in predicting the 5-year CP incidence in risk score 1 （without the number of AP episodes） was 0.83 （0.79, 0.87）, whereas the AUC （95%CI） in risk score 2 （including the number of AP episodes） was 0.84 （0.80, 0.88）. This result demonstrated that the risk score 2 has somewhat better prediction performance than risk score 1. However, both of them had similar performance between the derivation and validation cohorts.CONCLUSIONIn the study,we identifed the risk factors of CP and devel-oped a prediction score 展开更多
Optimization of energy consump-tion for ecast model based on big data platform and parallel random forest
A healthy data set is acquired through data collection and preprocessing based on the construction of distribu...Optimization of energy consump-tion for ecast model based on big data platform and parallel random forest
A healthy data set is acquired through data collection and preprocessing based on the construction of distributed big data analysis platform such as Hadoop,Spark and Hbase.Re-gression forecasting model of energy consumption based on the parallel random forest algorithm is built to comprehensively ana-lyze and compare the relationship between input based on ran-dom forest prediction model,model parameters and output.The emphasis lies on comparative analysis of the decision tree num-ber,depth of the decision tree and maximumnumber of split,which will affect the training model accuracy,running time and complexity.Optimization of the prediction model canachieve ac-curate prediction on the coal consumption for power supply and soft measurement calculation.展开更多
文摘由于电离层电子密度随时间变化,且空间分布不均匀,对不同频段的无线电波产生延缓和折射,因此电离层电子密度变化是影响短波通信、卫星通信、全球导航卫星系统和其他空间通信质量的一个主要因素,本文对全球电离层电子密度(Number of electron,Ne)的预测工作对短波通信设备三维射线实时追踪定位提供必要条件。本文采用国际电离层参考模型提供的2016年电离层Ne数据,根据数据的三维空间时间序列特征,搭建了自编码器和卷积长短期记忆(Convolutional Long Short-Term Memory Network,Conv LSTM)网络组成的网络结构,在不引入地球自转周期之外任何先验知识的条件下,对Ne数据进行深度学习并实现预测,首先通过实验对比了SGD、Adagrad、Adadelta、Adam、Adamax和Nadam六种优化算法的性能,又对比了三种预测策略的均方根误差(Root Mean Square Error, RMSE),1h-to-1h预测策略的全球平均RMSE为1.0 NEU(最大值的0.4%),1h-to-24h和24h-to-24h预测策略的全球平均RMSE为6.3 NEU(2.6%)。由实验结果得出以下结论,一是Nadam优化算法更适合电离层Ne的深度学习,二是1h预测策略的性能与之前类似的电离层TEC预测工作(RMSE高于1.5 TECU,最大值的1%)相比有竞争力,但预测时间太短且对数据的实时性要求较高,三是两种24h预测策略虽能实现长期预测但性能不理想,要实现三维空间时间序列的长期高精度预测需要进一步改善神经网络、模型结构和预测策略。
文摘As the demand for wind energy continues to grow at exponential rate, reducing operation and maintenance (O & M) costs and improving reliability have become top priorities in wind turbine maintenance strategies. Prediction of wind turbine failures before they reach a catastrophic stage is critical to reduce the O & M cost due to unnecessary scheduled maintenance. A SCADA-data based condition monitoring system, which takes advantage of data already collected at the wind turbine controller, is a cost-effective way to monitor wind turbines for early warning of failures. This article proposes a methodology of fault prediction and automatically generating warning and alarm for wind turbine main bearings based on stored SCADA data using Artificial Neural Network (ANN). The ANN model of turbine main bearing normal behavior is established and then the deviation between estimated and actual values of the parameter is calculated. Furthermore, a method has been developed to generate early warning and alarm and avoid false warnings and alarms based on the deviation. In this way, wind farm operators are able to have enough time to plan maintenance, and thus, unanticipated downtime can be avoided and O & M costs can be reduced.
文摘The Hong Kong Observatory （HKO） has been developing a suite of nowcasting systems to support op- erations of the forecasting center and to provide a variety of nowcasting services for the general public and specialized users. The core system is named the Short-range Warnings of Intense Rainstorm of Localized Systems （SWIRLS）, which is a radar-based nowcasting system mainly for the automatic tracking of the movement of radar echoes and the short-range Quantitative Precipitation Forecast （QPF）. The differential, integral （or variational）, and object-oriented tracking algorithms were developed and integrated into the nowcasting suite. In order to predict severe weather associated with intense thunderstorms, such as high gust, hail, and lightning, SWIRLS was enhanced to SWIRLS-II by introduction of a number of physical models, especially the icing physics as well as the thermodynamics of the atmosphere. SWIRLS-Ⅱ was further enhanced with non-hydrostatic, high resolution numerical models for extending the forecast range up to 6h ahead. Meanwhile, SWIRLS was also modified for providing nowcasting services for aviation community and specialized users. To take into account the rapid development of lightning events, ensemble nowcasting techniques such as time-lagged and weighted average ensemble approaches were also adopted in the nowcasting system. Apart from operational uses in Hong Kong, SWIRLS/SWIRLS-Ⅱ was also exported to other places to participate in several international events such as the WMO/WWRP Forecast Demon- stration Project （FDP） during the Beijing 2008 Olympics Games and the Shanghai Expo 2010. Meanwhile, SWIRLS has also been transferred to various regional meteorological organizations for establishing their nowcasting infrastructure. This paper summarizes the history and the technologies of SWIRLS/SWIRLS-Ⅱ and its variants and the associated nowcasting applications and services provided by the HKO since the mid 1990s.
文摘AIM To explore the risk factors of developing chronic pan-creatitis （CP） in patients with acute pancreatitis （AP） and develop a prediction score for CP.METHODS Using the National Health Insurance Research Database in Taiwan, we obtained large, population-based data of 5971 eligible patients diagnosed with AP from 2000 to 2013. After excluding patients with obstructive pancreatitis and biliary pancreatitis and those with a follow-up period of less than 1 year, we conducted a multivariate analysis using the data of 3739 patients to identify the risk factors of CP and subsequently develop a scoring system that could predict the development of CP in patients with AP. In addition, we validated the scoring system using a validation cohort.RESULTS Among the study subjects, 142 patients （12.98%） developed CP among patients with RAP. On the other hand, only 32 patients （1.21%） developed CP among patients with only one episode of AP. The multivariate analysis revealed that the presence of recurrent AP （RAP）, alcoho-lism, smoking habit, and age of onset of 〈 55 years were the four important risk factors for CP. We developed a scoring system （risk score 1 and risk score 2） from the derivation cohort by classifying the patients into low-risk, moderate-risk, and high-risk categories based on similar magnitudes of hazard and validated the performance using another validation cohort. Using the prediction score model, the area under the curve （AUC） [95% confdence interval （CI）] in predicting the 5-year CP incidence in risk score 1 （without the number of AP episodes） was 0.83 （0.79, 0.87）, whereas the AUC （95%CI） in risk score 2 （including the number of AP episodes） was 0.84 （0.80, 0.88）. This result demonstrated that the risk score 2 has somewhat better prediction performance than risk score 1. However, both of them had similar performance between the derivation and validation cohorts.CONCLUSIONIn the study,we identifed the risk factors of CP and devel-oped a prediction score
文摘Optimization of energy consump-tion for ecast model based on big data platform and parallel random forest
A healthy data set is acquired through data collection and preprocessing based on the construction of distributed big data analysis platform such as Hadoop,Spark and Hbase.Re-gression forecasting model of energy consumption based on the parallel random forest algorithm is built to comprehensively ana-lyze and compare the relationship between input based on ran-dom forest prediction model,model parameters and output.The emphasis lies on comparative analysis of the decision tree num-ber,depth of the decision tree and maximumnumber of split,which will affect the training model accuracy,running time and complexity.Optimization of the prediction model canachieve ac-curate prediction on the coal consumption for power supply and soft measurement calculation.
