针对现有时间序列在线预测方法存在对数据特性变化感知与预测及时性不足的问题,创新设计了一种基于信息感知权重与误差预测的时间序列在线预测方法。该方法利用信息感知权重替换代价函数中遗忘因子λ0参量;通过建立输入数据与预测误差...针对现有时间序列在线预测方法存在对数据特性变化感知与预测及时性不足的问题,创新设计了一种基于信息感知权重与误差预测的时间序列在线预测方法。该方法利用信息感知权重替换代价函数中遗忘因子λ0参量;通过建立输入数据与预测误差的映射关系进行误差预测,采用加权误差补偿系数实现误差补偿。通过改变隐含层节点数方法进行多次单步预测实验,实验结果从预测精度和泛化性等多方面验证了设计方法优异的单步预测能力。其中,Sinc、Mackey-Glass和Solar Energy 3个数据选取点的单步预测方差分别达到1.56×10-13、2.29×10-7与1.43。根据实际失效情况分别设定失效电压为5.8与5.6 V,并针对封装降压电源模块加速寿命实验实测数据进行多步预测。五步与十步预测结果显示设计方法均有效预测电源失效。实验结果全面说明设计方法在预测数据特性发生变化情况时,能够稳定、精准且有效地完成在线单步与多步预测。展开更多
This paper proposes a novel method to predict the spur gear pair’s static transmission error based on the accuracy grade,in which manufacturing errors(MEs),assembly errors(AEs),tooth deflections(TDs)and profile modif...This paper proposes a novel method to predict the spur gear pair’s static transmission error based on the accuracy grade,in which manufacturing errors(MEs),assembly errors(AEs),tooth deflections(TDs)and profile modifications(PMs)are considered.For the prediction,a discrete gear model for generating the error tooth profile based on the ISO accuracy grade is presented.Then,the gear model and a tooth deflection model for calculating the tooth compliance on gear meshing are coupled with the transmission error model to make the prediction by checking the interference status between gear and pinion.The prediction method is validated by comparison with the experimental results from the literature,and a set of cases are simulated to study the effects of MEs,AEs,TDs and PMs on the static transmission error.In addition,the time-varying backlash caused by both MEs and AEs,and the contact ratio under load conditions are also investigated.The results show that the novel method can effectively predict the range of the static transmission error under different accuracy grades.The prediction results can provide references for the selection of gear design parameters and the optimization of transmission performance in the design stage of gear systems.展开更多
An important problem in demand planning for energy consumption is developing an accurate energy forecasting model. In fact, it is not possible to allocate the energy resources in an optimal manner without having accur...An important problem in demand planning for energy consumption is developing an accurate energy forecasting model. In fact, it is not possible to allocate the energy resources in an optimal manner without having accurate demand value. A new energy forecasting model was proposed based on the back-propagation(BP) type neural network and imperialist competitive algorithm. The proposed method offers the advantage of local search ability of BP technique and global search ability of imperialist competitive algorithm. Two types of empirical data regarding the energy demand(gross domestic product(GDP), population, import, export and energy demand) in Turkey from 1979 to 2005 and electricity demand(population, GDP, total revenue from exporting industrial products and electricity consumption) in Thailand from 1986 to 2010 were investigated to demonstrate the applicability and merits of the present method. The performance of the proposed model is found to be better than that of conventional back-propagation neural network with low mean absolute error.展开更多
文摘针对现有时间序列在线预测方法存在对数据特性变化感知与预测及时性不足的问题,创新设计了一种基于信息感知权重与误差预测的时间序列在线预测方法。该方法利用信息感知权重替换代价函数中遗忘因子λ0参量;通过建立输入数据与预测误差的映射关系进行误差预测,采用加权误差补偿系数实现误差补偿。通过改变隐含层节点数方法进行多次单步预测实验,实验结果从预测精度和泛化性等多方面验证了设计方法优异的单步预测能力。其中,Sinc、Mackey-Glass和Solar Energy 3个数据选取点的单步预测方差分别达到1.56×10-13、2.29×10-7与1.43。根据实际失效情况分别设定失效电压为5.8与5.6 V,并针对封装降压电源模块加速寿命实验实测数据进行多步预测。五步与十步预测结果显示设计方法均有效预测电源失效。实验结果全面说明设计方法在预测数据特性发生变化情况时,能够稳定、精准且有效地完成在线单步与多步预测。
基金Project(51675061)supported by the National Natural Science Foundation of China。
文摘This paper proposes a novel method to predict the spur gear pair’s static transmission error based on the accuracy grade,in which manufacturing errors(MEs),assembly errors(AEs),tooth deflections(TDs)and profile modifications(PMs)are considered.For the prediction,a discrete gear model for generating the error tooth profile based on the ISO accuracy grade is presented.Then,the gear model and a tooth deflection model for calculating the tooth compliance on gear meshing are coupled with the transmission error model to make the prediction by checking the interference status between gear and pinion.The prediction method is validated by comparison with the experimental results from the literature,and a set of cases are simulated to study the effects of MEs,AEs,TDs and PMs on the static transmission error.In addition,the time-varying backlash caused by both MEs and AEs,and the contact ratio under load conditions are also investigated.The results show that the novel method can effectively predict the range of the static transmission error under different accuracy grades.The prediction results can provide references for the selection of gear design parameters and the optimization of transmission performance in the design stage of gear systems.
文摘An important problem in demand planning for energy consumption is developing an accurate energy forecasting model. In fact, it is not possible to allocate the energy resources in an optimal manner without having accurate demand value. A new energy forecasting model was proposed based on the back-propagation(BP) type neural network and imperialist competitive algorithm. The proposed method offers the advantage of local search ability of BP technique and global search ability of imperialist competitive algorithm. Two types of empirical data regarding the energy demand(gross domestic product(GDP), population, import, export and energy demand) in Turkey from 1979 to 2005 and electricity demand(population, GDP, total revenue from exporting industrial products and electricity consumption) in Thailand from 1986 to 2010 were investigated to demonstrate the applicability and merits of the present method. The performance of the proposed model is found to be better than that of conventional back-propagation neural network with low mean absolute error.
