为了能够更加准确地实现地铁客流预测,提出了一种基于经验模态分解算法(empirical mode decomposition,EMD)优化非线性自回归(nonlinear auto regressive,NAR)动态神经网络的地铁客流量短时预测模型.分析地铁客流量数据后发现日客流量...为了能够更加准确地实现地铁客流预测,提出了一种基于经验模态分解算法(empirical mode decomposition,EMD)优化非线性自回归(nonlinear auto regressive,NAR)动态神经网络的地铁客流量短时预测模型.分析地铁客流量数据后发现日客流量具有一定的变化规律,为此使用了基于时间序列的NAR动态神经网络,该网络具有优秀的非线性动态拟合能力和反馈记忆的功能.结合EMD经验模态分解算法优化NAR动态神经网络预测模型,以此来减少预测误差,提高预测精度.结果显示,EMD-NAR神经网络组合预测模型适用于地铁客流的短时预测,预测精度可达93%,具有较好的应用价值.展开更多
水泥生产立磨出风口温度是判断立磨运行状态是否安全稳定的关键参数,对该参数提前预测可以减少立磨振动,提高运行稳定性,增加产量,降低能耗及相关碳排放。水泥立磨系统具有多参数、大时滞和非线性等复杂特性。针对上述问题,提出了基于...水泥生产立磨出风口温度是判断立磨运行状态是否安全稳定的关键参数,对该参数提前预测可以减少立磨振动,提高运行稳定性,增加产量,降低能耗及相关碳排放。水泥立磨系统具有多参数、大时滞和非线性等复杂特性。针对上述问题,提出了基于互相关延时分析优化的非线性自回归外部输入(Nonlinear AutoRegressive with eXogenous inputs,NARX)神经网络,并用于立磨出风口温度预测。首先,采用皮尔逊相关性分析从多个参数中确定影响立磨出风口温度的关键参数。同时,利用互相关延时分析进行时滞分析,解决大时滞问题。其次,通过优化的NARX神经网络,实现非线性工况下温度的精准预测。案例验证结果表明,所提出模型的拟合度达到了0.99967,均方误差为0.56483,预测精度达到了98.4%以上。预测模型结果可指导立磨操作人员及时控制立磨振动,提高水泥产量并降低能耗和碳排放。展开更多
Pantograph-catenary contact force provides the main basis for evaluation of current quality collection; however,the pantograph-catenary contact force is largely affected by the catenary irregularities.To analyze the c...Pantograph-catenary contact force provides the main basis for evaluation of current quality collection; however,the pantograph-catenary contact force is largely affected by the catenary irregularities.To analyze the correlated relationship between catenary irregularities and pantograph-catenary contact force,a method based on nonlinear auto-regressive with exogenous input(NARX) neural networks was developed.First,to collect the test data of catenary irregularities and contact force,the pantograph/catenary dynamics model was established and dynamic simulation was conducted using MATLAB/Simulink.Second,catenary irregularities were used as the input to NARX neural network and the contact force was determined as output of the NARX neural network,in which the neural network was trained by an improved training mechanism based on the regularization algorithm.The simulation results show that the testing error and correlation coefficient are 0.1100 and 0.8029,respectively,and the prediction accuracy is satisfactory.And the comparisons with other algorithms indicate the validity and superiority of the proposed approach.展开更多
文摘为了能够更加准确地实现地铁客流预测,提出了一种基于经验模态分解算法(empirical mode decomposition,EMD)优化非线性自回归(nonlinear auto regressive,NAR)动态神经网络的地铁客流量短时预测模型.分析地铁客流量数据后发现日客流量具有一定的变化规律,为此使用了基于时间序列的NAR动态神经网络,该网络具有优秀的非线性动态拟合能力和反馈记忆的功能.结合EMD经验模态分解算法优化NAR动态神经网络预测模型,以此来减少预测误差,提高预测精度.结果显示,EMD-NAR神经网络组合预测模型适用于地铁客流的短时预测,预测精度可达93%,具有较好的应用价值.
文摘水泥生产立磨出风口温度是判断立磨运行状态是否安全稳定的关键参数,对该参数提前预测可以减少立磨振动,提高运行稳定性,增加产量,降低能耗及相关碳排放。水泥立磨系统具有多参数、大时滞和非线性等复杂特性。针对上述问题,提出了基于互相关延时分析优化的非线性自回归外部输入(Nonlinear AutoRegressive with eXogenous inputs,NARX)神经网络,并用于立磨出风口温度预测。首先,采用皮尔逊相关性分析从多个参数中确定影响立磨出风口温度的关键参数。同时,利用互相关延时分析进行时滞分析,解决大时滞问题。其次,通过优化的NARX神经网络,实现非线性工况下温度的精准预测。案例验证结果表明,所提出模型的拟合度达到了0.99967,均方误差为0.56483,预测精度达到了98.4%以上。预测模型结果可指导立磨操作人员及时控制立磨振动,提高水泥产量并降低能耗和碳排放。
文摘南极Dome A(冰穹A)因其优良的观测条件被誉为地球上最好的天文观测台址之一。Dome A温度常年处于-30^-80℃,相对湿度40%~80%,温度起伏大,望远镜镜面易结霜,影响天文观测的效率和质量。为实现无人值守的智能化镜面除霜、减少除霜对观测时间的占用、降低除霜对镜面视宁度的影响、减少除霜对能源的消耗,提出了智能化除霜方法。首先,分析环境、科学数据、仪器三者的关系,利用外部输入非线性自回归(nonlinear auto regressive models with exogenous input,NARX)时间序列神经网络构建望远镜镜面状态的预测模型;其次,设计南极望远镜智能化除霜仿真系统,实时预测镜面情况,根据预测结果模拟采取相应的应对措施。结果表明该方法能有效实现智能化除霜,减少了人为干预,节约了观测时间,提高了望远镜运行的可靠性。
基金Project(20120009110035)supported by Specialized Research Fund for the Doctoral Program of Higher Education of ChinaProject(2011BAG01B05)supported by National Key Technology Research and Development Program of ChinaProject(2011AA110501)supported by National High-tech Research and Development Program of China
文摘Pantograph-catenary contact force provides the main basis for evaluation of current quality collection; however,the pantograph-catenary contact force is largely affected by the catenary irregularities.To analyze the correlated relationship between catenary irregularities and pantograph-catenary contact force,a method based on nonlinear auto-regressive with exogenous input(NARX) neural networks was developed.First,to collect the test data of catenary irregularities and contact force,the pantograph/catenary dynamics model was established and dynamic simulation was conducted using MATLAB/Simulink.Second,catenary irregularities were used as the input to NARX neural network and the contact force was determined as output of the NARX neural network,in which the neural network was trained by an improved training mechanism based on the regularization algorithm.The simulation results show that the testing error and correlation coefficient are 0.1100 and 0.8029,respectively,and the prediction accuracy is satisfactory.And the comparisons with other algorithms indicate the validity and superiority of the proposed approach.
