Inherent flaws in the extended Kalman filter(EKF) algorithm were pointed out and unscented Kalman filter(UKF) was put forward as an alternative.Furthermore,a novel adaptive unscented Kalman filter(AUKF) based on innov...Inherent flaws in the extended Kalman filter(EKF) algorithm were pointed out and unscented Kalman filter(UKF) was put forward as an alternative.Furthermore,a novel adaptive unscented Kalman filter(AUKF) based on innovation was developed.The three data-fusing approaches were analyzed and evaluated in a mathematically rigorous way.Field experiments conducted in lake further demonstrate that AUKF reduces the position error approximately by 65% compared with EKF and by 35% UKF and improves the robust performance.展开更多
本研究提出了一种基于反向传播神经网络(BPNN)和自适应无迹卡尔曼滤波器(AUKF)的SOC(state of charge)估计方法。首先针对电池SOC与端电压之间在不同温度下的关系,研究设计了一系列温度补偿策略,以提高在低温、低SOC条件下的估计精度。...本研究提出了一种基于反向传播神经网络(BPNN)和自适应无迹卡尔曼滤波器(AUKF)的SOC(state of charge)估计方法。首先针对电池SOC与端电压之间在不同温度下的关系,研究设计了一系列温度补偿策略,以提高在低温、低SOC条件下的估计精度。其次,利用反向传播神经网络(BPNN)建立了一个耦合了温度补偿策略的电池模型。这个模型能更好地适应低温和低SOC条件下的电池状态变化,提高了SOC估计的准确性。最后,基于BPNN电池模型建立了BPNN-AUKF的SOC估计框架,通过利用测量值与测量预测值之间的信息和残差序列,对系统过程和测量噪声协方差进行估计修正。通过实验验证,发现该方法在低温环境下具有明显优势,相比传统方法能够更准确地估计电池的SOC,且具备较好的泛化能力。这种基于BPNN-AUKF方法的SOC估计器不仅适用于自主无人潜水器(AUV),而且对于其他在复杂环境中工作的车辆也具有广泛的应用价值。展开更多
基金Projects(2009AA093302,2002AA401003)supported by the National High-Tech Research and Development Program of ChinaProject(YYYJ-0917)supported by the Knowledge Innovation of Chinese Academy of Sciences+1 种基金Projects(61273334,61233013)supported by the National Natural Science Foundation of ChinaProject(2011010025-401)supported by the Natural Science Foundation of Liaoning Province,China
文摘Inherent flaws in the extended Kalman filter(EKF) algorithm were pointed out and unscented Kalman filter(UKF) was put forward as an alternative.Furthermore,a novel adaptive unscented Kalman filter(AUKF) based on innovation was developed.The three data-fusing approaches were analyzed and evaluated in a mathematically rigorous way.Field experiments conducted in lake further demonstrate that AUKF reduces the position error approximately by 65% compared with EKF and by 35% UKF and improves the robust performance.
文摘本研究提出了一种基于反向传播神经网络(BPNN)和自适应无迹卡尔曼滤波器(AUKF)的SOC(state of charge)估计方法。首先针对电池SOC与端电压之间在不同温度下的关系,研究设计了一系列温度补偿策略,以提高在低温、低SOC条件下的估计精度。其次,利用反向传播神经网络(BPNN)建立了一个耦合了温度补偿策略的电池模型。这个模型能更好地适应低温和低SOC条件下的电池状态变化,提高了SOC估计的准确性。最后,基于BPNN电池模型建立了BPNN-AUKF的SOC估计框架,通过利用测量值与测量预测值之间的信息和残差序列,对系统过程和测量噪声协方差进行估计修正。通过实验验证,发现该方法在低温环境下具有明显优势,相比传统方法能够更准确地估计电池的SOC,且具备较好的泛化能力。这种基于BPNN-AUKF方法的SOC估计器不仅适用于自主无人潜水器(AUV),而且对于其他在复杂环境中工作的车辆也具有广泛的应用价值。
