建立磁流变阻尼器的动态模型以描述其强非线性动力学行为是智能磁流变控制系统设计及应用的关键环节之一。泛化能力是衡量基于人工神经网络技术的磁流变阻尼器非参数化模型性能的重要指标,也是保证控制系统稳定性和可靠性的重要因素。...建立磁流变阻尼器的动态模型以描述其强非线性动力学行为是智能磁流变控制系统设计及应用的关键环节之一。泛化能力是衡量基于人工神经网络技术的磁流变阻尼器非参数化模型性能的重要指标,也是保证控制系统稳定性和可靠性的重要因素。基于磁流变阻尼器的动力学试验数据,提出贝叶斯推理分析框架下的非线性自回归(nonlinear autoregressive with exogenous inputs,NARX)神经网络技术建立磁流变阻尼器的动态模型,通过网络结构优化和正则化学习算法的结合以有效地提高模型的预测精度和泛化能力。研究结果表明,基于贝叶斯推理的NARX网络模型能够准确地预测磁流变阻尼器在周期和随机激励下的非线性动态行为,同时验证了该模型相比于非正则化模型在泛化性能方面的优越性,因此,有利于实现磁流变控制系统的实时、鲁棒智能化控制。展开更多
参数识别是结构健康监测、性能评估的关键问题之一。作为一种代表性的动力系统时域参数化模型方法,自回归滑动平均(Auto-regressive and moving average,ARMA)模型在机械和土木工程结构的参数识别中得到了广泛应用;另一方面,尽管一般而...参数识别是结构健康监测、性能评估的关键问题之一。作为一种代表性的动力系统时域参数化模型方法,自回归滑动平均(Auto-regressive and moving average,ARMA)模型在机械和土木工程结构的参数识别中得到了广泛应用;另一方面,尽管一般而言神经网络模型的权重和阈值并不需要具备明确的物理意义,但由于神经网络具有描述复杂函数关系的能力,作为一种非参数化模型方法在结构动力系统的建模和控制领域发挥重要作用。该文首先通过结构运动平衡方程的离散时间解,证明了非参数化神经网络模型与ARMA模型在描述线性结构动力系统的响应时间序列上的等效性,在此基础上,提出了一种从结构的非参数化神经网络模型中抽取结构物理参数的新方法。通过一个多自由度系统的数值模拟结果和一个四层钢框架模型的动力试验实测数据验证了所提出的结构参数抽取方法的有效性。展开更多
Moving object extraction and classification are important problems in automated video surveillance systems. A background model based on region segmentation is proposed. An adaptive single Gaussian background model is ...Moving object extraction and classification are important problems in automated video surveillance systems. A background model based on region segmentation is proposed. An adaptive single Gaussian background model is used in the stable region with gradual changes, and a nonparametric model is used in the variable region with jumping changes. A generalized agglomerative scheme is used to merge the pixels in the variable region and fill in the small interspaces. A two-threshold sequential algorithmic scheme is used to group the background samples of the variable region into distinct Gaussian distributions to accelerate the kernel density computation speed of the nonparametric model. In the feature-based object classification phase, the surveillance scene is first partitioned according to the road boundaries of different traffic directions and then re-segmented according to their scene localities. The method improves the discriminability of the features in each partition. AdaBoost method is applied to evaluate the relative importance of the features in each partition respectively and distinguish whether an object is a vehicle, a single human, a human group, or a bike. Experimental results show that the proposed method achieves higher performance in comparison with the existing method.展开更多
文摘建立磁流变阻尼器的动态模型以描述其强非线性动力学行为是智能磁流变控制系统设计及应用的关键环节之一。泛化能力是衡量基于人工神经网络技术的磁流变阻尼器非参数化模型性能的重要指标,也是保证控制系统稳定性和可靠性的重要因素。基于磁流变阻尼器的动力学试验数据,提出贝叶斯推理分析框架下的非线性自回归(nonlinear autoregressive with exogenous inputs,NARX)神经网络技术建立磁流变阻尼器的动态模型,通过网络结构优化和正则化学习算法的结合以有效地提高模型的预测精度和泛化能力。研究结果表明,基于贝叶斯推理的NARX网络模型能够准确地预测磁流变阻尼器在周期和随机激励下的非线性动态行为,同时验证了该模型相比于非正则化模型在泛化性能方面的优越性,因此,有利于实现磁流变控制系统的实时、鲁棒智能化控制。
文摘参数识别是结构健康监测、性能评估的关键问题之一。作为一种代表性的动力系统时域参数化模型方法,自回归滑动平均(Auto-regressive and moving average,ARMA)模型在机械和土木工程结构的参数识别中得到了广泛应用;另一方面,尽管一般而言神经网络模型的权重和阈值并不需要具备明确的物理意义,但由于神经网络具有描述复杂函数关系的能力,作为一种非参数化模型方法在结构动力系统的建模和控制领域发挥重要作用。该文首先通过结构运动平衡方程的离散时间解,证明了非参数化神经网络模型与ARMA模型在描述线性结构动力系统的响应时间序列上的等效性,在此基础上,提出了一种从结构的非参数化神经网络模型中抽取结构物理参数的新方法。通过一个多自由度系统的数值模拟结果和一个四层钢框架模型的动力试验实测数据验证了所提出的结构参数抽取方法的有效性。
基金Project supported by the Science Fund for Creative Research Groups of National Natural Science Foundation of China(No.51521064)the National Natural Science Foundation of China(Nos.11172260,11372270,and 51375434)
基金supported by the Science and Technology Program of Zhejiang Province of China(2005C11001-02).
文摘Moving object extraction and classification are important problems in automated video surveillance systems. A background model based on region segmentation is proposed. An adaptive single Gaussian background model is used in the stable region with gradual changes, and a nonparametric model is used in the variable region with jumping changes. A generalized agglomerative scheme is used to merge the pixels in the variable region and fill in the small interspaces. A two-threshold sequential algorithmic scheme is used to group the background samples of the variable region into distinct Gaussian distributions to accelerate the kernel density computation speed of the nonparametric model. In the feature-based object classification phase, the surveillance scene is first partitioned according to the road boundaries of different traffic directions and then re-segmented according to their scene localities. The method improves the discriminability of the features in each partition. AdaBoost method is applied to evaluate the relative importance of the features in each partition respectively and distinguish whether an object is a vehicle, a single human, a human group, or a bike. Experimental results show that the proposed method achieves higher performance in comparison with the existing method.
