为应对当今供应链库存管理面临的牛鞭效应、两时间尺度特性和不确定性干扰等挑战,开发了一种基于径向基函数神经网络(radial basis function neural network,RBFNN)的两时间尺度供应链H_(∞)最优控制器。利用奇异摄动理论将原两时间尺...为应对当今供应链库存管理面临的牛鞭效应、两时间尺度特性和不确定性干扰等挑战,开发了一种基于径向基函数神经网络(radial basis function neural network,RBFNN)的两时间尺度供应链H_(∞)最优控制器。利用奇异摄动理论将原两时间尺度供应链模型分解为2个具有不同时间尺度的独立子系统;创新性地使用RBFNN在线近似补偿子系统的不确定项,进而采用H_(∞)控制来抑制RBFNN近似误差带来的不确定性。在理论层面上分析证明了所提方法的稳定性。通过一个电视机生产流程仿真案例,验证了所提方法相比2种其他两时间尺度问题解决方法,具有更高的跟踪控制精度和应用可行性。展开更多
为实现对船体分段焊接质量的有效管控,提出基于径向基函数神经网络(Radial Basis Function Neural Network,RBFNN)模型和异常检测的船体分段焊接质量溯源方法。从质量影响因素、不合格产品质量溯源方法和不合格产品质量溯源体系架构等...为实现对船体分段焊接质量的有效管控,提出基于径向基函数神经网络(Radial Basis Function Neural Network,RBFNN)模型和异常检测的船体分段焊接质量溯源方法。从质量影响因素、不合格产品质量溯源方法和不合格产品质量溯源体系架构等方面对船体分段焊接不合格产品质量溯源进行设计。从数据预处理、影响因素定位和影响因素排序等方面对船体分段焊接不合格产品质量溯源流程进行设置。经实例验证,所提出的方法可有效进行船体分段焊接质量溯源。展开更多
A description of the reliability evaluation of tactical network is given, which reflects not only the non-reliable factors of nodes and links but also the factors of network topological structure. On the basis of this...A description of the reliability evaluation of tactical network is given, which reflects not only the non-reliable factors of nodes and links but also the factors of network topological structure. On the basis of this description, a reliability prediction model and its algorithms are put forward based on the radial basis function neural network (RBFNN) for the tactical network. This model can carry out the non-linear mapping relationship between the network topological structure, the nodes reliabilities, the links reliabilities and the reliability of network. The results of simulation prove the effectiveness of this method in the reliability and the connectivity prediction for tactical network.展开更多
在复杂连续环境下,强化学习系统的状态空间面临维数灾难问题,需要采取量化的方法,降低输入空间的复杂度。径向基神经网络(RBFNN:Radial Basis Function Neural Networks)具有较强的函数逼近能力及泛化能力,由此提出了基于径向基神经网络...在复杂连续环境下,强化学习系统的状态空间面临维数灾难问题,需要采取量化的方法,降低输入空间的复杂度。径向基神经网络(RBFNN:Radial Basis Function Neural Networks)具有较强的函数逼近能力及泛化能力,由此提出了基于径向基神经网络的Q学习方法,并将其应用于单机器人的自主导航。在基于径向基神经网络的强化学习系统中,用径向基神经网络逼近状态空间和Q函数,使学习系统具有良好的泛化能力。仿真结果表明,该导航方法具有较强的避碰能力,提高了机器人对环境的适应能力。展开更多
A fuzzy observations-based radial basis function neural network （FORBFNN） is presented for modeling nonlinear systems in which the observations of response are imprecise but can be represented as fuzzy membership fu...A fuzzy observations-based radial basis function neural network （FORBFNN） is presented for modeling nonlinear systems in which the observations of response are imprecise but can be represented as fuzzy membership functions. In the FORBFNN model, the weight coefficients of nodes in the hidden layer are identified by using the fuzzy expectation-maximization （ EM ） algorithm, whereas the optimal number of these nodes as well as the centers and widths of radial basis functions are automatically constructed by using a data-driven method. Namely, the method starts with an initial node, and then a new node is added in a hidden layer according to some rules. This procedure is not terminated until the model meets the preset requirements. The method considers both the accuracy and complexity of the model. Numerical simulation results show that the modeling method is effective, and the established model has high prediction accuracy.展开更多
在交通碳达峰和碳中和的背景下,高精度、细粒度、可实施性强的机动车能耗实时预测方法成为交通减碳关键组成之一。针对传统基于回归的车辆能耗模型普适性较差的问题,提出了一种基于径向基函数神经网络(radial basis function neural net...在交通碳达峰和碳中和的背景下,高精度、细粒度、可实施性强的机动车能耗实时预测方法成为交通减碳关键组成之一。针对传统基于回归的车辆能耗模型普适性较差的问题,提出了一种基于径向基函数神经网络(radial basis function neural network,RBFNN)的车辆能耗预测模型。首先分析车辆能耗影响因素并基于Min-Max标准化方法对影响因素矩阵进行归一化处理,然后基于灰狼算法(grey wolf optimization,GWO)优化RBFNN算法隐藏层中心点、高斯函数的宽度和隐含层与输出层连接的权值的训练,最后从横向模型对比和实车实测数据进行模型预测准确度分析。测试结果表明:RBFNN算法预测准确度较传统回归模型提高约12%,整体准确度达到90%以上,能够很好地对城市机动车能耗进行预测。展开更多
文摘为应对当今供应链库存管理面临的牛鞭效应、两时间尺度特性和不确定性干扰等挑战,开发了一种基于径向基函数神经网络(radial basis function neural network,RBFNN)的两时间尺度供应链H_(∞)最优控制器。利用奇异摄动理论将原两时间尺度供应链模型分解为2个具有不同时间尺度的独立子系统;创新性地使用RBFNN在线近似补偿子系统的不确定项,进而采用H_(∞)控制来抑制RBFNN近似误差带来的不确定性。在理论层面上分析证明了所提方法的稳定性。通过一个电视机生产流程仿真案例,验证了所提方法相比2种其他两时间尺度问题解决方法,具有更高的跟踪控制精度和应用可行性。
文摘为实现对船体分段焊接质量的有效管控,提出基于径向基函数神经网络(Radial Basis Function Neural Network,RBFNN)模型和异常检测的船体分段焊接质量溯源方法。从质量影响因素、不合格产品质量溯源方法和不合格产品质量溯源体系架构等方面对船体分段焊接不合格产品质量溯源进行设计。从数据预处理、影响因素定位和影响因素排序等方面对船体分段焊接不合格产品质量溯源流程进行设置。经实例验证,所提出的方法可有效进行船体分段焊接质量溯源。
文摘A description of the reliability evaluation of tactical network is given, which reflects not only the non-reliable factors of nodes and links but also the factors of network topological structure. On the basis of this description, a reliability prediction model and its algorithms are put forward based on the radial basis function neural network (RBFNN) for the tactical network. This model can carry out the non-linear mapping relationship between the network topological structure, the nodes reliabilities, the links reliabilities and the reliability of network. The results of simulation prove the effectiveness of this method in the reliability and the connectivity prediction for tactical network.
文摘在复杂连续环境下,强化学习系统的状态空间面临维数灾难问题,需要采取量化的方法,降低输入空间的复杂度。径向基神经网络(RBFNN:Radial Basis Function Neural Networks)具有较强的函数逼近能力及泛化能力,由此提出了基于径向基神经网络的Q学习方法,并将其应用于单机器人的自主导航。在基于径向基神经网络的强化学习系统中,用径向基神经网络逼近状态空间和Q函数,使学习系统具有良好的泛化能力。仿真结果表明,该导航方法具有较强的避碰能力,提高了机器人对环境的适应能力。
基金The National Natural Science Foundation of China(No.51106025,51106027,51036002)Specialized Research Fund for the Doctoral Program of Higher Education(No.20130092110061)the Youth Foundation of Nanjing Institute of Technology(No.QKJA201303)
文摘A fuzzy observations-based radial basis function neural network （FORBFNN） is presented for modeling nonlinear systems in which the observations of response are imprecise but can be represented as fuzzy membership functions. In the FORBFNN model, the weight coefficients of nodes in the hidden layer are identified by using the fuzzy expectation-maximization （ EM ） algorithm, whereas the optimal number of these nodes as well as the centers and widths of radial basis functions are automatically constructed by using a data-driven method. Namely, the method starts with an initial node, and then a new node is added in a hidden layer according to some rules. This procedure is not terminated until the model meets the preset requirements. The method considers both the accuracy and complexity of the model. Numerical simulation results show that the modeling method is effective, and the established model has high prediction accuracy.
文摘在交通碳达峰和碳中和的背景下,高精度、细粒度、可实施性强的机动车能耗实时预测方法成为交通减碳关键组成之一。针对传统基于回归的车辆能耗模型普适性较差的问题,提出了一种基于径向基函数神经网络(radial basis function neural network,RBFNN)的车辆能耗预测模型。首先分析车辆能耗影响因素并基于Min-Max标准化方法对影响因素矩阵进行归一化处理,然后基于灰狼算法(grey wolf optimization,GWO)优化RBFNN算法隐藏层中心点、高斯函数的宽度和隐含层与输出层连接的权值的训练,最后从横向模型对比和实车实测数据进行模型预测准确度分析。测试结果表明:RBFNN算法预测准确度较传统回归模型提高约12%,整体准确度达到90%以上,能够很好地对城市机动车能耗进行预测。
