This paper investigates the feedback control of hidden Markov process（HMP） in the face of loss of some observation processes.The control action facilitates or impedes some particular transitions from an inferred cur...This paper investigates the feedback control of hidden Markov process（HMP） in the face of loss of some observation processes.The control action facilitates or impedes some particular transitions from an inferred current state in the attempt to maximize the probability that the HMP is driven to a desirable absorbing state.This control problem is motivated by the need for judicious resource allocation to win an air operation involving two opposing forces.The effectiveness of a receding horizon control scheme based on the inferred discrete state is examined.Tolerance to loss of sensors that help determine the state of the air operation is achieved through a decentralized scheme that estimates a continuous state from measurements of linear models with additive noise.The discrete state of the HMP is identified using three well-known detection schemes.The sub-optimal control policy based on the detected state is implemented on-line in a closed-loop,where the air operation is simulated as a stochastic process with SimEvents,and the measurement process is simulated for a range of single sensor loss rates.展开更多
隐蔽火区地表碳通量监测对评估其温室效应及火区范围圈定十分重要。针对碳通量影响因素多、难预测等问题,提出了一种基于灰狼优化算法(Grey Wolf Optimization,GWO)-改进高斯过程回归(Gaussian Process Regression,GPR)-核密度估计(Kern...隐蔽火区地表碳通量监测对评估其温室效应及火区范围圈定十分重要。针对碳通量影响因素多、难预测等问题,提出了一种基于灰狼优化算法(Grey Wolf Optimization,GWO)-改进高斯过程回归(Gaussian Process Regression,GPR)-核密度估计(Kernel Density Estimation,KDE)预测模型。采用格拉布斯检验法剔除异常值,运用GWO优化GPR算法中的超参数,以提高预测精度。使用验证集预测误差并进行KDE建模,得到碳通量的区间预测值,进而针对组合模型的泛化能力及参数敏感性分析进行评估。结果显示:GWO-GPR-KDE模型的平均绝对误差、均方根误差、决定系数、80%置信区间宽度和95%置信区间宽度分别为0.95386、1.2663、0.92656、0.387和0.823,这些评估指标均优于随机森林(Random Forest,RF)、反向传播神经网络(Back Propagation Neural Network,BPNN)、结合多层感知器的支持向量机(Multilayer Perceptron-Support Vector Machine,MLP-SVM)、高斯过程回归(Gaussian Process Regression,GPR)等经典模型。GWO-GPR-KDE模型对隐蔽火区地表碳通量预测具有较好的准确性和泛化性,为煤田火区防控和温室效应评估提供了新思路。展开更多
文摘This paper investigates the feedback control of hidden Markov process（HMP） in the face of loss of some observation processes.The control action facilitates or impedes some particular transitions from an inferred current state in the attempt to maximize the probability that the HMP is driven to a desirable absorbing state.This control problem is motivated by the need for judicious resource allocation to win an air operation involving two opposing forces.The effectiveness of a receding horizon control scheme based on the inferred discrete state is examined.Tolerance to loss of sensors that help determine the state of the air operation is achieved through a decentralized scheme that estimates a continuous state from measurements of linear models with additive noise.The discrete state of the HMP is identified using three well-known detection schemes.The sub-optimal control policy based on the detected state is implemented on-line in a closed-loop,where the air operation is simulated as a stochastic process with SimEvents,and the measurement process is simulated for a range of single sensor loss rates.
文摘隐蔽火区地表碳通量监测对评估其温室效应及火区范围圈定十分重要。针对碳通量影响因素多、难预测等问题,提出了一种基于灰狼优化算法(Grey Wolf Optimization,GWO)-改进高斯过程回归(Gaussian Process Regression,GPR)-核密度估计(Kernel Density Estimation,KDE)预测模型。采用格拉布斯检验法剔除异常值,运用GWO优化GPR算法中的超参数,以提高预测精度。使用验证集预测误差并进行KDE建模,得到碳通量的区间预测值,进而针对组合模型的泛化能力及参数敏感性分析进行评估。结果显示:GWO-GPR-KDE模型的平均绝对误差、均方根误差、决定系数、80%置信区间宽度和95%置信区间宽度分别为0.95386、1.2663、0.92656、0.387和0.823,这些评估指标均优于随机森林(Random Forest,RF)、反向传播神经网络(Back Propagation Neural Network,BPNN)、结合多层感知器的支持向量机(Multilayer Perceptron-Support Vector Machine,MLP-SVM)、高斯过程回归(Gaussian Process Regression,GPR)等经典模型。GWO-GPR-KDE模型对隐蔽火区地表碳通量预测具有较好的准确性和泛化性,为煤田火区防控和温室效应评估提供了新思路。
