Traditional methods for plan path prediction have low accuracy and stability. In this paper, we propose a novel approach for plan path prediction based on relative motion between positions(RMBP) by mining historical f...Traditional methods for plan path prediction have low accuracy and stability. In this paper, we propose a novel approach for plan path prediction based on relative motion between positions(RMBP) by mining historical flight trajectories. A probability statistical model is introduced to model the stochastic factors during the whole flight process. The model object is the sequence of velocity vectors in the three-dimensional Earth space. First, we model the moving trend of aircraft including the speed(constant, acceleration, or deceleration), yaw(left, right, or straight), and pitch(climb, descent, or cruise) using a hidden Markov model(HMM) under the restrictions of aircraft performance parameters. Then, several Gaussian mixture models(GMMs) are used to describe the conditional distribution of each moving trend. Once the models are built, machine learning algorithms are applied to obtain the optimal parameters of the model from the historical training data. After completing the learning process, the velocity vector sequence of the flight is predicted by the proposed model under the Bayesian framework, so that we can use kinematic equations, depending on the moving patterns, to calculate the flight position at every radar acquisition cycle. To obtain higher prediction accuracy, a uniform interpolation method is used to correct the predicted position each second. Finally, a plan trajectory is concatenated by the predicted discrete points. Results of simulations with collected data demonstrate that this approach not only fulfils the goals of traditional methods, such as the prediction of fly-over time and altitude of waypoints along the planned route, but also can be used to plan a complete path for an aircraft with high accuracy. Experiments are conducted to demonstrate the superiority of this approach to some existing methods.展开更多
Winding is an important part of the electrical machine and plays a key role in reliability.In this paper,the reliability of multiphase winding structure in permanent magnet machines is evaluated based on the Markov mo...Winding is an important part of the electrical machine and plays a key role in reliability.In this paper,the reliability of multiphase winding structure in permanent magnet machines is evaluated based on the Markov model.The mean time to failure is used to compare the reliability of different windings structure.The mean time to failure of multiphase winding is derived in terms of the underlying parameters.The mean time to failure of winding is affected by the number of phases,the winding failure rate,the fault-tolerant mechanism success probability,and the state transition success probability.The influence of the phase number,winding distribution types,multi three-phase structure,and fault-tolerant mechanism success probability on the winding reliability is investigated.The results of reliability analysis lay the foundation for the reliability design of permanent magnet machines.展开更多
Deep reinforcement learning (deep RL) has the potential to replace classic robotic controllers. State-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Poli...Deep reinforcement learning (deep RL) has the potential to replace classic robotic controllers. State-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient and Soft Actor-Critic Reinforcement Algorithms, to mention a few, have been investigated for training robots to walk. However, conflicting performance results of these algorithms have been reported in the literature. In this work, we present the performance analysis of the above three state-of-the-art Deep Reinforcement algorithms for a constant velocity walking task on a quadruped. The performance is analyzed by simulating the walking task of a quadruped equipped with a range of sensors present on a physical quadruped robot. Simulations of the three algorithms across a range of sensor inputs and with domain randomization are performed. The strengths and weaknesses of each algorithm for the given task are discussed. We also identify a set of sensors that contribute to the best performance of each Deep Reinforcement algorithm.展开更多
Technological advances,innovation and the new industry 4.0 paradigm guide Distribution System Operators towards a competitive market that requires the articulation of flexible demand response systems.The lack of measu...Technological advances,innovation and the new industry 4.0 paradigm guide Distribution System Operators towards a competitive market that requires the articulation of flexible demand response systems.The lack of measurement and standardization systems in the industry process chain in developing countries prevents the penetration of demand management models,generating inefficiency in the analysis and processing of informa-tion to validate the flexibility potential that large consumers can contribute to the network operator.In this sense,the research uses as input variables the energy and power of the load profile provided by the utility energy meter to obtain the disaggregated forecast in quarter-hour intervals in 4-time windows validated through metrics and its results evaluated by the RMS error to get the total error generated by the methodology with the appli-cation of Machine Learning and Big Data techniques in the Python computational tool through Combinatorial Disaggregation Optimization and Factorial Hidden Markov models.展开更多
Markov decision process(MDP)offers a general framework for modelling sequential decision making where outcomes are random.In particular,it serves as a mathematical framework for reinforcement learning.This paper intro...Markov decision process(MDP)offers a general framework for modelling sequential decision making where outcomes are random.In particular,it serves as a mathematical framework for reinforcement learning.This paper introduces an extension of MDP,namely quantum MDP(q MDP),that can serve as a mathematical model of decision making about quantum systems.We develop dynamic programming algorithms for policy evaluation and finding optimal policies for q MDPs in the case of finite-horizon.The results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.展开更多
In this paper, we introduce the concepts of square neurons, power neu-rons, and new learning algorithms based on square neurons, and power neurons. First, we briefly review the basic idea of the Boltzmann Machine, spe...In this paper, we introduce the concepts of square neurons, power neu-rons, and new learning algorithms based on square neurons, and power neurons. First, we briefly review the basic idea of the Boltzmann Machine, specifically that the invariant distributions of the Boltzmann Machine generate Markov chains. We further review ABM (Attrasoft Boltzmann Machine). Next, we review the θ-transformation and its completeness, i.e. any function can be expanded by θ-transformation. The invariant distribution of the ABM is a θ-transformation;therefore, an ABM can simulate any distribution. We review the linear neurons and the associated learning algorithm. We then discuss the problems of the exponential neurons used in ABM, which are unstable, and the problems of the linear neurons, which do not discriminate the wrong answers from the right answers as sharply as the exponential neurons. Finally, we introduce the concept of square neurons and power neurons. We also discuss the advantages of the learning algorithms based on square neurons and power neurons, which have the stability of the linear neurons and the sharp discrimination of the exponential neurons.展开更多
Hornik, Stinchcombe & White have shown that the multilayer feed forward networks with enough hidden layers are universal approximators. Roux & Bengio have proved that adding hidden units yield a strictly impro...Hornik, Stinchcombe & White have shown that the multilayer feed forward networks with enough hidden layers are universal approximators. Roux & Bengio have proved that adding hidden units yield a strictly improved modeling power, and Restricted Boltzmann Machines (RBM) are universal approximators of discrete distributions. In this paper, we provide yet another proof. The advantage of this new proof is that it will lead to several new learning algorithms. We prove that the Deep Neural Networks implement an expansion and the expansion is complete. First, we briefly review the basic Boltzmann Machine and that the invariant distributions of the Boltzmann Machine generate Markov chains. We then review the θ-transformation and its completeness, i.e. any function can be expanded by θ-transformation. We further review ABM (Attrasoft Boltzmann Machine). The invariant distribution of the ABM is a θ-transformation;therefore, an ABM can simulate any distribution. We discuss how to convert an ABM into a Deep Neural Network. Finally, by establishing the equivalence between an ABM and the Deep Neural Network, we prove that the Deep Neural Network is complete.展开更多
This paper proposes a hybrid Bayesian Network(BN)method for short-term forecasting of crude oil prices.The method performed is a hybrid,based on both the aspects of classification of influencing factors as well as the...This paper proposes a hybrid Bayesian Network(BN)method for short-term forecasting of crude oil prices.The method performed is a hybrid,based on both the aspects of classification of influencing factors as well as the regression of the out-ofsample values.For the sake of performance comparison,several other hybrid methods have also been devised using the methods of Markov Chain Monte Carlo(MCMC),Random Forest(RF),Support Vector Machine(SVM),neural networks(NNET)and generalized autoregressive conditional heteroskedasticity(GARCH).The hybrid methodology is primarily reliant upon constructing the crude oil price forecast from the summation of its Intrinsic Mode Functions(IMF)and its residue,extracted by an Empirical Mode Decomposition(EMD)of the original crude price signal.The Volatility Index(VIX)as well as the Implied Oil Volatility Index(OVX)has been considered among the influencing parameters of the crude price forecast.The final set of influencing parameters were selected as the whole set of significant contributors detected by the methods of Bayesian Network,Quantile Regression with Lasso penalty(QRL),Bayesian Lasso(BLasso)and the Bayesian Ridge Regression(BRR).The performance of the proposed hybrid-BN method is reported for the three crude price benchmarks:West Texas Intermediate,Brent Crude and the OPEC Reference Basket.展开更多
基金Project supported by the National Natural Science Foundation of China(No.71573184)the National Key Scientific Instrument and Equipment Development Project(No.2013YQ490879)the Special Program of Office of China Air Traffic Control Commission(No.GKG201403004)
文摘Traditional methods for plan path prediction have low accuracy and stability. In this paper, we propose a novel approach for plan path prediction based on relative motion between positions(RMBP) by mining historical flight trajectories. A probability statistical model is introduced to model the stochastic factors during the whole flight process. The model object is the sequence of velocity vectors in the three-dimensional Earth space. First, we model the moving trend of aircraft including the speed(constant, acceleration, or deceleration), yaw(left, right, or straight), and pitch(climb, descent, or cruise) using a hidden Markov model(HMM) under the restrictions of aircraft performance parameters. Then, several Gaussian mixture models(GMMs) are used to describe the conditional distribution of each moving trend. Once the models are built, machine learning algorithms are applied to obtain the optimal parameters of the model from the historical training data. After completing the learning process, the velocity vector sequence of the flight is predicted by the proposed model under the Bayesian framework, so that we can use kinematic equations, depending on the moving patterns, to calculate the flight position at every radar acquisition cycle. To obtain higher prediction accuracy, a uniform interpolation method is used to correct the predicted position each second. Finally, a plan trajectory is concatenated by the predicted discrete points. Results of simulations with collected data demonstrate that this approach not only fulfils the goals of traditional methods, such as the prediction of fly-over time and altitude of waypoints along the planned route, but also can be used to plan a complete path for an aircraft with high accuracy. Experiments are conducted to demonstrate the superiority of this approach to some existing methods.
文摘Winding is an important part of the electrical machine and plays a key role in reliability.In this paper,the reliability of multiphase winding structure in permanent magnet machines is evaluated based on the Markov model.The mean time to failure is used to compare the reliability of different windings structure.The mean time to failure of multiphase winding is derived in terms of the underlying parameters.The mean time to failure of winding is affected by the number of phases,the winding failure rate,the fault-tolerant mechanism success probability,and the state transition success probability.The influence of the phase number,winding distribution types,multi three-phase structure,and fault-tolerant mechanism success probability on the winding reliability is investigated.The results of reliability analysis lay the foundation for the reliability design of permanent magnet machines.
文摘Deep reinforcement learning (deep RL) has the potential to replace classic robotic controllers. State-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient and Soft Actor-Critic Reinforcement Algorithms, to mention a few, have been investigated for training robots to walk. However, conflicting performance results of these algorithms have been reported in the literature. In this work, we present the performance analysis of the above three state-of-the-art Deep Reinforcement algorithms for a constant velocity walking task on a quadruped. The performance is analyzed by simulating the walking task of a quadruped equipped with a range of sensors present on a physical quadruped robot. Simulations of the three algorithms across a range of sensor inputs and with domain randomization are performed. The strengths and weaknesses of each algorithm for the given task are discussed. We also identify a set of sensors that contribute to the best performance of each Deep Reinforcement algorithm.
文摘Technological advances,innovation and the new industry 4.0 paradigm guide Distribution System Operators towards a competitive market that requires the articulation of flexible demand response systems.The lack of measurement and standardization systems in the industry process chain in developing countries prevents the penetration of demand management models,generating inefficiency in the analysis and processing of informa-tion to validate the flexibility potential that large consumers can contribute to the network operator.In this sense,the research uses as input variables the energy and power of the load profile provided by the utility energy meter to obtain the disaggregated forecast in quarter-hour intervals in 4-time windows validated through metrics and its results evaluated by the RMS error to get the total error generated by the methodology with the appli-cation of Machine Learning and Big Data techniques in the Python computational tool through Combinatorial Disaggregation Optimization and Factorial Hidden Markov models.
基金partly supported by National Key R&D Program of China(No.2018YFA0306701)the Australian Research Council(Nos.DP160101652 and DP180100691)+1 种基金National Natural Science Foundation of China(No.61832015)the Key Research Program of Frontier Sciences,Chinese Academy of Sciences。
文摘Markov decision process(MDP)offers a general framework for modelling sequential decision making where outcomes are random.In particular,it serves as a mathematical framework for reinforcement learning.This paper introduces an extension of MDP,namely quantum MDP(q MDP),that can serve as a mathematical model of decision making about quantum systems.We develop dynamic programming algorithms for policy evaluation and finding optimal policies for q MDPs in the case of finite-horizon.The results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.
文摘In this paper, we introduce the concepts of square neurons, power neu-rons, and new learning algorithms based on square neurons, and power neurons. First, we briefly review the basic idea of the Boltzmann Machine, specifically that the invariant distributions of the Boltzmann Machine generate Markov chains. We further review ABM (Attrasoft Boltzmann Machine). Next, we review the θ-transformation and its completeness, i.e. any function can be expanded by θ-transformation. The invariant distribution of the ABM is a θ-transformation;therefore, an ABM can simulate any distribution. We review the linear neurons and the associated learning algorithm. We then discuss the problems of the exponential neurons used in ABM, which are unstable, and the problems of the linear neurons, which do not discriminate the wrong answers from the right answers as sharply as the exponential neurons. Finally, we introduce the concept of square neurons and power neurons. We also discuss the advantages of the learning algorithms based on square neurons and power neurons, which have the stability of the linear neurons and the sharp discrimination of the exponential neurons.
文摘Hornik, Stinchcombe & White have shown that the multilayer feed forward networks with enough hidden layers are universal approximators. Roux & Bengio have proved that adding hidden units yield a strictly improved modeling power, and Restricted Boltzmann Machines (RBM) are universal approximators of discrete distributions. In this paper, we provide yet another proof. The advantage of this new proof is that it will lead to several new learning algorithms. We prove that the Deep Neural Networks implement an expansion and the expansion is complete. First, we briefly review the basic Boltzmann Machine and that the invariant distributions of the Boltzmann Machine generate Markov chains. We then review the θ-transformation and its completeness, i.e. any function can be expanded by θ-transformation. We further review ABM (Attrasoft Boltzmann Machine). The invariant distribution of the ABM is a θ-transformation;therefore, an ABM can simulate any distribution. We discuss how to convert an ABM into a Deep Neural Network. Finally, by establishing the equivalence between an ABM and the Deep Neural Network, we prove that the Deep Neural Network is complete.
文摘This paper proposes a hybrid Bayesian Network(BN)method for short-term forecasting of crude oil prices.The method performed is a hybrid,based on both the aspects of classification of influencing factors as well as the regression of the out-ofsample values.For the sake of performance comparison,several other hybrid methods have also been devised using the methods of Markov Chain Monte Carlo(MCMC),Random Forest(RF),Support Vector Machine(SVM),neural networks(NNET)and generalized autoregressive conditional heteroskedasticity(GARCH).The hybrid methodology is primarily reliant upon constructing the crude oil price forecast from the summation of its Intrinsic Mode Functions(IMF)and its residue,extracted by an Empirical Mode Decomposition(EMD)of the original crude price signal.The Volatility Index(VIX)as well as the Implied Oil Volatility Index(OVX)has been considered among the influencing parameters of the crude price forecast.The final set of influencing parameters were selected as the whole set of significant contributors detected by the methods of Bayesian Network,Quantile Regression with Lasso penalty(QRL),Bayesian Lasso(BLasso)and the Bayesian Ridge Regression(BRR).The performance of the proposed hybrid-BN method is reported for the three crude price benchmarks:West Texas Intermediate,Brent Crude and the OPEC Reference Basket.
