This paper establishes the prediction model of low cycle fatigue damage of steam turbine rotor using the rich data from finite element analysis. In order to monitor the damage, a multiple regression analysis of input ...
详细信息
This paper establishes the prediction model of low cycle fatigue damage of steam turbine rotor using the rich data from finite element analysis. In order to monitor the damage, a multiple regression analysis of input data/output data with high correlation is made via dynamic PLS. The variation of the process parameters is extracted and it restrains the multiple dependency of the several parameters in different time series. Finally, a simulation of rolling process of a domestic 300MW turbine unit validates the effectiveness and accuracy of the prediction model based on dynamic PLS.
In the combustion system and ash fouling system of boiler,the furnace exit gas temperature(FEGT)is the key parameter for ensuring high *** it is hard to achieve satisfactory performance through conventional control st...
详细信息
In the combustion system and ash fouling system of boiler,the furnace exit gas temperature(FEGT)is the key parameter for ensuring high *** it is hard to achieve satisfactory performance through conventional control strategy,the control problem of FEGT has become critical and significant in coal-fired boiler *** this paper,a new predictive control scheme based on particle swarm optimization(PSO)and CM-LSSVM-PLS model is *** the proposed control scheme,a new CM-LSSVM-PLS method is proposed and used as the predictive model to predict the future *** the process of CM-LSSVM-PLS method,c-means cluster(CM)algorithm is used to partition the training data into several different subsets by considering the characteristics of operational *** sub-models are subsequently developed in the individual subsets based on least squares support vector machine(LSSVM).Then,partial least squares algorithm(PLS)is employed as the combination ***,PSO is used as the receding optimization *** proposed control is verified through operation data of a 300MW generating *** simulation results show that the effectiveness of our proposed control scheme.
In recent years, more and more plug-in hybrid electric vehicles (PHEVs) have been put to use in smart grid. In this paper, we consider a dynamic aggregator-PHEV system, where the aggregator convinces the PHEVs to use ...
详细信息
In recent years, more and more plug-in hybrid electric vehicles (PHEVs) have been put to use in smart grid. In this paper, we consider a dynamic aggregator-PHEV system, where the aggregator convinces the PHEVs to use electricity rather than gas by setting an appropriate charging price dynamically. We propose a payoff-maximizing algorithm for the aggregator to decide not only the charging price but also the electricity amount purchased from real-time power market based on Lyapunov optimization. Furthermore, we transform the power purchase problem into the energy allocation problem among all the PHEVs. The proposed algorithm operates in real time and does not require any prior knowledge of the statistical information of the system. Theoretically, we demonstrate the proposed algorithm can guarantee system stability and achieve a result that is away from the optimum by O(1/V ), where V is a control parameter. The effectiveness and robustness of the algorithm is validated through simulation results.
The increasing demands on the indoor location service inspire the wide attentions to investigate the indoor position algorithms. Access point(AP) selection is critical important for increasing the estimation accuracy ...
详细信息
The increasing demands on the indoor location service inspire the wide attentions to investigate the indoor position algorithms. Access point(AP) selection is critical important for increasing the estimation accuracy of the indoor location. In this paper, the key features in influencing the accuracy of indoor location systems are investigated. Base on the analysis results, we present an AP selection strategy for indoor location by proposing a novel AP selection index for test point. By using the experiment data, the K-Nearest Neighbor(KNN) and weighted-KNN(WKNN) indoor location methods are carried out to illustrate the performance proposed AP selection strategy. The performance of our AP selection strategy is validated by comparing with the exhaustive AP selection strategy, the fisher AP selection strategy and the largest RSSI strength AP selection strategy. The experiment results show that the proposed AP selection strategy can improve the location accuracy of indoor location with Wi-Fi.
This paper mainly studies the hourly water demand forecasting performances of water supply system in shanghai with LS-SVM. The teaching-learning-based optimization(TLBO) is adopted to adjust the hyper-parameters of le...
详细信息
This paper mainly studies the hourly water demand forecasting performances of water supply system in shanghai with LS-SVM. The teaching-learning-based optimization(TLBO) is adopted to adjust the hyper-parameters of least squares support vector machine(LS-SVM).To improve the forecast accuracy, An ameliorated TLBO algorithm called ATLBO is introduced. The experimental results show that the model of water demand forecasting with ATLBO has better regression precision than grid search, particle swarm optimization(PSO) and TLBO.
Monitoring system of furnace ash fouling is the foundation of the soot-blowing operation on furnace *** furnace exit gas temperature(FEGT) is the key parameter in monitoring system,a new CM-LSSVM-PLS method is propose...
详细信息
Monitoring system of furnace ash fouling is the foundation of the soot-blowing operation on furnace *** furnace exit gas temperature(FEGT) is the key parameter in monitoring system,a new CM-LSSVM-PLS method is proposed to predict *** the process of CM-LSSVM-PLS method,considering the characteristics of operational data,c-means(CM) cluster algorithm is used to partition the training data into several different *** are subsequently developed in the individual subsets based on least squares support vector machine(LSSVM).Finally,partial least squares(PLS) algorithm is employed as the combination *** single LSSVM is established to make a comparison with CM-LSSVM-PLS *** proposed model is verified through operation data of a 300 MW generating *** comparison result shows that the new CM-LSSVM-PLS method can predict FEGT accurately while the time consumed in modeling decrease drastically.
Consensus is a fundamental and important problem for cooperative *** paper mainly studies the consensus of networked multi-agent systems with nonlinear couplings via pinning *** adaptive desired weighting consensus pr...
详细信息
ISBN:
(纸本)9781479947249
Consensus is a fundamental and important problem for cooperative *** paper mainly studies the consensus of networked multi-agent systems with nonlinear couplings via pinning *** adaptive desired weighting consensus protocol is proposed to control a small fraction of pinned agents for directed ***,an adaptive controller gain average consensus protocol is presented via the selected pinning agents for weighted directed *** conditions for achieving the desired consensus asymptotically are ***,theoretical results are validated via simulations.
In this paper, we present a new adaptive backstepping control design method to solve the overparametrization problem in parameter estimation. Unlike the existing schemes, the concept of tuning functions is not ***, th...
详细信息
In this paper, we present a new adaptive backstepping control design method to solve the overparametrization problem in parameter estimation. Unlike the existing schemes, the concept of tuning functions is not ***, the number of parameter estimates is reduced to be minimal, which is exactly the same as that of unknown parameters. The parametric strict-feedback system is employed to illustrate our design procedure.
In this work, inspired from this biological motivation that in living cells, the execution time of different biological processes is difficult to know precisely and very sensitive to environmental factors that might b...
详细信息
There are currently several ways of wireless access to support vehicular communication, including vehicular ad-hoc networks (VANETs) and cellular networks (off-the-shelf 3G and LTE). It is necessary to make a seamless...
详细信息
ISBN:
(纸本)9781479944484
There are currently several ways of wireless access to support vehicular communication, including vehicular ad-hoc networks (VANETs) and cellular networks (off-the-shelf 3G and LTE). It is necessary to make a seamless handover decision to guarantee quality of service (QoS) of communications for a vehicle moving in the regions covered by more than one access networks. In this paper, we provide a performance guaranteed optimized handover decision algorithm. With this algorithm, the communication of vehicles can handover through heterogeneous wireless access networks not only to reach overall load balance among all access points, but also to maximize the data rate of the whole networks as well as the vehicles' fairness. In addition, in the process of decision making, the data rate of handover vehicles is estimated. Simulations are performed to demonstrate the efficiency of the proposed algorithm.
暂无评论