【摘 要】
:
Operating at different operation steps,process variable correlations of batch processes present the typical multiphase and transition characteristics.The existing phase partition algorithms have sever
【机 构】
:
State Key Laboratory of Industrial Control Technology,Department of Control Science and Engineering,
论文部分内容阅读
Operating at different operation steps,process variable correlations of batch processes present the typical multiphase and transition characteristics.The existing phase partition algorithms have several disadvantages,such as time sequence disorder,missing monitoring performance,unavailable quantitative index indicating transition patterns,and dependence on process prior knowledge.In particular,identification of transition patterns do not have the related theory support.To effectively overcome these problems,in this work,a self-optimization sequential phase partition and transition identification(SSPTI)algorithm is proposed.Combining process variable correlations,influence degree on monitoring performance are self-optimized for phase partition without key parameters and prior process knowledge.Moreover,a quantitative index based on density and distance from the perspective of clustering analysis is further defined to indicate transition patterns.
其他文献
In the process industries,local linearization of a nonlinear process,which is essentially modeling of the process dynamics at a specific operating point with a simplified linear model,is commonly used
In this paper,a deep learning model referred as NARX-DNN based on Deep Neural Network(DNN)and Nonlinear Auto Regressive with Extension X input(NARX)neural network is developed to model the coal-fired
This paper proposes a new predictive control scheme for the high-speed electric multiple unit(EMU),by establishing multiple distributed state-space model for each power unit based on the subspace mode
T-S fuzzy inverse model identification based on particle swarm optimization(PSO)algorithm is proposed for a class of nonlinear process,and it is applied to direct adaptive inverse control of nonlinear
This paper addresses the problem of disturbance attenuation and rejection for discrete-time Markovian jump systems with lossy measurements and multiple disturbances.The measurement transmission from t
Frequency spectral features of mechanical vibration and acoustic signals relate to difficult-to-measure product quality and quantity parameters of complex industrial process.Selective ensemble(SEN)mod
Cognitive radio(CR)needs to aware the surroundings and adapts the transmission parameters to the environment.One key problem of CRis to understand the multi-dimension and multi-scale characteristics o
This paper puts forward a novel energy management method aiming at reducing energy cost,pollution emission and peak load in the micro-grid.According to a certain Shanghai Sci-tech Parks microgrid,this
The inverse relationship between train mechanical energy consumption and trip time is proved by infinitesimal increment analysis of train speed profile.Firstly,a general optimal model for train drivin
Moving window local outlier probability(MWLoOP)is an outlier detecting method which was proposed for monitoring time-varying industrial processes; however,for the practical industrial processes,beside