Methanol-to-olefins,as a promising non-oil pathway for the synthesis of light olefins,has been successfully industrialized.The accurate prediction of process variables can yield significant benefits for advanced proce...Methanol-to-olefins,as a promising non-oil pathway for the synthesis of light olefins,has been successfully industrialized.The accurate prediction of process variables can yield significant benefits for advanced process control and optimization.The challenge of this task is underscored by the failure of traditional methods in capturing the complex characteristics of industrial processes,such as high nonlinearities,dynamics,and data distribution shift caused by diverse operating conditions.In this paper,we propose a novel hybrid spatial-temporal deep learning prediction model to address these issues.Firstly,a unique data normalization technique called reversible instance normalization is employed to solve the problem of different data distributions.Subsequently,convolutional neural network integrated with the self-attention mechanism are utilized to extract the temporal patterns.Meanwhile,a multi-graph convolutional network is leveraged to model the spatial interactions.Afterward,the extracted temporal and spatial features are fused as input into a fully connected neural network to complete the prediction.Finally,the outputs are denormalized to obtain the ultimate results.The monitoring results of the dynamic trends of process variables in an actual industrial methanol-to-olefins process demonstrate that our model not only achieves superior prediction performance but also can reveal complex spatial-temporal relationships using the learned attention matrices and adjacency matrices,making the model more interpretable.Lastly,this model is deployed onto an end-to-end Industrial Internet Platform,which achieves effective practical results.展开更多
Effects of some important structural parameters,i.e.slat pitch,and layout position,on dynamic forces acting on the baffles were examined in the fluidized bed of FCC particles operating under different superficial gas ...Effects of some important structural parameters,i.e.slat pitch,and layout position,on dynamic forces acting on the baffles were examined in the fluidized bed of FCC particles operating under different superficial gas velocities.The experimental baffles were made of multiple inclined slats.We found that the forces acting on the baffles decreased significantly with reducing pitch between the slats.For the baffles with a small slat pitch,the forces acting on the baffles increased slightly and then decreased with increasing superficial gas velocity,which is very different from the measured results of a single slat or tube immersed in fluidized beds.The different results are greatly related to the appearance of the“gas cushion”beneath the baffles,whose height increases with increasing superficial gas velocity.On the other hand,a region with stronger particle circulation induced by the inclined slat array was observed in the experiments.The slat near the wall and located below the region of downward-flowing particles was found to be subjected to the severest forces.Therefore,the slats located in similar locations of industrial baffles are suggested to be reinforced to increase their structural strength.展开更多
基金the National Natural Science Foundation of China(Grant No.21991093)the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDA29050200)+1 种基金the Dalian Institute of Chemical Physics(DICP I202135)the Energy Science and Technology Revolution Project(Grant No.E2010412).
文摘Methanol-to-olefins,as a promising non-oil pathway for the synthesis of light olefins,has been successfully industrialized.The accurate prediction of process variables can yield significant benefits for advanced process control and optimization.The challenge of this task is underscored by the failure of traditional methods in capturing the complex characteristics of industrial processes,such as high nonlinearities,dynamics,and data distribution shift caused by diverse operating conditions.In this paper,we propose a novel hybrid spatial-temporal deep learning prediction model to address these issues.Firstly,a unique data normalization technique called reversible instance normalization is employed to solve the problem of different data distributions.Subsequently,convolutional neural network integrated with the self-attention mechanism are utilized to extract the temporal patterns.Meanwhile,a multi-graph convolutional network is leveraged to model the spatial interactions.Afterward,the extracted temporal and spatial features are fused as input into a fully connected neural network to complete the prediction.Finally,the outputs are denormalized to obtain the ultimate results.The monitoring results of the dynamic trends of process variables in an actual industrial methanol-to-olefins process demonstrate that our model not only achieves superior prediction performance but also can reveal complex spatial-temporal relationships using the learned attention matrices and adjacency matrices,making the model more interpretable.Lastly,this model is deployed onto an end-to-end Industrial Internet Platform,which achieves effective practical results.
基金supports by the National Natural Science Foundation of China(grant No.21276273)the Ministry of Science and Technology of China(grant No.2012CB215004)the Science Foundation of China University of Petroleum,Beijing(grant No.2462015YQ0312).
文摘Effects of some important structural parameters,i.e.slat pitch,and layout position,on dynamic forces acting on the baffles were examined in the fluidized bed of FCC particles operating under different superficial gas velocities.The experimental baffles were made of multiple inclined slats.We found that the forces acting on the baffles decreased significantly with reducing pitch between the slats.For the baffles with a small slat pitch,the forces acting on the baffles increased slightly and then decreased with increasing superficial gas velocity,which is very different from the measured results of a single slat or tube immersed in fluidized beds.The different results are greatly related to the appearance of the“gas cushion”beneath the baffles,whose height increases with increasing superficial gas velocity.On the other hand,a region with stronger particle circulation induced by the inclined slat array was observed in the experiments.The slat near the wall and located below the region of downward-flowing particles was found to be subjected to the severest forces.Therefore,the slats located in similar locations of industrial baffles are suggested to be reinforced to increase their structural strength.