The flow regimes of GLCC with horizon inlet and a vertical pipe are investigated in experiments,and the velocities and pressure drops data labeled by the corresponding flow regimes are collected.Combined with the flow...The flow regimes of GLCC with horizon inlet and a vertical pipe are investigated in experiments,and the velocities and pressure drops data labeled by the corresponding flow regimes are collected.Combined with the flow regimes data of other GLCC positions from other literatures in existence,the gas and liquid superficial velocities and pressure drops are used as the input of the machine learning algorithms respectively which are applied to identify the flow regimes.The choosing of input data types takes the availability of data for practical industry fields into consideration,and the twelve machine learning algorithms are chosen from the classical and popular algorithms in the area of classification,including the typical ensemble models,SVM,KNN,Bayesian Model and MLP.The results of flow regimes identification show that gas and liquid superficial velocities are the ideal type of input data for the flow regimes identification by machine learning.Most of the ensemble models can identify the flow regimes of GLCC by gas and liquid velocities with the accuracy of 0.99 and more.For the pressure drops as the input of each algorithm,it is not the suitable as gas and liquid velocities,and only XGBoost and Bagging Tree can identify the GLCC flow regimes accurately.The success and confusion of each algorithm are analyzed and explained based on the experimental phenomena of flow regimes evolution processes,the flow regimes map,and the principles of algorithms.The applicability and feasibility of each algorithm according to different types of data for GLCC flow regimes identification are proposed.展开更多
The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this...The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes.展开更多
The flow characteristics of a dual fluidised bed gasifier(DFBG)are more complex than those of a single fluidised bed gasifier.For stable operation and appropriate control,a cold DFBG test facility with both an upper a...The flow characteristics of a dual fluidised bed gasifier(DFBG)are more complex than those of a single fluidised bed gasifier.For stable operation and appropriate control,a cold DFBG test facility with both an upper and a lower U-valve was built,and electrical capacitance tomography(ECT)sensors were installed with pressure transducers to investigate the effects of operating conditions on gas-solids flow hydrodynamics.The operating parameters included gas velocities in the riser and in the bubbling fluidised bed,aeration velocity in the lower U-valve,bed material inventory,and particle size.This is the first time that ECT was applied in different flow zones of a dual fluidised bed gasifier system.The experimental results indicated that ECT in the recycle chamber could monitor the performance of the lower U-valve under different operating conditions for early detection of gas shortcut from the riser to the bubbling bed.Three main flow regimes in the riser and the differences between the reactors were identified by two sets of ECT sensors with pressure transducers.Finally,the effects of the operating conditions on the pressure drop in different parts of the DFBG was investigated.展开更多
Selected milestones in the development and use of electrical tomography in powder conveying, slurry processing and multi-phase flow are highlighted. The ability to map concentration in opaque mixtures under process-re...Selected milestones in the development and use of electrical tomography in powder conveying, slurry processing and multi-phase flow are highlighted. The ability to map concentration in opaque mixtures under process-realistic conditions was a major innovation for the method and has had far reaching implications. Subsequent developments have enabled velocity information to be abstracted resulting in the ability to measure component flux and motion.展开更多
文摘The flow regimes of GLCC with horizon inlet and a vertical pipe are investigated in experiments,and the velocities and pressure drops data labeled by the corresponding flow regimes are collected.Combined with the flow regimes data of other GLCC positions from other literatures in existence,the gas and liquid superficial velocities and pressure drops are used as the input of the machine learning algorithms respectively which are applied to identify the flow regimes.The choosing of input data types takes the availability of data for practical industry fields into consideration,and the twelve machine learning algorithms are chosen from the classical and popular algorithms in the area of classification,including the typical ensemble models,SVM,KNN,Bayesian Model and MLP.The results of flow regimes identification show that gas and liquid superficial velocities are the ideal type of input data for the flow regimes identification by machine learning.Most of the ensemble models can identify the flow regimes of GLCC by gas and liquid velocities with the accuracy of 0.99 and more.For the pressure drops as the input of each algorithm,it is not the suitable as gas and liquid velocities,and only XGBoost and Bagging Tree can identify the GLCC flow regimes accurately.The success and confusion of each algorithm are analyzed and explained based on the experimental phenomena of flow regimes evolution processes,the flow regimes map,and the principles of algorithms.The applicability and feasibility of each algorithm according to different types of data for GLCC flow regimes identification are proposed.
基金Project supported by the National High Technology and Research Development Program Special Fund of China (GrantNo: 2002AA616050).
文摘The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes.
基金This work was funded by the National Natural Science Founda-tion of China(Nos.61771455 and 61811530333)Chinese Academy of Sciences Major International Collaboration Project and the Royal Society Newton Advanced Fellowship(NA170124).
文摘The flow characteristics of a dual fluidised bed gasifier(DFBG)are more complex than those of a single fluidised bed gasifier.For stable operation and appropriate control,a cold DFBG test facility with both an upper and a lower U-valve was built,and electrical capacitance tomography(ECT)sensors were installed with pressure transducers to investigate the effects of operating conditions on gas-solids flow hydrodynamics.The operating parameters included gas velocities in the riser and in the bubbling fluidised bed,aeration velocity in the lower U-valve,bed material inventory,and particle size.This is the first time that ECT was applied in different flow zones of a dual fluidised bed gasifier system.The experimental results indicated that ECT in the recycle chamber could monitor the performance of the lower U-valve under different operating conditions for early detection of gas shortcut from the riser to the bubbling bed.Three main flow regimes in the riser and the differences between the reactors were identified by two sets of ECT sensors with pressure transducers.Finally,the effects of the operating conditions on the pressure drop in different parts of the DFBG was investigated.
基金support of co-workers in the tomography groups at University of Leeds and the University of Manchester with funding to enable us to develop the frontiers of tomography provided by EPSRC (EP/D031257/1)
文摘Selected milestones in the development and use of electrical tomography in powder conveying, slurry processing and multi-phase flow are highlighted. The ability to map concentration in opaque mixtures under process-realistic conditions was a major innovation for the method and has had far reaching implications. Subsequent developments have enabled velocity information to be abstracted resulting in the ability to measure component flux and motion.