Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications.However,the various working conditions would degrade the diagnostic performance and m...Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications.However,the various working conditions would degrade the diagnostic performance and make gear fault diagnosis(GFD)more and more challenging.In this paper,a novel model parameter transfer(NMPT)is proposed to boost the performance of GFD under varying working conditions.Based on the previous transfer strategy that controls empirical risk of source domain,this method further integrates the superiorities of multi-task learning with the idea of transfer learning(TL)to acquire transferable knowledge by minimizing the discrepancies of separating hyperplanes between one specific working condition(target domain)and another(source domain),and then transferring both commonality and specialty parameters over tasks to make use of source domain samples to assist target GFD task when sufficient labeled samples from target domain are unavailable.For NMPT implementation,insufficient target domain features and abundant source domain features with supervised information are fed into NMPT model to train a robust classifier for target GFD task.Related experiments prove that NMPT is expected to be a valuable technology to boost practical GFD performance under various working conditions.The proposed methods provides a transfer learning-based framework to handle the problem of insufficient training samples in target task caused by variable operation conditions.展开更多
The accurate prediction of photovoltaic(PV)power generation is an important basis for hybrid grid scheduling.With the expansion of the scale of PV power plants and the popularization of distributed PV,this study propo...The accurate prediction of photovoltaic(PV)power generation is an important basis for hybrid grid scheduling.With the expansion of the scale of PV power plants and the popularization of distributed PV,this study proposes a multilayer PV power generation prediction model based on transfer learning to solve the problems of the lack of data on new PV bases and the low accuracy of PV power generation prediction.The proposed model,called DRAM,concatenates a dilated convolutional neural network(DCNN)module with a bidirectional long short-term memory(BiLSTM)module,and integrates an attention mechanism.First,the processed data are input into the DCNN layer,and the dilation convolution mechanism captures the spatial features of the wide sensory field of the input data.Subsequently,the temporal characteristics between the features are extracted in the BiLSTM layer.Finally,an attention mechanism is used to strengthen the key features by assigning weights to efficiently construct the relationship between the features and output variables.In addition,the power prediction accuracy of the new PV sites was improved by transferring the pre-trained model parameters to the new PV site prediction model.In this study,the pre-training of models using data from different source domains and the correlations between these pre-trained models and the target domain were analyzed.展开更多
Knowledge of the oxygen mass transfer of aerators under operational conditions in a full-scale wastewater treatment plant （WWTP） is meaningful for the optimization of WWTP, however, scarce to best of our knowledge. ...Knowledge of the oxygen mass transfer of aerators under operational conditions in a full-scale wastewater treatment plant （WWTP） is meaningful for the optimization of WWTP, however, scarce to best of our knowledge. Through analyzing a plug flow aeration tank in the Lucun WWTP, in Wuxi, China, the oxygenation capacity of fine-bubble aerators under process conditions have been measured in- situ using the off-gas method and the non-steady-state method. The off-gas method demonstrated that the aerators in different corridors in the aeration tank of WWTP had significantly different oxygen transfer performance; furthermore, the aerators in the same corridor shared almost equal oxygen transfer performance over the course of a day. Results measured by the two methods showed that the oxygen transfer performance of fine-bubble aerators in the aeration tank decreased dramatically compared with that in the clean water. The loss of oxygen transfer coefficient was over 50% under low-aeration conditions （aeration amount 〈 0.67 Nm 3 /hr）. However, as the aeration amount reached 0.96 Nm 3 /hr, the discrepancy of oxygen transfer between the process condition and clean water was negligible. The analysis also indicated that the non-steady-state and off-gas methods resulted in comparable estimates of oxygen transfer parameters for the aerators under process conditions.展开更多
In this paper,we propose a parameterization transfer algorithm for planar domains bounded by B-spline curves,where the shapes of the planar domains are similar.The domain geometries are considered to be similar if the...In this paper,we propose a parameterization transfer algorithm for planar domains bounded by B-spline curves,where the shapes of the planar domains are similar.The domain geometries are considered to be similar if their simplified skeletons have the same structures.One domain we call source domain,and it is parameterized using multi-patch B-spline surfaces.The resulting parameterization is C1 continuous in the regular region and G1 continuous around singular points regardless of whether the parameterization of the source domain is C1/G1 continuous or not.In this algorithm,boundary control points of the source domain are extracted from its parameterization as sequential points,and we establish a correspondence between sequential boundary control points of the source domain and the target boundary through discrete sampling and fitting.Transfer of the parametrization satisfies C1/G1 continuity under discrete harmonic mapping with continuous constraints.The new algorithm has a lower calculation cost than a decomposition-based parameterization with a high-quality parameterization result.We demonstrate that the result of the parameterization transfer in this paper can be applied in isogeometric analysis.Moreover,because of the consistency of the parameterization for the two models,this method can be applied in many other geometry processing algorithms,such as morphing and deformation.展开更多
A single potential step chronoabsorptometric method for the determination of ki- netic parameters of simple quasi-reversible reactions is described.It is verified by determining the kinetic parameters for the electror...A single potential step chronoabsorptometric method for the determination of ki- netic parameters of simple quasi-reversible reactions is described.It is verified by determining the kinetic parameters for the electroreduction of ferricyanide.A long-optical-path electro- chemical cell with a plug-in electrode is used.The thickness of solution layer is 0.55 mm展开更多
Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention recently.However,with the increasi...Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention recently.However,with the increasing volume of visual-language pre-training model parameters,direct transfer learning consumes a substantial amount of computational and storage resources.Moreover,recently proposed parameter-efficient transfer learning methods mainly focus on the reconstruction of channel features,ignoring the spatial features which are vital for modeling key entity relationships.To address these issues,we design an efficient transfer learning framework for RSCIR,which is based on spatial feature efficient reconstruction(SPER).A concise and efficient spatial adapter is introduced to enhance the extraction of spatial relationships.The spatial adapter is able to spatially reconstruct the features in the backbone with few parameters while incorporating the prior information from the channel dimension.We conduct quantitative and qualitative experiments on two different commonly used RSCIR datasets.Compared with traditional methods,our approach achieves an improvement of 3%-11% in sumR metric.Compared with methods finetuning all parameters,our proposed method only trains less than 1% of the parameters,while maintaining an overall performance of about 96%.展开更多
The objective of this study is to predict grain size and heat transfer coefficient at the metal-die interface during high pressure die casting process and solidification of the magnesium alloy AM60. Multiple runs of t...The objective of this study is to predict grain size and heat transfer coefficient at the metal-die interface during high pressure die casting process and solidification of the magnesium alloy AM60. Multiple runs of the commercial casting simulation package, ProCASTTM, were used to model the mold filling and solidification events employing a range of interfacial heat transfer coefficient values. The simulation results were used to estimate the centerline cooling curve at various locations through the casting. The centerline cooling curves, together with the die temperature and the thermodynamic properties of the alloy, were then used as inputs to compute the solution to the Stefan problem of a moving phase boundary, thereby providing the through-thickness cooling curves at each chosen location of the casting, Finally, the local cooling rate was used to calculate the resulting grain size via previously established relationships. The effects of die temperature, filling time and heat transfer coefficient on the grain structure in skin region and core region were quantitatively characterized. It was observed that the grain size of skin region strongly depends on above three factors whereas the grain size of core region shows dependence on the interracial heat transfer coefficient and thickness of the samples. The grain size distribution from surface to center was estimated from the relationship between grain size and the predicted cooling rate. The prediction of grain size matches well with experimental results. A comparison of the predicted and experimentally determined grain size profiles enables the determination of the apparent interracial heat transfer coefficient for different locations.展开更多
This paper implemented cooling configuration design on certain gas turbine HP rotor using parameterized method.It is convenient for complicated gas turbine blade modeling using parameters and also benefit for the geom...This paper implemented cooling configuration design on certain gas turbine HP rotor using parameterized method.It is convenient for complicated gas turbine blade modeling using parameters and also benefit for the geometry modify in later period.Parameterized modeling is the foundation of air cooling turbine blade design method engineering application.Mesh quality can be awarded when generated complicated cooling configuration blade grids,and also the increase of calculation error can arise by many mesh blocks.Film cooling and serpentine passage can effectively enhance the cooling effectiveness and protect blade.展开更多
基金Supported by National Natural Science Foundation of China(Grant No.51835009).
文摘Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications.However,the various working conditions would degrade the diagnostic performance and make gear fault diagnosis(GFD)more and more challenging.In this paper,a novel model parameter transfer(NMPT)is proposed to boost the performance of GFD under varying working conditions.Based on the previous transfer strategy that controls empirical risk of source domain,this method further integrates the superiorities of multi-task learning with the idea of transfer learning(TL)to acquire transferable knowledge by minimizing the discrepancies of separating hyperplanes between one specific working condition(target domain)and another(source domain),and then transferring both commonality and specialty parameters over tasks to make use of source domain samples to assist target GFD task when sufficient labeled samples from target domain are unavailable.For NMPT implementation,insufficient target domain features and abundant source domain features with supervised information are fed into NMPT model to train a robust classifier for target GFD task.Related experiments prove that NMPT is expected to be a valuable technology to boost practical GFD performance under various working conditions.The proposed methods provides a transfer learning-based framework to handle the problem of insufficient training samples in target task caused by variable operation conditions.
基金Science and Technology Project of State Grid Ningxia Electric Power Co.,Ltd Research on Distributed Photovoltaic Fine Power Prediction Technology for Day-Ahead Scheduling,5229NX230007.
文摘The accurate prediction of photovoltaic(PV)power generation is an important basis for hybrid grid scheduling.With the expansion of the scale of PV power plants and the popularization of distributed PV,this study proposes a multilayer PV power generation prediction model based on transfer learning to solve the problems of the lack of data on new PV bases and the low accuracy of PV power generation prediction.The proposed model,called DRAM,concatenates a dilated convolutional neural network(DCNN)module with a bidirectional long short-term memory(BiLSTM)module,and integrates an attention mechanism.First,the processed data are input into the DCNN layer,and the dilation convolution mechanism captures the spatial features of the wide sensory field of the input data.Subsequently,the temporal characteristics between the features are extracted in the BiLSTM layer.Finally,an attention mechanism is used to strengthen the key features by assigning weights to efficiently construct the relationship between the features and output variables.In addition,the power prediction accuracy of the new PV sites was improved by transferring the pre-trained model parameters to the new PV site prediction model.In this study,the pre-training of models using data from different source domains and the correlations between these pre-trained models and the target domain were analyzed.
基金supported by the Major Water Project of the National Science and Technology (No.2011ZX07319-001-004, 2011ZX07301-002)
文摘Knowledge of the oxygen mass transfer of aerators under operational conditions in a full-scale wastewater treatment plant （WWTP） is meaningful for the optimization of WWTP, however, scarce to best of our knowledge. Through analyzing a plug flow aeration tank in the Lucun WWTP, in Wuxi, China, the oxygenation capacity of fine-bubble aerators under process conditions have been measured in- situ using the off-gas method and the non-steady-state method. The off-gas method demonstrated that the aerators in different corridors in the aeration tank of WWTP had significantly different oxygen transfer performance; furthermore, the aerators in the same corridor shared almost equal oxygen transfer performance over the course of a day. Results measured by the two methods showed that the oxygen transfer performance of fine-bubble aerators in the aeration tank decreased dramatically compared with that in the clean water. The loss of oxygen transfer coefficient was over 50% under low-aeration conditions （aeration amount 〈 0.67 Nm 3 /hr）. However, as the aeration amount reached 0.96 Nm 3 /hr, the discrepancy of oxygen transfer between the process condition and clean water was negligible. The analysis also indicated that the non-steady-state and off-gas methods resulted in comparable estimates of oxygen transfer parameters for the aerators under process conditions.
基金supported by the National Natural Science Foundation of China(Grant Nos.62072148 and U22A2033)the National Key R&D Program of China(Grant Nos.2022YFB3303000 and 2020YFB1709402)+2 种基金the Zhejiang Provincial Science and Technology Program in China(Grant No.2021C01108)the NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization(Grant No.U1909210)the Fundamental Research Funds for the Provincial Universities of Zhejiang(Grant No.490 GK219909299001-028).
文摘In this paper,we propose a parameterization transfer algorithm for planar domains bounded by B-spline curves,where the shapes of the planar domains are similar.The domain geometries are considered to be similar if their simplified skeletons have the same structures.One domain we call source domain,and it is parameterized using multi-patch B-spline surfaces.The resulting parameterization is C1 continuous in the regular region and G1 continuous around singular points regardless of whether the parameterization of the source domain is C1/G1 continuous or not.In this algorithm,boundary control points of the source domain are extracted from its parameterization as sequential points,and we establish a correspondence between sequential boundary control points of the source domain and the target boundary through discrete sampling and fitting.Transfer of the parametrization satisfies C1/G1 continuity under discrete harmonic mapping with continuous constraints.The new algorithm has a lower calculation cost than a decomposition-based parameterization with a high-quality parameterization result.We demonstrate that the result of the parameterization transfer in this paper can be applied in isogeometric analysis.Moreover,because of the consistency of the parameterization for the two models,this method can be applied in many other geometry processing algorithms,such as morphing and deformation.
文摘A single potential step chronoabsorptometric method for the determination of ki- netic parameters of simple quasi-reversible reactions is described.It is verified by determining the kinetic parameters for the electroreduction of ferricyanide.A long-optical-path electro- chemical cell with a plug-in electrode is used.The thickness of solution layer is 0.55 mm
基金supported by the National Key R&D Program of China(No.2022ZD0118402)。
文摘Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention recently.However,with the increasing volume of visual-language pre-training model parameters,direct transfer learning consumes a substantial amount of computational and storage resources.Moreover,recently proposed parameter-efficient transfer learning methods mainly focus on the reconstruction of channel features,ignoring the spatial features which are vital for modeling key entity relationships.To address these issues,we design an efficient transfer learning framework for RSCIR,which is based on spatial feature efficient reconstruction(SPER).A concise and efficient spatial adapter is introduced to enhance the extraction of spatial relationships.The spatial adapter is able to spatially reconstruct the features in the backbone with few parameters while incorporating the prior information from the channel dimension.We conduct quantitative and qualitative experiments on two different commonly used RSCIR datasets.Compared with traditional methods,our approach achieves an improvement of 3%-11% in sumR metric.Compared with methods finetuning all parameters,our proposed method only trains less than 1% of the parameters,while maintaining an overall performance of about 96%.
基金jointly supported by Canadian Network for Research and Innovation in Machining TechnologyNatural Sciences and Engineering Research Council of Canada-Automotive Partnership Canada programNRCan’s Office of Energy R&D through the Program on Energy R&D
文摘The objective of this study is to predict grain size and heat transfer coefficient at the metal-die interface during high pressure die casting process and solidification of the magnesium alloy AM60. Multiple runs of the commercial casting simulation package, ProCASTTM, were used to model the mold filling and solidification events employing a range of interfacial heat transfer coefficient values. The simulation results were used to estimate the centerline cooling curve at various locations through the casting. The centerline cooling curves, together with the die temperature and the thermodynamic properties of the alloy, were then used as inputs to compute the solution to the Stefan problem of a moving phase boundary, thereby providing the through-thickness cooling curves at each chosen location of the casting, Finally, the local cooling rate was used to calculate the resulting grain size via previously established relationships. The effects of die temperature, filling time and heat transfer coefficient on the grain structure in skin region and core region were quantitatively characterized. It was observed that the grain size of skin region strongly depends on above three factors whereas the grain size of core region shows dependence on the interracial heat transfer coefficient and thickness of the samples. The grain size distribution from surface to center was estimated from the relationship between grain size and the predicted cooling rate. The prediction of grain size matches well with experimental results. A comparison of the predicted and experimentally determined grain size profiles enables the determination of the apparent interracial heat transfer coefficient for different locations.
基金Sponsored by the National Natural Science Foundation of China(Grant No. 50476028)
文摘This paper implemented cooling configuration design on certain gas turbine HP rotor using parameterized method.It is convenient for complicated gas turbine blade modeling using parameters and also benefit for the geometry modify in later period.Parameterized modeling is the foundation of air cooling turbine blade design method engineering application.Mesh quality can be awarded when generated complicated cooling configuration blade grids,and also the increase of calculation error can arise by many mesh blocks.Film cooling and serpentine passage can effectively enhance the cooling effectiveness and protect blade.
