Extensional approach vs. intensional approach is taxonomy of tackling uncertainty. In this paper,we compare these two approaches. Extensional systems are computational convenient but semantically sloppy,while intensio...Extensional approach vs. intensional approach is taxonomy of tackling uncertainty. In this paper,we compare these two approaches. Extensional systems are computational convenient but semantically sloppy,while intensional systems are semantically clear but computational clumsy. The trade-off between sematic clarity and computational efficiency has been the main issue of concern.展开更多
In data-driven fault diagnosis for turbo-generator sets,the fault samples are usually expensive to obtain,and inevitably with noise,which will both lead to an unsatisfying identification performance of diagnosis model...In data-driven fault diagnosis for turbo-generator sets,the fault samples are usually expensive to obtain,and inevitably with noise,which will both lead to an unsatisfying identification performance of diagnosis models.To address these issues,this paper proposes a fault diagnosis model for turbo-generator sets based on Weighted Extension Neural Network(W-ENN).WENN is a novel neural network which has three types of connection weights and an improved correlation function.The performance of the proposed model is validated against Extension Neural Network(ENN),Support Vector Machine(SVM),Relevance Vector Machine(RVM)and Extreme Learning Machine(ELM)based models.The results indicate that,on noisy small sample sets,the proposed model is superior to the other models in terms of higher identification accuracy with fewer samples and strong noise-tolerant ability.The findings of this study may serve as a powerful fault diagnosis model for turbo-generator sets on noisy small sample sets.展开更多
Aggregate engineering of non-covalent networks endows supramolecular polymers with thermo-mechanical versatility,stimuli-responsive phase transitions and intrinsic damage-healing capabilities.However,most non-covalent...Aggregate engineering of non-covalent networks endows supramolecular polymers with thermo-mechanical versatility,stimuli-responsive phase transitions and intrinsic damage-healing capabilities.However,most non-covalent networks are vulnerable at elevated temperatures,which suppresses the robustness of supramolecular polymers.Herein,ureidocytosine(UCy)motifs,which are capable of forming extensive non-covalent networks and thus robust molecular aggregates via multivalent hydrogen bonds and aromatic stackings,are proposed to enable precise programming of the thermo-mechanical versatility.Molecular simulations reveal that the enthalpic contributions from the UCy aggregates play dominant roles to compensate the entropic loss from the redistributions of polymeric spacers and stabilize the non-covalent networks over wide temperature windows.Such aggregate-level strategy offers prospects for applications which require thermo-mechanical versatility of supramolecular polymers,such as 3D printing,microfabrication and damage-healing coating.展开更多
文摘Extensional approach vs. intensional approach is taxonomy of tackling uncertainty. In this paper,we compare these two approaches. Extensional systems are computational convenient but semantically sloppy,while intensional systems are semantically clear but computational clumsy. The trade-off between sematic clarity and computational efficiency has been the main issue of concern.
基金the National Natural Science Foundation of China(No.51775272,No.51005114)The Fundamental Research Funds for the Central Universities,China(No.NS2014050)。
文摘In data-driven fault diagnosis for turbo-generator sets,the fault samples are usually expensive to obtain,and inevitably with noise,which will both lead to an unsatisfying identification performance of diagnosis models.To address these issues,this paper proposes a fault diagnosis model for turbo-generator sets based on Weighted Extension Neural Network(W-ENN).WENN is a novel neural network which has three types of connection weights and an improved correlation function.The performance of the proposed model is validated against Extension Neural Network(ENN),Support Vector Machine(SVM),Relevance Vector Machine(RVM)and Extreme Learning Machine(ELM)based models.The results indicate that,on noisy small sample sets,the proposed model is superior to the other models in terms of higher identification accuracy with fewer samples and strong noise-tolerant ability.The findings of this study may serve as a powerful fault diagnosis model for turbo-generator sets on noisy small sample sets.
基金supported by the Research Grant Council of Hong Kong(No.CityU 11305219)City University of Hong Kong(Nos.6000685 and 9610348)Research Grant Council of Hong Kong(No.C1025-14E).
文摘Aggregate engineering of non-covalent networks endows supramolecular polymers with thermo-mechanical versatility,stimuli-responsive phase transitions and intrinsic damage-healing capabilities.However,most non-covalent networks are vulnerable at elevated temperatures,which suppresses the robustness of supramolecular polymers.Herein,ureidocytosine(UCy)motifs,which are capable of forming extensive non-covalent networks and thus robust molecular aggregates via multivalent hydrogen bonds and aromatic stackings,are proposed to enable precise programming of the thermo-mechanical versatility.Molecular simulations reveal that the enthalpic contributions from the UCy aggregates play dominant roles to compensate the entropic loss from the redistributions of polymeric spacers and stabilize the non-covalent networks over wide temperature windows.Such aggregate-level strategy offers prospects for applications which require thermo-mechanical versatility of supramolecular polymers,such as 3D printing,microfabrication and damage-healing coating.
