Data augmentation is an important task of using existing data to expand data sets.Using generative countermeasure network technology to realize data augmentation has the advantages of high-quality generated samples,si...Data augmentation is an important task of using existing data to expand data sets.Using generative countermeasure network technology to realize data augmentation has the advantages of high-quality generated samples,simple training,and fewer restrictions on the number of generated samples.However,in the field of transmission line insulator images,the freely synthesized samples are prone to produce fuzzy backgrounds and disordered samples of the main insulator features.To solve the above problems,this paper uses the cycle generative adversarial network(Cycle-GAN)used for domain conversion in the generation countermeasure network as the initial framework and uses the self-attention mechanism and channel attention mechanism to assist the conversion to realize the mutual conversion of different insulator samples.The attention module with prior knowledge is used to build the generation countermeasure network,and the generative adversarial network(GAN)model with local controllable generation is built to realize the directional generation of insulator belt defect samples.The experimental results show that the samples obtained by this method are improved in a number of quality indicators,and the quality effect of the samples obtained is excellent,which has a reference value for the data expansion of insulator images.展开更多
Amidst the development of photoelectrochemical(PEC)CO_(2) conversion toward practical application,the production of high-value chemicals beyond C1 compounds under mild conditions is greatly desired yet challenging.Her...Amidst the development of photoelectrochemical(PEC)CO_(2) conversion toward practical application,the production of high-value chemicals beyond C1 compounds under mild conditions is greatly desired yet challenging.Here,through rational PEC device design by combining Au-loaded and N-doped TiO_(2) plate nanoarray photoanode with Zn-doped Cu_(2)O dark cathode,efficient conversion of CO_(2) to CH3COOH has been achieved with an outstanding Faradaic efficiency up to 58.1%(91.5%carbon selectivity)at 0.5 V vs.Ag/AgCl.Temperature programmed desorption and in situ Raman spectra reveal that the Zn-dopant in Cu_(2)O plays multiple roles in selective catalytic CO_(2) conversion,including local electronic structure manipulation and active site modification,which together promote the formation of intermediate*CH2/*CH3 for C-C coupling.Apart from that,it is also unveiled that the sufficient electron density provided by the Au-loaded and N-doped TiO_(2) plate nanoarray photoanode plays an equally important role by initiating multi-electron CO_(2) reduction.This work provides fresh insights into the PEC system design to reach the multi-electron reduction reaction and facilitate the C-C coupling reaction toward high-value multicarbon(C2+)chemical production via CO_(2) conversion.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant No.61973055Fundamental Research Funds for the Central Universities under Grant No.ZYGX2020J011Regional Innovation Cooperation Funds of Sichuan under Grant No.2024YFHZ0089.
文摘Data augmentation is an important task of using existing data to expand data sets.Using generative countermeasure network technology to realize data augmentation has the advantages of high-quality generated samples,simple training,and fewer restrictions on the number of generated samples.However,in the field of transmission line insulator images,the freely synthesized samples are prone to produce fuzzy backgrounds and disordered samples of the main insulator features.To solve the above problems,this paper uses the cycle generative adversarial network(Cycle-GAN)used for domain conversion in the generation countermeasure network as the initial framework and uses the self-attention mechanism and channel attention mechanism to assist the conversion to realize the mutual conversion of different insulator samples.The attention module with prior knowledge is used to build the generation countermeasure network,and the generative adversarial network(GAN)model with local controllable generation is built to realize the directional generation of insulator belt defect samples.The experimental results show that the samples obtained by this method are improved in a number of quality indicators,and the quality effect of the samples obtained is excellent,which has a reference value for the data expansion of insulator images.
基金financially supported in part by the National Key R&D Program of China (2017YFA0207301, and 2017YFA0403402)the National Natural Science Foundation of China (21725102, 91961106, U1832156, 22075267, 21803002, 91963108, 21950410514, and U1732272)+5 种基金CAS Key Research Program of Frontier Sciences (QYZDB-SSW-SLH018)Science and Technological Fund of Anhui Province for Outstanding Youth (2008085 J05)Youth Innovation Promotion Association of CAS (2019444)Young Elite Scientist Sponsorship Program by CAST, China Postdoctoral Science Foundation (2019 M652190, 2020 T130627)Chinese Universities Scientific Fund (WK2060190096), MOST (2018YFA0208603)DNL Cooperation Fund, CAS (DNL201922, DNL180201)
文摘Amidst the development of photoelectrochemical(PEC)CO_(2) conversion toward practical application,the production of high-value chemicals beyond C1 compounds under mild conditions is greatly desired yet challenging.Here,through rational PEC device design by combining Au-loaded and N-doped TiO_(2) plate nanoarray photoanode with Zn-doped Cu_(2)O dark cathode,efficient conversion of CO_(2) to CH3COOH has been achieved with an outstanding Faradaic efficiency up to 58.1%(91.5%carbon selectivity)at 0.5 V vs.Ag/AgCl.Temperature programmed desorption and in situ Raman spectra reveal that the Zn-dopant in Cu_(2)O plays multiple roles in selective catalytic CO_(2) conversion,including local electronic structure manipulation and active site modification,which together promote the formation of intermediate*CH2/*CH3 for C-C coupling.Apart from that,it is also unveiled that the sufficient electron density provided by the Au-loaded and N-doped TiO_(2) plate nanoarray photoanode plays an equally important role by initiating multi-electron CO_(2) reduction.This work provides fresh insights into the PEC system design to reach the multi-electron reduction reaction and facilitate the C-C coupling reaction toward high-value multicarbon(C2+)chemical production via CO_(2) conversion.
