Recent studies for computer vision and deep learning-based,post-earthquake inspections on RC structures mainly perform well for specific tasks,while the trained models must be fine-tuned and re-trained when facing new...Recent studies for computer vision and deep learning-based,post-earthquake inspections on RC structures mainly perform well for specific tasks,while the trained models must be fine-tuned and re-trained when facing new tasks and datasets,which is inevitably time-consuming.This study proposes a multi-task learning approach that simultaneously accomplishes the semantic segmentation of seven-type structural components,three-type seismic damage,and four-type deterioration states.The proposed method contains a CNN-based encoder-decoder backbone subnetwork with skip-connection modules and a multi-head,task-specific recognition subnetwork.The backbone subnetwork is designed to extract multi-level features of post-earthquake RC structures.The multi-head,task-specific recognition subnetwork consists of three individual self-attention pipelines,each of which utilizes extracted multi-level features from the backbone network as a mutual guidance for the individual segmentation task.A synthetical loss function is designed with real-time adaptive coefficients to balance multi-task losses and focus on the most unstably fluctuating one.Ablation experiments and comparative studies are further conducted to demonstrate their effectiveness and necessity.The results show that the proposed method can simultaneously recognize different structural components,seismic damage,and deterioration states,and that the overall performance of the three-task learning models gains general improvement when compared to all single-task and dual-task models.展开更多
Structural health monitoring is widely utilized in outdoor environments,especially under harsh conditions,which can introduce noise into the monitoring system.Therefore,designing an effective denoising strategy to enh...Structural health monitoring is widely utilized in outdoor environments,especially under harsh conditions,which can introduce noise into the monitoring system.Therefore,designing an effective denoising strategy to enhance the performance of guided wave damage detection in noisy environments is crucial.This paper introduces a local temporal principal component analysis(PCA)reconstruction approach for denoising guided waves prior to implementing unsupervised damage detection,achieved through novel autoencoder-based reconstruction.Experimental results demonstrate that the proposed denoising method significantly enhances damage detection performance when guided waves are contaminated by noise,with SNR values ranging from 10 to-5 dB.Following the implementation of the proposed denoising approach,the AUC score can elevate from 0.65 to 0.96 when dealing with guided waves corrputed by noise at a level of-5 dB.Additionally,the paper provides guidance on selecting the appropriate number of components used in the denoising PCA reconstruction,aiding in the optimization of the damage detection in noisy conditions.展开更多
Substrate, a typical ultra-slender aluminum alloy structural components with a large aspect ratio and complex internal structure, was traditionally manufactured by re-assembly and sub-welding. In order to realize the ...Substrate, a typical ultra-slender aluminum alloy structural components with a large aspect ratio and complex internal structure, was traditionally manufactured by re-assembly and sub-welding. In order to realize the monoblock casting of the substrate, the Pro/E software was utilized to carry out three-dimensional(3D) modeling of the substrate casting, and the filling and solidification processes were calculated, as well as the location and types of casting defects were predicted by the casting simulation software Anycasting. Results of the filling process simulation show that the metal liquid is distributed into each gap runner evenly and smoothly. There is no serious vortex phenomenon in the mold cavity, and the trajectory of the virtual particles is clear. Results of the solidification process simulation show that shrinkage cavities mainly appear at the junction of gap runners and the rail surface of the substrate. The average deformation is 0.6 mm in X direction, 3.8 mm in Y direction, and 8.2 mm in Z direction. Based on the simulation results, the casting process of the substrate was optimized, and qualified castings were successfully produced, which will provide a reference for the casting process design of other ultraslender aluminum alloy structural components.展开更多
This study investigates structural topology optimization of thermoelastic structures considering two kinds of objectives ofminimumstructural compliance and elastic strain energy with a specified available volume const...This study investigates structural topology optimization of thermoelastic structures considering two kinds of objectives ofminimumstructural compliance and elastic strain energy with a specified available volume constraint.To explicitly express the configuration evolution in the structural topology optimization under combination of mechanical and thermal load conditions,the moving morphable components(MMC)framework is adopted.Based on the characteristics of the MMC framework,the number of design variables can be reduced substantially.Corresponding optimization formulation in the MMC topology optimization framework and numerical solution procedures are developed for several numerical examples.Different optimization results are obtained with structural compliance and elastic strain energy as objectives,respectively,for thermoelastic problems.The effectiveness of the proposed optimization formulation is validated by the numerical examples.It is revealed that for the optimization design of the thermoelastic structural strength,the objective function with the minimum structural strain energy can achieve a better performance than that from structural compliance design.展开更多
The aim of this study was to analyze the physicochemical and structural characteristics of the Venn components of wheat gliadin to provide theoretical basis of gliadin for processing in dough and Chinese steamed bread...The aim of this study was to analyze the physicochemical and structural characteristics of the Venn components of wheat gliadin to provide theoretical basis of gliadin for processing in dough and Chinese steamed bread. Eight Venn components, Gli-8, Gli-9, Gli-10, Gli-11, Gli-12, Gli-13, Gli-14, and Gli-15, were extracted from wheat gliadin based on their solubility. The results of physicochemical characteristics showed that the differences in the contents, TDS,electrical conductivity, particle size and zeta potential of Venn components were significant, respectively. The content of Gli-15 in gliadin was the highest, and the content of Gli-9 was the lowest. The TDS value of Gli-9 was the highest(336.0), and the TDS value of Gli-15 was the lowest(52.0). The electrical conductivity of Gli-9 was the highest,which was 7.54 times the lowest value of Gli-11. The zeta potential of Gli-9 was -25.2 mV, and the zeta potential of the Gli-15 was -7.64 mV. However, the difference in the p H values was not significant. The results of UV spectrum and FTIR analysis showed that the secondary structures of the Venn components had significant differences. The results of the XRD patterns indicated that the Venn components might not be a single substance. The results of CLSM images implied that the molecular interactions among the components were varied. Hence, the results could provide research materials and basic data for deep processing and utilization of gliadin.展开更多
基金National Key R&D Program of China under Grant No.2019YFC1511005the National Natural Science Foundation of China under Grant Nos.51921006,52192661 and 52008138+2 种基金the China Postdoctoral Science Foundation under Grant Nos.BX20190102 and 2019M661286the Heilongjiang Natural Science Foundation under Grant No.LH2022E070the Heilongjiang Province Postdoctoral Science Foundation under Grant Nos.LBH-TZ2016 and LBH-Z19064。
文摘Recent studies for computer vision and deep learning-based,post-earthquake inspections on RC structures mainly perform well for specific tasks,while the trained models must be fine-tuned and re-trained when facing new tasks and datasets,which is inevitably time-consuming.This study proposes a multi-task learning approach that simultaneously accomplishes the semantic segmentation of seven-type structural components,three-type seismic damage,and four-type deterioration states.The proposed method contains a CNN-based encoder-decoder backbone subnetwork with skip-connection modules and a multi-head,task-specific recognition subnetwork.The backbone subnetwork is designed to extract multi-level features of post-earthquake RC structures.The multi-head,task-specific recognition subnetwork consists of three individual self-attention pipelines,each of which utilizes extracted multi-level features from the backbone network as a mutual guidance for the individual segmentation task.A synthetical loss function is designed with real-time adaptive coefficients to balance multi-task losses and focus on the most unstably fluctuating one.Ablation experiments and comparative studies are further conducted to demonstrate their effectiveness and necessity.The results show that the proposed method can simultaneously recognize different structural components,seismic damage,and deterioration states,and that the overall performance of the three-task learning models gains general improvement when compared to all single-task and dual-task models.
基金National Science Foundation of Zhejiang under Contract(LY23E010001)。
文摘Structural health monitoring is widely utilized in outdoor environments,especially under harsh conditions,which can introduce noise into the monitoring system.Therefore,designing an effective denoising strategy to enhance the performance of guided wave damage detection in noisy environments is crucial.This paper introduces a local temporal principal component analysis(PCA)reconstruction approach for denoising guided waves prior to implementing unsupervised damage detection,achieved through novel autoencoder-based reconstruction.Experimental results demonstrate that the proposed denoising method significantly enhances damage detection performance when guided waves are contaminated by noise,with SNR values ranging from 10 to-5 dB.Following the implementation of the proposed denoising approach,the AUC score can elevate from 0.65 to 0.96 when dealing with guided waves corrputed by noise at a level of-5 dB.Additionally,the paper provides guidance on selecting the appropriate number of components used in the denoising PCA reconstruction,aiding in the optimization of the damage detection in noisy conditions.
文摘Substrate, a typical ultra-slender aluminum alloy structural components with a large aspect ratio and complex internal structure, was traditionally manufactured by re-assembly and sub-welding. In order to realize the monoblock casting of the substrate, the Pro/E software was utilized to carry out three-dimensional(3D) modeling of the substrate casting, and the filling and solidification processes were calculated, as well as the location and types of casting defects were predicted by the casting simulation software Anycasting. Results of the filling process simulation show that the metal liquid is distributed into each gap runner evenly and smoothly. There is no serious vortex phenomenon in the mold cavity, and the trajectory of the virtual particles is clear. Results of the solidification process simulation show that shrinkage cavities mainly appear at the junction of gap runners and the rail surface of the substrate. The average deformation is 0.6 mm in X direction, 3.8 mm in Y direction, and 8.2 mm in Z direction. Based on the simulation results, the casting process of the substrate was optimized, and qualified castings were successfully produced, which will provide a reference for the casting process design of other ultraslender aluminum alloy structural components.
基金Financial supports for this research were provided by the National Nat-ural Science Foundation of China(Nos.11672057,12002278,U1906233)the National Key R&D Program of China(2017YFC0307201)+1 种基金the Key R&D Program of Shandong Province(2019JZZY010801)the Fundamental Research Funds for the Central Universities(NWPU-G2020KY05308)。
文摘This study investigates structural topology optimization of thermoelastic structures considering two kinds of objectives ofminimumstructural compliance and elastic strain energy with a specified available volume constraint.To explicitly express the configuration evolution in the structural topology optimization under combination of mechanical and thermal load conditions,the moving morphable components(MMC)framework is adopted.Based on the characteristics of the MMC framework,the number of design variables can be reduced substantially.Corresponding optimization formulation in the MMC topology optimization framework and numerical solution procedures are developed for several numerical examples.Different optimization results are obtained with structural compliance and elastic strain energy as objectives,respectively,for thermoelastic problems.The effectiveness of the proposed optimization formulation is validated by the numerical examples.It is revealed that for the optimization design of the thermoelastic structural strength,the objective function with the minimum structural strain energy can achieve a better performance than that from structural compliance design.
基金The authors thanks for the financial support of the National Key Research and Development Program(2016YFD0400203)the National Natural Science Foundation of China(Project No.31771897,31871852,and 31772023).
文摘The aim of this study was to analyze the physicochemical and structural characteristics of the Venn components of wheat gliadin to provide theoretical basis of gliadin for processing in dough and Chinese steamed bread. Eight Venn components, Gli-8, Gli-9, Gli-10, Gli-11, Gli-12, Gli-13, Gli-14, and Gli-15, were extracted from wheat gliadin based on their solubility. The results of physicochemical characteristics showed that the differences in the contents, TDS,electrical conductivity, particle size and zeta potential of Venn components were significant, respectively. The content of Gli-15 in gliadin was the highest, and the content of Gli-9 was the lowest. The TDS value of Gli-9 was the highest(336.0), and the TDS value of Gli-15 was the lowest(52.0). The electrical conductivity of Gli-9 was the highest,which was 7.54 times the lowest value of Gli-11. The zeta potential of Gli-9 was -25.2 mV, and the zeta potential of the Gli-15 was -7.64 mV. However, the difference in the p H values was not significant. The results of UV spectrum and FTIR analysis showed that the secondary structures of the Venn components had significant differences. The results of the XRD patterns indicated that the Venn components might not be a single substance. The results of CLSM images implied that the molecular interactions among the components were varied. Hence, the results could provide research materials and basic data for deep processing and utilization of gliadin.