The production of advanced 3D engineering materials relies on energy-intensive moldable materials such as metals and plastics,making it difficult to cope with the increasingly severe global energy crisis.Wood,as a sus...The production of advanced 3D engineering materials relies on energy-intensive moldable materials such as metals and plastics,making it difficult to cope with the increasingly severe global energy crisis.Wood,as a sustainable material,can be molded through hydrothermal treatment,but the limited plasticity hinders its ability to manufacture precision devices.Herein,the process of hydrogen-bond domain reorganization is used in the manufacture of highly moldable wood to enhance the plasticity of wood and ensure the stability of the cellulose structure.The native hydrogen-bond network in the wood cell wall is disrupted and liberated the cellulose fibril matrix through delignification.Subsequent epoxidized soybean oil acrylate(AESO)plasticization enables significantly enhanced plasticity.Hydrogen-bond domains between fibers are reconstructed through moisture variation.Meanwhile,AESO forms a protective layer on the surface of the fibers,preventing excessive moisture from entering and causing the collapse of the fiber framework.This process allows the material to be shaped into complex 3D geometries,including origami cranes or honeycombs,through low-energy hydrothermal processing.This strategy addresses both dimensional stability challenges and environmental instability associated with wood composite materials and offers an eco-friendly alternative to functionalized structures in aviation and transportation.展开更多
针对重组竹热压成型过程中工艺参数多因素耦合、依赖经验调参且试错成本高的问题,亟需建立工艺参数与质量指标之间的定量映射关系,并进一步实现面向目标性能的参数反推。为此,提出一种基于多策略(multi-strategy,MS)交通拥堵优化算法(tr...针对重组竹热压成型过程中工艺参数多因素耦合、依赖经验调参且试错成本高的问题,亟需建立工艺参数与质量指标之间的定量映射关系,并进一步实现面向目标性能的参数反推。为此,提出一种基于多策略(multi-strategy,MS)交通拥堵优化算法(traffic jam optimization,TJO)优化的支持向量回归(support vector regression,SVR)方法——MSTJO-SVR,用于构建重组竹工艺参数与质量指标的双向预测模型。正向预测以密度、含水率、施胶量和保压时间为工艺参数输入,以静曲强度、水平抗剪强度、吸水宽度膨胀率和吸水厚度膨胀率为质量指标输出;反向预测以质量指标为输入,反推相应工艺参数。通过MS-TJO对SVR关键超参数进行联合寻优,提高模型对非线性关系的表征能力与预测稳定性。结果表明,所构建的MS-TJO-SVR在正向与反向预测任务中均具有较高的拟合精度和较小的预测误差,且在与传统SVR及其他优化SVR方法的对比中表现出更优的综合性能。研究结果可为重组竹热压成型参数优化与质量预测提供有效的建模工具与方法参考。展开更多
基金supported by the National Natural Science Foundation of China(Grant No.32571971 and 22408239)Sichuan Science and Technology Program(2024NSFSC0987)+1 种基金Beijing Natural Science Foundation(2254096)Postdoctoral Innovation Talent Support Program(BX20240038).
摘要The production of advanced 3D engineering materials relies on energy-intensive moldable materials such as metals and plastics,making it difficult to cope with the increasingly severe global energy crisis.Wood,as a sustainable material,can be molded through hydrothermal treatment,but the limited plasticity hinders its ability to manufacture precision devices.Herein,the process of hydrogen-bond domain reorganization is used in the manufacture of highly moldable wood to enhance the plasticity of wood and ensure the stability of the cellulose structure.The native hydrogen-bond network in the wood cell wall is disrupted and liberated the cellulose fibril matrix through delignification.Subsequent epoxidized soybean oil acrylate(AESO)plasticization enables significantly enhanced plasticity.Hydrogen-bond domains between fibers are reconstructed through moisture variation.Meanwhile,AESO forms a protective layer on the surface of the fibers,preventing excessive moisture from entering and causing the collapse of the fiber framework.This process allows the material to be shaped into complex 3D geometries,including origami cranes or honeycombs,through low-energy hydrothermal processing.This strategy addresses both dimensional stability challenges and environmental instability associated with wood composite materials and offers an eco-friendly alternative to functionalized structures in aviation and transportation.
摘要针对重组竹热压成型过程中工艺参数多因素耦合、依赖经验调参且试错成本高的问题,亟需建立工艺参数与质量指标之间的定量映射关系,并进一步实现面向目标性能的参数反推。为此,提出一种基于多策略(multi-strategy,MS)交通拥堵优化算法(traffic jam optimization,TJO)优化的支持向量回归(support vector regression,SVR)方法——MSTJO-SVR,用于构建重组竹工艺参数与质量指标的双向预测模型。正向预测以密度、含水率、施胶量和保压时间为工艺参数输入,以静曲强度、水平抗剪强度、吸水宽度膨胀率和吸水厚度膨胀率为质量指标输出;反向预测以质量指标为输入,反推相应工艺参数。通过MS-TJO对SVR关键超参数进行联合寻优,提高模型对非线性关系的表征能力与预测稳定性。结果表明,所构建的MS-TJO-SVR在正向与反向预测任务中均具有较高的拟合精度和较小的预测误差,且在与传统SVR及其他优化SVR方法的对比中表现出更优的综合性能。研究结果可为重组竹热压成型参数优化与质量预测提供有效的建模工具与方法参考。