The structure and working principle of a self-deigned high pressure electronic pneumatic pressure reducing valve (EPPRV) with slide pilot are introduced.The resistance value formulas and the relationship between the r...The structure and working principle of a self-deigned high pressure electronic pneumatic pressure reducing valve (EPPRV) with slide pilot are introduced.The resistance value formulas and the relationship between the resistance and pressure of three typical pneumatic resistances are obtained.Then,the method of static characteristics analysis only considering pneumatic resistances is proposed,the resistance network from gas supply to load is built up,and the mathematical model is derived from the flow rate formulas and flow conservation equations,with the compressibility of high pressure gas and temperature drop during the expansion considered in the model.Finally,the pilot spool displacement of 1.5 mm at an output pressure of 15MPa and the enlarging operating stroke of the pilot spool are taken as optimization targets,and the optimization is carried out based on genetic algorithm and the model mentioned above.The results show that the static characteristics of the EPPRV are significantly improved.The idea of static characteristics analysis and optimization based on pneumatic resistance network is valuable for the design of pneumatic components or system.展开更多
为求解高维优化问题,提出基于反向学习和衰减因子的灰狼优化算法(grey wolf algorithm based on opposition learning and reduction factor,ORGWO).设计一种灰狼反向学习模型,模型考虑问题搜索边界信息和种群历史搜索信息,初始种群阶...为求解高维优化问题,提出基于反向学习和衰减因子的灰狼优化算法(grey wolf algorithm based on opposition learning and reduction factor,ORGWO).设计一种灰狼反向学习模型,模型考虑问题搜索边界信息和种群历史搜索信息,初始种群阶段增加反向学习,增强种群多样性.根据算法各个阶段不同特征引入衰减因子,平衡全局和局部勘探能力.选取8个高维函数和23个不同特征的优化函数对算法性能进行测试,进一步使用收敛性分析,寻优成功率,CPU时间,Wilcoxon秩和检验来评估改进算法,实验结果表明,ORGWO算法在求解高维问题上具有较好的精度,鲁棒性和更快的收敛速度.展开更多
针对目前在混合现实(MR)环境中高效率建立高质量三维(3D)模型的需求,基于神经辐射场算法(NeRF)的三维重建技术,提出了一种基于Laplacian算子的数据集优化算法。首先,围绕某线切割设备录制了一段1 min 51 s的视频,并采取等距提取视频帧...针对目前在混合现实(MR)环境中高效率建立高质量三维(3D)模型的需求,基于神经辐射场算法(NeRF)的三维重建技术,提出了一种基于Laplacian算子的数据集优化算法。首先,围绕某线切割设备录制了一段1 min 51 s的视频,并采取等距提取视频帧的方式,获取了训练数据集;然后,使用Laplacian算子对数据集进行了优化,同时保留了原始数据集作为对比,使用了基于NeRF算法的重建方式与传统的基于COLMAP的稠密点云重建方式,分别对两组数据集进行了三维重建;最后,在重建精度与重建速度方面,对不同重建方式、不同重建数据集的重建结果进行了比较。研究结果表明:COLMAP稠密点云重建耗时是基于NeRF重建耗时的9.98倍,而相较于COLMAP稠密点云重建,使用NeRF重建方式的模型表面缺陷较少;此外,使用Laplacian算子优化的数据集的NeRF重建在峰值信噪比(PSNR)和结构相似性(SSIM)指标上分别提升了2.43%、0.72%,有利于提升重建模型的质量。研究结果支持混合现实技术在制造业数字化转型中的应用,可为其提供有益的参考。展开更多
基金Project(50575202) supported by the National Natural Science Foundation of China
文摘The structure and working principle of a self-deigned high pressure electronic pneumatic pressure reducing valve (EPPRV) with slide pilot are introduced.The resistance value formulas and the relationship between the resistance and pressure of three typical pneumatic resistances are obtained.Then,the method of static characteristics analysis only considering pneumatic resistances is proposed,the resistance network from gas supply to load is built up,and the mathematical model is derived from the flow rate formulas and flow conservation equations,with the compressibility of high pressure gas and temperature drop during the expansion considered in the model.Finally,the pilot spool displacement of 1.5 mm at an output pressure of 15MPa and the enlarging operating stroke of the pilot spool are taken as optimization targets,and the optimization is carried out based on genetic algorithm and the model mentioned above.The results show that the static characteristics of the EPPRV are significantly improved.The idea of static characteristics analysis and optimization based on pneumatic resistance network is valuable for the design of pneumatic components or system.
文摘为求解高维优化问题,提出基于反向学习和衰减因子的灰狼优化算法(grey wolf algorithm based on opposition learning and reduction factor,ORGWO).设计一种灰狼反向学习模型,模型考虑问题搜索边界信息和种群历史搜索信息,初始种群阶段增加反向学习,增强种群多样性.根据算法各个阶段不同特征引入衰减因子,平衡全局和局部勘探能力.选取8个高维函数和23个不同特征的优化函数对算法性能进行测试,进一步使用收敛性分析,寻优成功率,CPU时间,Wilcoxon秩和检验来评估改进算法,实验结果表明,ORGWO算法在求解高维问题上具有较好的精度,鲁棒性和更快的收敛速度.
文摘针对目前在混合现实(MR)环境中高效率建立高质量三维(3D)模型的需求,基于神经辐射场算法(NeRF)的三维重建技术,提出了一种基于Laplacian算子的数据集优化算法。首先,围绕某线切割设备录制了一段1 min 51 s的视频,并采取等距提取视频帧的方式,获取了训练数据集;然后,使用Laplacian算子对数据集进行了优化,同时保留了原始数据集作为对比,使用了基于NeRF算法的重建方式与传统的基于COLMAP的稠密点云重建方式,分别对两组数据集进行了三维重建;最后,在重建精度与重建速度方面,对不同重建方式、不同重建数据集的重建结果进行了比较。研究结果表明:COLMAP稠密点云重建耗时是基于NeRF重建耗时的9.98倍,而相较于COLMAP稠密点云重建,使用NeRF重建方式的模型表面缺陷较少;此外,使用Laplacian算子优化的数据集的NeRF重建在峰值信噪比(PSNR)和结构相似性(SSIM)指标上分别提升了2.43%、0.72%,有利于提升重建模型的质量。研究结果支持混合现实技术在制造业数字化转型中的应用,可为其提供有益的参考。
