滚动轴承是机械设备中的常见关键部件,准确预测其剩余使用寿命对机械设备的安全稳定运行至关重要。针对目前轴承寿命预测存在的轴承退化特征不明显、模型泛化能力差以及数据长期依赖关系难以捕捉的问题,提出基于时频域信号优化器(Time-F...滚动轴承是机械设备中的常见关键部件,准确预测其剩余使用寿命对机械设备的安全稳定运行至关重要。针对目前轴承寿命预测存在的轴承退化特征不明显、模型泛化能力差以及数据长期依赖关系难以捕捉的问题,提出基于时频域信号优化器(Time-Frequency domain signal Ratio Optimizer,TFRO)的多重膨胀多核时间卷积网络(Multi inflated Multi kernel Time Convolutional Network,Mi-MkTCN)模型。TFRO优化器为了精准记忆重要信息,在每一个时间节点上,将过去信息和当前信息重组,其中过去信息中的重要的时频域特征经过了有比例的分配。Mi-MkTCN利用多重膨胀确保重要特征不丢失,再利用多核时间卷积网络实现对不同尺度特征的提取。最终的消融对比实验验证了改进方法的有效性,模型的平均绝对误差、均方误差及均方根误差指标分别为0.00145、0.05069和0.12045。实验结果表明,所提方法显著提升了轴承剩余使用寿命的预测精度,为轴承剩余使用寿命预测提供了高精度、高鲁棒性的解决方案。展开更多
Root-knot nematodes(RKNs)are the most widespread soil-borne obligate endoparasites.They can infect the roots of many crops and cause significant yield losses.The only commercially available RKN-resistant gene in tomat...Root-knot nematodes(RKNs)are the most widespread soil-borne obligate endoparasites.They can infect the roots of many crops and cause significant yield losses.The only commercially available RKN-resistant gene in tomatoes,Mi-1.2,fails at soil temperatures above 28℃.We cloned the heat-stable RKN-resistant gene,Mi-9,from a gene cluster composed of seven nucleotide-binding sites and leucine-rich repeat(NBS-LRR)type resistant genes in Solanum arcunum accession LA2157.Screening nematode infections in individual and combinatorial knockouts of five NBS-LRR genes showed that Mi-9 Candidate 4(MiC-4)alone is sufficient to confer heat-stable RKN resistance.Our study identifies a new source of heat-stable resistance to RKN in tomatoes for challenging environmental conditions.We also showcase a roadmap for rapid characterization of resistance genes by combining comparative genomics and genome editing,with the potential to be utilized in other crops.展开更多
By using Windows QTL Cartographer v2.5 software, QTLs for five weight traits of Liangshan semi-fine wool sheep were detected based on nine microsatellite markers on chromosome 3. According to the results, ① in refere...By using Windows QTL Cartographer v2.5 software, QTLs for five weight traits of Liangshan semi-fine wool sheep were detected based on nine microsatellite markers on chromosome 3. According to the results, ① in reference family 191, the QTL affecting weaning weight was detected at 110.01 cM with an additive effect of 6.860, explaining 29.3% of the phenotypic variance; ② in reference family 190, the QTL affecting weaning daily gain was detected at 227.41 cM with an additive effect of 0.013, explaining 1.7% of the phenotypic variance; ③there was no QTL affect- ing birth weight, 1.5-year weight and 2.5-year weight of Liangshan semi-fine wool sheep.展开更多
针对Informed-RRT(rapidly-exploring random tree)^(*)算法收敛速度慢、优化效率低和生成路径无法满足实际需求等问题,开展了基于MI-RRT^(*)(Modified Informed-RRT^(*))算法的路径规划研究,通过引入贪心采样和自适应步长的方法提高算...针对Informed-RRT(rapidly-exploring random tree)^(*)算法收敛速度慢、优化效率低和生成路径无法满足实际需求等问题,开展了基于MI-RRT^(*)(Modified Informed-RRT^(*))算法的路径规划研究,通过引入贪心采样和自适应步长的方法提高算法的收敛率,减少路径生成时间、降低内存占用;利用最小化Snap曲线优化的方法使路径平滑的同时动力也变化平缓,达到节省能量的效果,并提供实际可执行的路径。最后通过多组不同复杂度的实验环境表明,较Informed-RRT^(*)算法MI-RRT^(*)算法稳定性更高、所得规划路径平滑可执行,并且能够减少20%的迭代次数和25%的搜索时间,得出在开阔以及密集环境中MI-RRT^(*)算法较Informed-RRT^(*)和RRT^(*)算法有明显的优势。展开更多
文摘滚动轴承是机械设备中的常见关键部件,准确预测其剩余使用寿命对机械设备的安全稳定运行至关重要。针对目前轴承寿命预测存在的轴承退化特征不明显、模型泛化能力差以及数据长期依赖关系难以捕捉的问题,提出基于时频域信号优化器(Time-Frequency domain signal Ratio Optimizer,TFRO)的多重膨胀多核时间卷积网络(Multi inflated Multi kernel Time Convolutional Network,Mi-MkTCN)模型。TFRO优化器为了精准记忆重要信息,在每一个时间节点上,将过去信息和当前信息重组,其中过去信息中的重要的时频域特征经过了有比例的分配。Mi-MkTCN利用多重膨胀确保重要特征不丢失,再利用多核时间卷积网络实现对不同尺度特征的提取。最终的消融对比实验验证了改进方法的有效性,模型的平均绝对误差、均方误差及均方根误差指标分别为0.00145、0.05069和0.12045。实验结果表明,所提方法显著提升了轴承剩余使用寿命的预测精度,为轴承剩余使用寿命预测提供了高精度、高鲁棒性的解决方案。
基金supported by the National Key R&D Program of China(2018YFA0900600 and 2021YFF1000103-5)the Strategic Priority Research Program of Chinese Academy of Sciences(XDA24030503)。
文摘Root-knot nematodes(RKNs)are the most widespread soil-borne obligate endoparasites.They can infect the roots of many crops and cause significant yield losses.The only commercially available RKN-resistant gene in tomatoes,Mi-1.2,fails at soil temperatures above 28℃.We cloned the heat-stable RKN-resistant gene,Mi-9,from a gene cluster composed of seven nucleotide-binding sites and leucine-rich repeat(NBS-LRR)type resistant genes in Solanum arcunum accession LA2157.Screening nematode infections in individual and combinatorial knockouts of five NBS-LRR genes showed that Mi-9 Candidate 4(MiC-4)alone is sufficient to confer heat-stable RKN resistance.Our study identifies a new source of heat-stable resistance to RKN in tomatoes for challenging environmental conditions.We also showcase a roadmap for rapid characterization of resistance genes by combining comparative genomics and genome editing,with the potential to be utilized in other crops.
基金Supported by Fund of the Federal Ministry of Education and Research(BMBF),Germany(CHN 00316)Project of Science and Technology Department of Sichuan Province(2012JY0126)~~
文摘By using Windows QTL Cartographer v2.5 software, QTLs for five weight traits of Liangshan semi-fine wool sheep were detected based on nine microsatellite markers on chromosome 3. According to the results, ① in reference family 191, the QTL affecting weaning weight was detected at 110.01 cM with an additive effect of 6.860, explaining 29.3% of the phenotypic variance; ② in reference family 190, the QTL affecting weaning daily gain was detected at 227.41 cM with an additive effect of 0.013, explaining 1.7% of the phenotypic variance; ③there was no QTL affect- ing birth weight, 1.5-year weight and 2.5-year weight of Liangshan semi-fine wool sheep.
文摘针对Informed-RRT(rapidly-exploring random tree)^(*)算法收敛速度慢、优化效率低和生成路径无法满足实际需求等问题,开展了基于MI-RRT^(*)(Modified Informed-RRT^(*))算法的路径规划研究,通过引入贪心采样和自适应步长的方法提高算法的收敛率,减少路径生成时间、降低内存占用;利用最小化Snap曲线优化的方法使路径平滑的同时动力也变化平缓,达到节省能量的效果,并提供实际可执行的路径。最后通过多组不同复杂度的实验环境表明,较Informed-RRT^(*)算法MI-RRT^(*)算法稳定性更高、所得规划路径平滑可执行,并且能够减少20%的迭代次数和25%的搜索时间,得出在开阔以及密集环境中MI-RRT^(*)算法较Informed-RRT^(*)和RRT^(*)算法有明显的优势。
