Based on previous research work,we present a spectrum deviation method to recognize a foreshock or generalized foreshock in this paper. The criterion to determine whether an event is a foreshock is a wide spectrum for...Based on previous research work,we present a spectrum deviation method to recognize a foreshock or generalized foreshock in this paper. The criterion to determine whether an event is a foreshock is a wide spectrum for an ordinary event,however,a moderate earthquake with foreshock or generalized foreshock has the characteristics of a narrow frequency band,and it deviates to the low frequency. It may be explained by metastable extension in the rupture source or related area of the main shock or regional fragmentation damage and crack nucleation process. The calculation results of two foreshocks,the M_S4. 7 event which occurred before the Yushu M_S7. 1 earthquake on April 14,2010 and the M_S5. 3 event which occurred before the Yutian M_S7. 3 earthquake on February 12,2014,show that the spectra of foreshocks shift,and they are quite different from the nonforeshock seismic spectrum of equivalent size. Therefore,this result can verify the validity of the spectrum deviation method.展开更多
In this paper, the sum deviation just-in-time （JIT） sequencing problem in mixed-model production systems is studied relating with the discrete apportionment problem together with their respective mathematical formul...In this paper, the sum deviation just-in-time （JIT） sequencing problem in mixed-model production systems is studied relating with the discrete apportionment problem together with their respective mathematical formulations. The assignment formulation for the first problem is briefly discussed followed by the existence of JIT cyclic sequences. Presenting the concise discussion on divisor methods for the discrete apportionment problem, we have proposed two mean-based divisor functions for this problem claiming that they are better than the existing divisors; hence, we found a better bound for the JIT sequencing problem. The linkage of both the problems is characterized in terms of similar type of objective functions. The problems are shown equivalent via suitable transformations and similar properties. The joint approaches for the two problems are discussed in terms of global and local deviations proposing equitably efficient solution.展开更多
针对FasterVit网络存在的注意力机制失衡、池化策略缺陷导致部分重要特征无法保留和损失函数不能全面考虑所有类别的信息导致学习到的特征比较分散等问题,提出了一种基于CFasterVit-三并联分支融合注意力机制(triple-parallel fusion at...针对FasterVit网络存在的注意力机制失衡、池化策略缺陷导致部分重要特征无法保留和损失函数不能全面考虑所有类别的信息导致学习到的特征比较分散等问题,提出了一种基于CFasterVit-三并联分支融合注意力机制(triple-parallel fusion attention model,TFAM)与余弦均匀流形逼近与投影(cosineuniform manifold approximation and projection,COS-UMAP)模型的滚动轴承故障诊断方法。该模型由FasterVit-TFAM网络、COS-UMAP降维算法和激活函数类距均值标准差损失函数(class-distance mean standard deviation loss,CMSD)-Softmax组成。首先,提出了一种新的注意力机制TFAM,并与FasterVit网络结合,提升了FasterVit网络信息关注的均衡性和表征能力;其次,将基于COS-UMAP降维算法取代FasterVit网络全连接层前最后一次池化操作,有效筛选并保留多维数据中的重要特征;最后,将类距均值标准差损失函数替换Softmax激活函数中的交叉熵损失函数,更全面地学习特征并提高模型的泛化性。西安交通大学滚动轴承数据集滚动轴承故障试验结果表明,TFAM注意力机制和其他注意力机制相比诊断准确率最大提升8.0%,COS-UMAP对比其他降维算法诊断准确率最大提升15.8%,CMSD对比交叉熵损失函数诊断准确率提升0.5%,所提模型对故障样本的识别准确率达到了99.6%,相比FasterVit提升了1.4%,相较于其他网络模型最大提升7.8%;东南大学滚动轴承数据集仿真验证试验结果表明,所提模型对故障样本识别率达98.6%,相比FasterVit提升了2.2%,平均每轮训练时间缩短了16.92 s,对比其他网络模型最大提升12.2%,有效提高了滚动轴承故障诊断模型的准确率和泛化性能。展开更多
地下水干旱不仅严重制约着区域的社会经济发展,还给地下水资源管理带来了巨大挑战。以酒泉绿洲为例,根据11个观测井1985-2017年的月地下水位数据,选用6种概率分布函数构建了标准化地下水指数(Standardized Groundwater Index,SGI),并利...地下水干旱不仅严重制约着区域的社会经济发展,还给地下水资源管理带来了巨大挑战。以酒泉绿洲为例,根据11个观测井1985-2017年的月地下水位数据,选用6种概率分布函数构建了标准化地下水指数(Standardized Groundwater Index,SGI),并利用K-S检验(Kolmogorov-Smirnov test)和AIC准则(Akaike information criterion)进行分布函数的优选。结果表明:Gev分布和Beta分布在不同时间尺度上均展现出较强的适用性。采用K-Means聚类法将11个观测井的SGI分为持续下降型、下降-上升型以及2002-2006年发生突变型。STL(Seasonal and Trend decomposition using Loess)分解结果显示,持续下降型观测井的地下水干旱情况由非干旱持续恶化成中度-重度干旱,下降-上升型观测井的地下水干旱情况不显著,2002-2006年发生突变型观测井在经历突变后,地下水干旱情况长期维持在中度-重度水平。此外,地下水观测井SGI的季节峰值集中在冬季的12、2月和春季的3、5月。展开更多
基金sponsored by the National Key Technology Support Program of China entitled "Application of Digital Seismic Technology to Mid-and Short-term Prediction of Strong Earthquake"(2012BAK19B02-01)
文摘Based on previous research work,we present a spectrum deviation method to recognize a foreshock or generalized foreshock in this paper. The criterion to determine whether an event is a foreshock is a wide spectrum for an ordinary event,however,a moderate earthquake with foreshock or generalized foreshock has the characteristics of a narrow frequency band,and it deviates to the low frequency. It may be explained by metastable extension in the rupture source or related area of the main shock or regional fragmentation damage and crack nucleation process. The calculation results of two foreshocks,the M_S4. 7 event which occurred before the Yushu M_S7. 1 earthquake on April 14,2010 and the M_S5. 3 event which occurred before the Yutian M_S7. 3 earthquake on February 12,2014,show that the spectra of foreshocks shift,and they are quite different from the nonforeshock seismic spectrum of equivalent size. Therefore,this result can verify the validity of the spectrum deviation method.
基金supported by the e-LINK project (EM ECW-ref.149674-EM-1-UK-ERAMUNDUS)financial support to carry out the work at Staffordshire University, Stafford, UK
文摘In this paper, the sum deviation just-in-time （JIT） sequencing problem in mixed-model production systems is studied relating with the discrete apportionment problem together with their respective mathematical formulations. The assignment formulation for the first problem is briefly discussed followed by the existence of JIT cyclic sequences. Presenting the concise discussion on divisor methods for the discrete apportionment problem, we have proposed two mean-based divisor functions for this problem claiming that they are better than the existing divisors; hence, we found a better bound for the JIT sequencing problem. The linkage of both the problems is characterized in terms of similar type of objective functions. The problems are shown equivalent via suitable transformations and similar properties. The joint approaches for the two problems are discussed in terms of global and local deviations proposing equitably efficient solution.
文摘针对FasterVit网络存在的注意力机制失衡、池化策略缺陷导致部分重要特征无法保留和损失函数不能全面考虑所有类别的信息导致学习到的特征比较分散等问题,提出了一种基于CFasterVit-三并联分支融合注意力机制(triple-parallel fusion attention model,TFAM)与余弦均匀流形逼近与投影(cosineuniform manifold approximation and projection,COS-UMAP)模型的滚动轴承故障诊断方法。该模型由FasterVit-TFAM网络、COS-UMAP降维算法和激活函数类距均值标准差损失函数(class-distance mean standard deviation loss,CMSD)-Softmax组成。首先,提出了一种新的注意力机制TFAM,并与FasterVit网络结合,提升了FasterVit网络信息关注的均衡性和表征能力;其次,将基于COS-UMAP降维算法取代FasterVit网络全连接层前最后一次池化操作,有效筛选并保留多维数据中的重要特征;最后,将类距均值标准差损失函数替换Softmax激活函数中的交叉熵损失函数,更全面地学习特征并提高模型的泛化性。西安交通大学滚动轴承数据集滚动轴承故障试验结果表明,TFAM注意力机制和其他注意力机制相比诊断准确率最大提升8.0%,COS-UMAP对比其他降维算法诊断准确率最大提升15.8%,CMSD对比交叉熵损失函数诊断准确率提升0.5%,所提模型对故障样本的识别准确率达到了99.6%,相比FasterVit提升了1.4%,相较于其他网络模型最大提升7.8%;东南大学滚动轴承数据集仿真验证试验结果表明,所提模型对故障样本识别率达98.6%,相比FasterVit提升了2.2%,平均每轮训练时间缩短了16.92 s,对比其他网络模型最大提升12.2%,有效提高了滚动轴承故障诊断模型的准确率和泛化性能。
文摘地下水干旱不仅严重制约着区域的社会经济发展,还给地下水资源管理带来了巨大挑战。以酒泉绿洲为例,根据11个观测井1985-2017年的月地下水位数据,选用6种概率分布函数构建了标准化地下水指数(Standardized Groundwater Index,SGI),并利用K-S检验(Kolmogorov-Smirnov test)和AIC准则(Akaike information criterion)进行分布函数的优选。结果表明:Gev分布和Beta分布在不同时间尺度上均展现出较强的适用性。采用K-Means聚类法将11个观测井的SGI分为持续下降型、下降-上升型以及2002-2006年发生突变型。STL(Seasonal and Trend decomposition using Loess)分解结果显示,持续下降型观测井的地下水干旱情况由非干旱持续恶化成中度-重度干旱,下降-上升型观测井的地下水干旱情况不显著,2002-2006年发生突变型观测井在经历突变后,地下水干旱情况长期维持在中度-重度水平。此外,地下水观测井SGI的季节峰值集中在冬季的12、2月和春季的3、5月。
