We propose a robust earthquake clustering method:the Bayesian Gaussian mixture model with nearest-neighbor distance(BGMM-NND)algorithm.Unlike the conventional nearest neighbor distance method,the BGMM-NND algorithm el...We propose a robust earthquake clustering method:the Bayesian Gaussian mixture model with nearest-neighbor distance(BGMM-NND)algorithm.Unlike the conventional nearest neighbor distance method,the BGMM-NND algorithm eliminates the need for hyperparameter tuning or reliance on fixed thresholds,offering enhanced flexibility for clustering across varied seismic scales.By integrating cumulative probability and BGMM with principal component analysis(PCA),the BGMM-NND algorithm effectively distinguishes between background and triggered earthquakes while maintaining the magnitude component and resolving the issue of excessively large spatial cluster domains.We apply the BGMM-NND algorithm to the Sichuan–Yunnan seismic catalog from 1971 to 2024,revealing notable variations in earthquake frequency,triggering characteristics,and recurrence patterns across different fault zones.Distinct clustering and triggering behaviors are identified along different segments of the Longmenshan Fault.Multiple seismic modes,namely,the short-distance mode,the medium-distance mode,the repeating-like mode,the uniform background mode,and the Wenchuan mode,are uncovered.The algorithm's flexibility and robust performance in earthquake clustering makes it a valuable tool for exploring seismicity characteristics,offering new insights into earthquake clustering and the spatiotemporal patterns of seismic activity.展开更多
Failure mode and effect analysis(FMEA)is a preven-tative risk evaluation method used to evaluate and eliminate fail-ure modes within a system.However,the traditional FMEA method exhibits many deficiencies that pose ch...Failure mode and effect analysis(FMEA)is a preven-tative risk evaluation method used to evaluate and eliminate fail-ure modes within a system.However,the traditional FMEA method exhibits many deficiencies that pose challenges in prac-tical applications.To improve the conventional FMEA,many modified FMEA models have been suggested.However,the majority of them inadequately address consensus issues and focus on achieving a complete ranking of failure modes.In this research,we propose a new FMEA approach that integrates a two-stage consensus reaching model and a density peak clus-tering algorithm for the assessment and clustering of failure modes.Firstly,we employ the interval 2-tuple linguistic vari-ables(I2TLVs)to express the uncertain risk evaluations provided by FMEA experts.Then,a two-stage consensus reaching model is adopted to enable FMEA experts to reach a consensus.Next,failure modes are categorized into several risk clusters using a density peak clustering algorithm.Finally,the proposed FMEA is illustrated by a case study of load-bearing guidance devices of subway systems.The results show that the proposed FMEA model can more easily to describe the uncertain risk information of failure modes by using the I2TLVs;the introduction of an endogenous feedback mechanism and an exogenous feedback mechanism can accelerate the process of consensus reaching;and the density peak clustering of failure modes successfully improves the practical applicability of FMEA.展开更多
Michael K.Ng等人提出了新K-Modes聚类算法,它采用基于相对频率的启发式相异度度量方法,有效地提高了聚类精度,但不足的是在计算各类的属性分类值频率时假定类中样本对聚类的贡献相同。为了考虑类中样本对类中心的不同影响,提出一种粗糙...Michael K.Ng等人提出了新K-Modes聚类算法,它采用基于相对频率的启发式相异度度量方法,有效地提高了聚类精度,但不足的是在计算各类的属性分类值频率时假定类中样本对聚类的贡献相同。为了考虑类中样本对类中心的不同影响,提出一种粗糙K-Modes算法,通过粗糙集的上、下近似度量数据样本在类内的重要性程度,不仅可以获得比新K-Modes算法更好的聚类效果,而且可以在保证聚类效果的基础上降低白亮等人提出的基于粗糙集改进的K-Modes算法的计算复杂度。对几个UCI的数据集的测试实验结果显示出新算法的优良性能。展开更多
为解决现有k-modes聚类方法因忽略了变量属性之间的弱相关性,常造成其在实际应用中聚类性能不佳的问题,提出一种包含属性弱相关性的新k-modes聚类方法。引入最大信息系数(maximum information coefficient,MIC)度量数据集中变量属性之...为解决现有k-modes聚类方法因忽略了变量属性之间的弱相关性,常造成其在实际应用中聚类性能不佳的问题,提出一种包含属性弱相关性的新k-modes聚类方法。引入最大信息系数(maximum information coefficient,MIC)度量数据集中变量属性之间的相关性;将得到的MIC值与原有距离进行融合,建立包含属性弱相关性信息的新度量方法,以增强变量属性间相关信息的完备性,建立更加精细的k-modes聚类方法;调用3种不同的数据集,将新方法与原有的k-modes聚类方法和其他改进k-modes聚类方法的性能进行对比,并通过仿真结果表明了新方法的有效性。展开更多
基金supported by the National Key Research and Development Program of China(Grant Nos.2021YFC3000705 and 2021YFC3000705-05)the National Natural Science Foundation of China(Grant No.42074049)the Youth Innovation Promotion Association of the Chinese Academy of Sciences(Grant No.2023471).
文摘We propose a robust earthquake clustering method:the Bayesian Gaussian mixture model with nearest-neighbor distance(BGMM-NND)algorithm.Unlike the conventional nearest neighbor distance method,the BGMM-NND algorithm eliminates the need for hyperparameter tuning or reliance on fixed thresholds,offering enhanced flexibility for clustering across varied seismic scales.By integrating cumulative probability and BGMM with principal component analysis(PCA),the BGMM-NND algorithm effectively distinguishes between background and triggered earthquakes while maintaining the magnitude component and resolving the issue of excessively large spatial cluster domains.We apply the BGMM-NND algorithm to the Sichuan–Yunnan seismic catalog from 1971 to 2024,revealing notable variations in earthquake frequency,triggering characteristics,and recurrence patterns across different fault zones.Distinct clustering and triggering behaviors are identified along different segments of the Longmenshan Fault.Multiple seismic modes,namely,the short-distance mode,the medium-distance mode,the repeating-like mode,the uniform background mode,and the Wenchuan mode,are uncovered.The algorithm's flexibility and robust performance in earthquake clustering makes it a valuable tool for exploring seismicity characteristics,offering new insights into earthquake clustering and the spatiotemporal patterns of seismic activity.
基金supported by the Fundamental Research Funds for the Central Universities(22120240094)Humanities and Social Science Fund of Ministry of Education China(22YJA630082).
文摘Failure mode and effect analysis(FMEA)is a preven-tative risk evaluation method used to evaluate and eliminate fail-ure modes within a system.However,the traditional FMEA method exhibits many deficiencies that pose challenges in prac-tical applications.To improve the conventional FMEA,many modified FMEA models have been suggested.However,the majority of them inadequately address consensus issues and focus on achieving a complete ranking of failure modes.In this research,we propose a new FMEA approach that integrates a two-stage consensus reaching model and a density peak clus-tering algorithm for the assessment and clustering of failure modes.Firstly,we employ the interval 2-tuple linguistic vari-ables(I2TLVs)to express the uncertain risk evaluations provided by FMEA experts.Then,a two-stage consensus reaching model is adopted to enable FMEA experts to reach a consensus.Next,failure modes are categorized into several risk clusters using a density peak clustering algorithm.Finally,the proposed FMEA is illustrated by a case study of load-bearing guidance devices of subway systems.The results show that the proposed FMEA model can more easily to describe the uncertain risk information of failure modes by using the I2TLVs;the introduction of an endogenous feedback mechanism and an exogenous feedback mechanism can accelerate the process of consensus reaching;and the density peak clustering of failure modes successfully improves the practical applicability of FMEA.
文摘为解决现有k-modes聚类方法因忽略了变量属性之间的弱相关性,常造成其在实际应用中聚类性能不佳的问题,提出一种包含属性弱相关性的新k-modes聚类方法。引入最大信息系数(maximum information coefficient,MIC)度量数据集中变量属性之间的相关性;将得到的MIC值与原有距离进行融合,建立包含属性弱相关性信息的新度量方法,以增强变量属性间相关信息的完备性,建立更加精细的k-modes聚类方法;调用3种不同的数据集,将新方法与原有的k-modes聚类方法和其他改进k-modes聚类方法的性能进行对比,并通过仿真结果表明了新方法的有效性。
