The Rayleigh distillation isotope fractionation(RDIF) model is one of the most popular methods used in isotope geochemistry. Numerous isotope signals observed in geologic processes have been interpreted with this mode...The Rayleigh distillation isotope fractionation(RDIF) model is one of the most popular methods used in isotope geochemistry. Numerous isotope signals observed in geologic processes have been interpreted with this model. The RDIF model provides a simple mathematic solution for the reservoir-limited equilibrium isotope fractionation effect. Due to the reservoir effect, tremendously large isotope fractionations will always be produced if the reservoir is close to being depleted. However, in real situations, many prerequisites assumed in the RDIF model are often difficult to meet. For instance, it requires the relocated materials, which are removed step by step from one reservoir to another with different isotope compositions(i.e., with isotope fractionation), to be isotopically equilibrated with materials in the first reservoir simultaneously. This ‘‘quick equilibrium requirement’’ is indeed hard to meet if the first reservoir is sufficiently large or the removal step is fast. The whole first reservoir will often fail to re-attain equilibrium in time before the next removal starts.This problem led the RDIF model to fail to interpret isotope signals of many real situations. Here a diffusion-coupled and Rayleigh-like(i.e., reservoir-effect included) separation process is chosen to investigate this problem. We find that the final isotope fractionations are controlled by both the diffusion process and the reservoir effects via the disequilibrium separation process. Due to its complexity, we choose to use a numerical simulation method to solve this problem by developing specific computing codes for the working model.According to our simulation results, the classical RDIF model only governs isotope fractionations correctly at the final stages of separation when the reservoir scale(or thickness of the system) is reduced to the order of magnitude of the quotient of the diffusivity and the separation rate. The RDIF model fails in other situations and the isotope fractionations will be diffusion-limited when the reservoir is relatively large, or the separation rate is fast. We find that the effect of internal isotope distribution inhomogeneity caused by diffusion on the Rayleigh-like separation process is significant and cannot be ignored. This method can be applied to study numerous geologic and planetary processes involving diffusion-limited disequilibrium separation processes including partial melting,evaporation, mineral precipitation, core segregation, etc.Importantly, we find that far more information can be extracted through analyzing isotopic signals of such ‘‘disequilibrium’’processes than those of fully equilibrated ones, e.g., reservoir size and the separation rate. Such information may provide a key to correctly interpreting many isotope signals observed from geochemical and cosmochemical processes.展开更多
为解决传统航空发动机异常检测方法准确率和泛化性能较低的问题,提出一种混合核最大相关熵的深度支持向量数据描述(mixed kernel maximum correntropy criterion-deep support vector data description,MKMCC-DSVDD)方法。首先,采用合...为解决传统航空发动机异常检测方法准确率和泛化性能较低的问题,提出一种混合核最大相关熵的深度支持向量数据描述(mixed kernel maximum correntropy criterion-deep support vector data description,MKMCC-DSVDD)方法。首先,采用合成少数类过采样技术扩充异常样本规模,提高对非均衡样本的泛化性能;其次,建立基于混合核改进的最大相关熵损失函数,可以在无须数据分布假设的前提下提升准确率;最后,构建基于MKMCC-DSVDD的航空发动机异常检测方法。在航空发动机气路系统和滑油系统异常检测实验中,所提方法平均曲线下的面积(area under curve,AUC)达到98.53%,表明其具有较高的实用性和泛化性能。展开更多
基金supported by the Strategic Priority Research Program (B) of CAS (No. XDB41000000)Pre-research Project on Civil Aerospace Technologies No. D020202 funded by the Chinese National Space Administration (CNSA) and Chinese NSF projects (No. 42130114)。
文摘The Rayleigh distillation isotope fractionation(RDIF) model is one of the most popular methods used in isotope geochemistry. Numerous isotope signals observed in geologic processes have been interpreted with this model. The RDIF model provides a simple mathematic solution for the reservoir-limited equilibrium isotope fractionation effect. Due to the reservoir effect, tremendously large isotope fractionations will always be produced if the reservoir is close to being depleted. However, in real situations, many prerequisites assumed in the RDIF model are often difficult to meet. For instance, it requires the relocated materials, which are removed step by step from one reservoir to another with different isotope compositions(i.e., with isotope fractionation), to be isotopically equilibrated with materials in the first reservoir simultaneously. This ‘‘quick equilibrium requirement’’ is indeed hard to meet if the first reservoir is sufficiently large or the removal step is fast. The whole first reservoir will often fail to re-attain equilibrium in time before the next removal starts.This problem led the RDIF model to fail to interpret isotope signals of many real situations. Here a diffusion-coupled and Rayleigh-like(i.e., reservoir-effect included) separation process is chosen to investigate this problem. We find that the final isotope fractionations are controlled by both the diffusion process and the reservoir effects via the disequilibrium separation process. Due to its complexity, we choose to use a numerical simulation method to solve this problem by developing specific computing codes for the working model.According to our simulation results, the classical RDIF model only governs isotope fractionations correctly at the final stages of separation when the reservoir scale(or thickness of the system) is reduced to the order of magnitude of the quotient of the diffusivity and the separation rate. The RDIF model fails in other situations and the isotope fractionations will be diffusion-limited when the reservoir is relatively large, or the separation rate is fast. We find that the effect of internal isotope distribution inhomogeneity caused by diffusion on the Rayleigh-like separation process is significant and cannot be ignored. This method can be applied to study numerous geologic and planetary processes involving diffusion-limited disequilibrium separation processes including partial melting,evaporation, mineral precipitation, core segregation, etc.Importantly, we find that far more information can be extracted through analyzing isotopic signals of such ‘‘disequilibrium’’processes than those of fully equilibrated ones, e.g., reservoir size and the separation rate. Such information may provide a key to correctly interpreting many isotope signals observed from geochemical and cosmochemical processes.
文摘为解决传统航空发动机异常检测方法准确率和泛化性能较低的问题,提出一种混合核最大相关熵的深度支持向量数据描述(mixed kernel maximum correntropy criterion-deep support vector data description,MKMCC-DSVDD)方法。首先,采用合成少数类过采样技术扩充异常样本规模,提高对非均衡样本的泛化性能;其次,建立基于混合核改进的最大相关熵损失函数,可以在无须数据分布假设的前提下提升准确率;最后,构建基于MKMCC-DSVDD的航空发动机异常检测方法。在航空发动机气路系统和滑油系统异常检测实验中,所提方法平均曲线下的面积(area under curve,AUC)达到98.53%,表明其具有较高的实用性和泛化性能。
