Disk failures,the most common and major failures in storage systems,increase the risk of service interruption and data loss,and bring additional maintenance costs,which reduces system reliability.Disk failure predicti...Disk failures,the most common and major failures in storage systems,increase the risk of service interruption and data loss,and bring additional maintenance costs,which reduces system reliability.Disk failure prediction methods aim to forecast failures,initiating prompt data migration and disk replacement.Existing methods continuously optimize the models with different sampling methods and modeling algorithms.However,due to issues such as inaccurate sample labeling,insufficient data sampling,and improper sample segmentation,the predictive capabilities of existing models within the lookahead-window time are unstable and decline as the lookahead-window time increases.To address this,we propose LWCM(Lookahead-Window Constrained Model)to improve the predictability and stability of failure prediction models within the lookahead-window time.LWCM leverages dynamic sample relabeling methods based on lookahead-window time constraints and failure symptom durations to modify inaccurate sample labels.LWCM utilizes effective sample data by using the two-phase data sampling method including initial expectation sampling and subsequent segmented resampling.LWCM employs dynamic weighted optimization in backpropagation to enhance the predictability and stability of the disk failure prediction model.Experimental results show that LWCM has better failure prediction performance.The true positive and false positive rates surpass those of the offline-RF model by 38.7%and 92.4%,respectively.Furthermore,LWCM demonstrates its applicability across disk models while maintaining stability within the lookahead constraint window.展开更多
Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can h...Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can handle only one will result in prediction bias in reality.Existing disk failure prediction methods simply fuse various models,lacking discussion of training data preparation and learning patterns when facing multiple issues,although the solutions to different issues often conflict with each other.As a result,we first explore the training data preparation for multiple issues via a data partitioning pattern,i.e.,our proposed multi-property data partitioning(MDP).Then,we consider learning with the partitioned data for multiple issues as learning multiple tasks,and introduce the model-agnostic meta-learning(MAML)framework to achieve the learning.Based on these improvements,we propose a novel disk failure prediction model named MDP-MAML.MDP addresses the challenges of uneven partitioning and difficulty in partitioning by time,and MAML addresses the challenge of learning with multiple domains and minor samples for multiple issues.In addition,MDP-MAML can assimilate emerging issues for learning and prediction.On the datasets reported by two real-world data centers,compared to state-of-the-art methods,MDP-MAML can improve the area under the curve(AUC)and false detection rate(FDR)from 0.85 to0.89 and from 0.85 to 0.91,respectively,while reducing false alarm rate(FAR)from 4.88%to 2.85%.展开更多
To investigate the ballistic resistance and failure pattern of aeroengine casing following the impact of disk fragments, and to determine the optimum case structure, the phenomena of a 1/3rd disk fragment impact on si...To investigate the ballistic resistance and failure pattern of aeroengine casing following the impact of disk fragments, and to determine the optimum case structure, the phenomena of a 1/3rd disk fragment impact on single and double-layered thin plate targets were simulated using nonlinear dynamical analysis software MSC.Dytran. Strain rate effect was introduced in a Johnson-Cook (JC) material model for the disk fragment and the plate. Impact modeling was based on the Arbitrary Lagrange-Eulerian method, and simulated using explicit finite element method (FEM). Simulation results showed that the major failure pattern of the plate is shearing and tensile fracture with large plastic deformation. It was also concluded that the ballistic limit velocity increases with the standoff distance when it is beyond a certain value, and that greater resistance is obtained when the front plate has either a proportionately low or high thickness. The impact resistance of a double-layered plate may exceed that of a single plate if the thicknesses and standoff distance of the two plates are set appropriately.展开更多
基金supported in part by the National Key Research and Development Program of China under Grant No.2023YFB4502801.
文摘Disk failures,the most common and major failures in storage systems,increase the risk of service interruption and data loss,and bring additional maintenance costs,which reduces system reliability.Disk failure prediction methods aim to forecast failures,initiating prompt data migration and disk replacement.Existing methods continuously optimize the models with different sampling methods and modeling algorithms.However,due to issues such as inaccurate sample labeling,insufficient data sampling,and improper sample segmentation,the predictive capabilities of existing models within the lookahead-window time are unstable and decline as the lookahead-window time increases.To address this,we propose LWCM(Lookahead-Window Constrained Model)to improve the predictability and stability of failure prediction models within the lookahead-window time.LWCM leverages dynamic sample relabeling methods based on lookahead-window time constraints and failure symptom durations to modify inaccurate sample labels.LWCM utilizes effective sample data by using the two-phase data sampling method including initial expectation sampling and subsequent segmented resampling.LWCM employs dynamic weighted optimization in backpropagation to enhance the predictability and stability of the disk failure prediction model.Experimental results show that LWCM has better failure prediction performance.The true positive and false positive rates surpass those of the offline-RF model by 38.7%and 92.4%,respectively.Furthermore,LWCM demonstrates its applicability across disk models while maintaining stability within the lookahead constraint window.
基金Project supported by the National Natural Science Foundation of China(No.61902135)the Shandong Provincial Natural Science Foundation,China(No.ZR2019LZH003)。
文摘Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can handle only one will result in prediction bias in reality.Existing disk failure prediction methods simply fuse various models,lacking discussion of training data preparation and learning patterns when facing multiple issues,although the solutions to different issues often conflict with each other.As a result,we first explore the training data preparation for multiple issues via a data partitioning pattern,i.e.,our proposed multi-property data partitioning(MDP).Then,we consider learning with the partitioned data for multiple issues as learning multiple tasks,and introduce the model-agnostic meta-learning(MAML)framework to achieve the learning.Based on these improvements,we propose a novel disk failure prediction model named MDP-MAML.MDP addresses the challenges of uneven partitioning and difficulty in partitioning by time,and MAML addresses the challenge of learning with multiple domains and minor samples for multiple issues.In addition,MDP-MAML can assimilate emerging issues for learning and prediction.On the datasets reported by two real-world data centers,compared to state-of-the-art methods,MDP-MAML can improve the area under the curve(AUC)and false detection rate(FDR)from 0.85 to0.89 and from 0.85 to 0.91,respectively,while reducing false alarm rate(FAR)from 4.88%to 2.85%.
基金Project (No. 1104-03) supported by the Aviation Propulsion Technology Development Program, China
文摘To investigate the ballistic resistance and failure pattern of aeroengine casing following the impact of disk fragments, and to determine the optimum case structure, the phenomena of a 1/3rd disk fragment impact on single and double-layered thin plate targets were simulated using nonlinear dynamical analysis software MSC.Dytran. Strain rate effect was introduced in a Johnson-Cook (JC) material model for the disk fragment and the plate. Impact modeling was based on the Arbitrary Lagrange-Eulerian method, and simulated using explicit finite element method (FEM). Simulation results showed that the major failure pattern of the plate is shearing and tensile fracture with large plastic deformation. It was also concluded that the ballistic limit velocity increases with the standoff distance when it is beyond a certain value, and that greater resistance is obtained when the front plate has either a proportionately low or high thickness. The impact resistance of a double-layered plate may exceed that of a single plate if the thicknesses and standoff distance of the two plates are set appropriately.
